docs(codec): PR-X12 substrate merged-canon — session A + B synthesis#196
Merged
Conversation
Lands `.claude/knowledge/pr-x12-codec-cognitive-substrate-mapping.md` (~576 lines) as the survives-compaction companion to the as-shipped `pr-x12-codec-x265-design.md`. Generalises the codec spec across the four industries it implicitly unifies (HEVC video, Gaussian splat, cognitive shaders / sparse attention, gradient compression for LLM training). # Why this doc Triggered by the PR #195 review session. PR-X12's mode taxonomy (Skip/Merge/Delta/Escape) shows up under different names in four disconnected research communities; each treats its own corner as the central knob (HEVC RDO, ZeRO buckets, splat sparsity reg, attention pruning). Without explicit naming of the unification, future agents will rediscover each corner independently and reimplement what the codec already provides. # Structure (citable by section number) - §0 — the big claim (PR-X12 is the gradient-quantisation substrate GenAI training has been missing for two years) - §1 — four-axis mapping table (x265 / splat / cognitive / gradient) - §2-§7 — deep mappings (mode taxonomy, CTU quad-tree, palette/basin codebook, transform basis, rANS, λ-RDO) - §8 — 15 numbered epiphanies (E-1..E-15) - §9 — 7 holy grail claims (H-1..H-7) - §10 — integration plan per sub-card (A4/A6/A7/A8) + 3 new PRs (splat, cognitive, gradient consumers) - §11 — exploration paths ranked by confidence (15 entries) - §12 — technical debt inventory (23 items T-1..T-23 across codec, ndarray substrate, lance-graph cognitive, cross-repo, PR #195) - §13 — 6 blasgraph/MKL synergies the HEVC team couldn't reach in 2013 (block-matched ME, batched DCT, partition tree as tropical- GEMM, CABAC replacement, learned deblocking, k-means at frame rate) - §14 — cross-references (design docs, rules, code paths) - §15 — how to use this doc (read order per use case) # Holy grail claims (load-bearing, citable) - H-1: PR-X12 + cam_pq is the HEVC SCC codec 2013 hardware couldn't build (4096-entry codebook at 60 fps) - H-2: The transform IS the optimiser (DCT-II ↔ Adam ↔ KFAC ↔ learned conv all share `Δ' = B·Δ`) — most underrated mapping - H-3: CTU quad-tree is the universal hierarchical-attention substrate (Mistral sliding window is depth-3 leaf processing) - H-4: rANS + k-means achieves Shannon-optimal lossless gradient compression (every published scheme is a special case) - H-5: PR-X12 generalises ZeRO (Merge captures parameter sharing that ZeRO's 3-bucket scheme can't) - H-6: 64×64 CTU is the right unit for both 4K video and 7B LLMs - H-7: The codec is the substrate; everything else is a renaming # Technical debt (23 items) Severity gradient P0/P1/P2/P3. Notable open items: - T-1, T-2: PR #195 CodeRabbit findings (BASIN_NONE collision + unwrap_or non-bijection) — actionable today - T-10..T-15: ndarray substrate (HPC graduation incomplete, no `Transform` trait yet, NEON tile-GEMM stub) - T-20..T-23: cross-repo coordination (cognitive-substrate- convergence-v1.md cross-ref, causal-edge v2 metadata wiring) # Board hygiene AGENT_LOG.md prepended with the session entry per CLAUDE.md rule "every PR adding a finding/agent run must PREPEND an AGENT_LOG entry in the same commit". Entry cites the doc structure, the 15 epiphanies + 7 holy grails by ID, and the 23 debt items. # No code changes Pure architecture / knowledge artifact. `cargo check --lib` clean (nothing to recheck). https://claude.ai/code/session_01HbqooFZHAjaUtFEzhA1R2u
621-line synthesis doc consolidating two parallel architecture threads on PR-X12's predictive-coder substrate: - Session A: pr-x12-codec-cognitive-substrate-mapping.md (cognitive shaders ↔ gradient ↔ HEVC mapping, this branch) - Session B: pr-x12-cross-domain-synergies.md (x265 ⇄ 3DGS ⇄ attention ⇄ SGD, merged to master via PR #195 commit 01c77cc) Both originals retained for archeology; merged-canon supersedes them for new content. Structure: - §1 overlap matrix (epiphanies, holy grails, plans, debt — unique vs shared between A and B) - §2 architectural claim with two-route falsifiability - §3 ten merge-only epiphanies (M:E-A..M:E-J) — the high-density section: universal LinearReduce<Basis> kernel, Morton+raster as space-filling curve, PR #195 CodeRabbit findings generalise to all four domains, ndarray-codec as 5th architectural category, three domain-specific plug-points only - §4 unified holy grail list (A:H + B:HG + M:H + 2 new M:H-NEW) - §5 unified plan with resolved critical path (B's A7-first wins, front-load A4-design) - §6 sequencing DAG - §7 unified technical debt (P0/P1/P2/P3 reranked across both docs) - §8 resolves 4 disagreements between A and B (each with winner + rationale) - §9 read order for the 4-doc family - §10 compaction-preservation contract (8 invariants) Key merge-only outputs: - Three load-bearing traits: PredictiveSignal, LinearReduce<Basis>, CurveOrder<const N> - M:H-NEW-1: single Rust binary consumes video|splat|gradient|kv-cache → compressed Lance column (the falsifiability test, Plan G builds it) - M:H-NEW-2: ~1.5 KLoC generic + ~200 LoC per domain = ~2 KLoC for four industries (25× code-density vs per-domain impls) Three new integration plans: - Plan G: multi-domain bench harness (2 weeks, MUST ship before A7) - Plan H: extract `ndarray-codec` crate (3 days, resolves dep-cycle) - Plan I: trait PredictiveSignal in protocol (3 days, bit-pattern isomorphism with splat without code merge) Citation IDs preserved from both originals: cite as (A:E-N), (B:E-N), (M:E-X). No code changes; pure synthesis. Cargo check clean.
Contributor
📝 WalkthroughWalkthroughThis PR adds/updates PR‑X12 architecture documentation (session log, refreshed spec, merged canonical spec) and modifies codec code to use the full 12-bit basin index (MAX_BASIN_IDX = 4095), removing the BASIN_NONE sentinel helper and related public re-exports and tests. ChangesPR-X12 Architecture Specification and Consolidation
Codec basin/API changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Warning Review ran into problems🔥 ProblemsGit: Failed to clone repository. Please run the Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In @.claude/knowledge/pr-x12-codec-cognitive-substrate-mapping.md:
- Around line 56-61: The Markdown file contains multiple untyped fenced code
blocks (e.g., the block starting with "Skip (2 bytes total) ⊂ free" and the
blocks listing "depth 0 … depth 3" variants) which trip markdownlint MD040;
update each triple-backtick fence to include the language identifier `text`
(e.g., replace ``` with ```text) for every occurrence mentioned (the blocks
around the "Skip/Merge/Delta/Escape" table and the three "depth 0–3" examples)
so the content stays identical but linting passes.
In @.claude/knowledge/pr-x12-substrate-merged-canon.md:
- Around line 6-7: The markdown triggers MD027/MD040/MD038 due to incorrect
list/blockquote markers, malformed code fences, and improper inline emphasis;
fix by converting the mis‑prefixed lines into a proper fenced code block using
```text with matching closing fence, remove leading '-' list markers inside that
code fence (e.g., the "ndarray = hardware..." and "ndarray-codec = ..." lines),
restore the bold line to "**Total stack..." (remove stray '-' prefix and change
"IS" to "is"), and ensure any inline code spans use backticks without
surrounding hyphens or stray punctuation so the blocks (the ASCII diagram fence
and the small inline code examples) pass markdownlint MD027/MD040/MD038 checks.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro Plus
Run ID: 6fc0db58-aa77-408f-bbf8-cda1d5e020b0
📒 Files selected for processing (3)
.claude/board/AGENT_LOG.md.claude/knowledge/pr-x12-codec-cognitive-substrate-mapping.md.claude/knowledge/pr-x12-substrate-merged-canon.md
Comment on lines
+6
to
+7
| > - `pr-x12-codec-cognitive-substrate-mapping.md` (session A: opus 4.7 main thread, this branch) | ||
| > - `pr-x12-cross-domain-synergies.md` (session B: parallel thread, PR #195 branch, commit `01c77ccc`) |
Contributor
There was a problem hiding this comment.
Clean up markdownlint issues in blockquote, code fences, and inline code spans.
This section currently triggers MD027/MD040/MD038; small formatting edits should make the doc lint-clean.
Proposed doc-lint fix
-> - `pr-x12-codec-cognitive-substrate-mapping.md` (session A: opus 4.7 main thread, this branch)
-> - `pr-x12-cross-domain-synergies.md` (session B: parallel thread, PR `#195` branch, commit `01c77ccc`)
+> - `pr-x12-codec-cognitive-substrate-mapping.md` (session A: opus 4.7 main thread, this branch)
+> - `pr-x12-cross-domain-synergies.md` (session B: parallel thread, PR `#195` branch, commit `01c77ccc`)
-```
+```text
- ndarray = hardware (SIMD, Palette, Base17, SpoDistanceMatrices, read_bgz7_file)
- ndarray-codec = compression substrate (Ctu, LeafCu, predict_intra, rANS) ← NEW
- lance-graph = thinking (NarsTruth, NarsEngine, TripleModel, AutocompleteCache)
- causal-edge = protocol (CausalEdge64, NarsTables, forward/learn)
- p64 = convergence highway (both repos meet here)-Total stack for all four industries: ~2 KLoC. Compared to ~50 KLoC per-domain implementations elsewhere. The 25× code-density delta IS the architectural payoff that justifies the eight sub-cards.
+Total stack for all four industries: ~2 KLoC. Compared to ~50 KLoC per-domain implementations elsewhere. The 25× code-density delta is the architectural payoff that justifies the eight sub-cards.
- +text
┌──────────────────────────────────────┐
│ Plan G (multi-domain bench) │
│ 2 weeks — UNFALSIFIABILITY GATE │
└──────────────────┬───────────────────┘
...
│ All unlocked │
└─────────────────┘
Also applies to: 165-171, 303-304, 411-455
🧰 Tools
🪛 markdownlint-cli2 (0.22.1)
[warning] 6-6: Multiple spaces after blockquote symbol
(MD027, no-multiple-space-blockquote)
[warning] 7-7: Multiple spaces after blockquote symbol
(MD027, no-multiple-space-blockquote)
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In @.claude/knowledge/pr-x12-substrate-merged-canon.md around lines 6 - 7, The
markdown triggers MD027/MD040/MD038 due to incorrect list/blockquote markers,
malformed code fences, and improper inline emphasis; fix by converting the
mis‑prefixed lines into a proper fenced code block using ```text with matching
closing fence, remove leading '-' list markers inside that code fence (e.g., the
"ndarray = hardware..." and "ndarray-codec = ..." lines), restore the bold line
to "**Total stack..." (remove stray '-' prefix and change "IS" to "is"), and
ensure any inline code spans use backticks without surrounding hyphens or stray
punctuation so the blocks (the ASCII diagram fence and the small inline code
examples) pass markdownlint MD027/MD040/MD038 checks.
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 4529c01f2c
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
|
|
||
| ### 4.1 The 12-bit basin = 4096-entry vocabulary | ||
|
|
||
| `MAX_BASIN_IDX = (1 << 12) - 1 = 4095` (`mode.rs:71`). Each `LeafCu` carries a 12-bit index into the per-frame basin codebook. For: |
There was a problem hiding this comment.
This section states MAX_BASIN_IDX = 4095 and frames the BASIN_NONE collision fix as pending, but src/hpc/codec/mode.rs in this commit already ships MAX_BASIN_IDX = 4094 with BASIN_NONE = 4095. Keeping the old values here can cause downstream design/docs work to assume the wrong valid basin range and reintroduce the resolved sentinel-collision bug in new consumers.
Useful? React with 👍 / 👎.
Two CodeRabbit MD040/MD027 findings + one Codex P2 stale-fact finding, all verified valid against current code. CodeRabbit (markdownlint): - pr-x12-codec-cognitive-substrate-mapping.md: 4 untyped code fences → ```text (Skip/Merge/Delta block at line 56; depth-0..3 quad-tree blocks for spatial/attention/gradient hierarchies at lines 80/91/104) - pr-x12-substrate-merged-canon.md: collapse `> - ` to `> - ` (lines 6-7, MD027 multi-space-after-blockquote), 2 untyped fences → ```text (architecture-rule list at line 165, sequencing diagram at line 411), and "delta IS" → "delta is" stylistic Codex P2 (stale doc vs shipped code): - Doc cited `MAX_BASIN_IDX = 4095` and framed BASIN_NONE collision as "pending / not yet merged / not yet pushed" — but PR #195 commit 2423298 already shipped `MAX_BASIN_IDX = 4094` with `BASIN_NONE = 4095` reserved sentinel, plus bijective `pack_leaf` via `?` operator with 3 regression tests. Updated: - §4.1 line 125: `MAX_BASIN_IDX = 4094` + sentinel-range explainer - §4.3 heading + body: "(resolved in PR #195)" with commit cite - §"Still open on PR #195" block: → "Resolved in PR #195 follow-up" - §12 debt-inventory T-1, T-2: marked ~~RESOLVED~~ with commit ref No content edits beyond what the findings asked for; citation IDs unchanged.
Contributor
There was a problem hiding this comment.
♻️ Duplicate comments (1)
.claude/knowledge/pr-x12-substrate-merged-canon.md (1)
303-303:⚠️ Potential issue | 🟡 Minor | ⚡ Quick winFix MD038: Remove space inside code span.
The inline code spans have improper spacing that triggers markdownlint MD038.
📝 Proposed fix
-**M:H-NEW-2** — `trait PredictiveSignal` + `trait LinearReduce<Basis>` + `trait CurveOrder<const N: usize>` factor the codec into three plug-points (per M:E-E + M:E-A + M:E-B). The codec body is `<150 LoC of generic glue. Domain consumers ship `<200 LoC` of trait impls. **Total stack for all four industries: ~2 KLoC.** Compared to ~50 KLoC per-domain implementations elsewhere. The 25× code-density delta is the architectural payoff that justifies the eight sub-cards. +**M:H-NEW-2** — `trait PredictiveSignal` + `trait LinearReduce<Basis>` + `trait CurveOrder<const N: usize>` factor the codec into three plug-points (per M:E-E + M:E-A + M:E-B). The codec body is `<150 LoC` of generic glue. Domain consumers ship `<200 LoC` of trait impls. **Total stack for all four industries: ~2 KLoC.** Compared to ~50 KLoC per-domain implementations elsewhere. The 25× code-density delta is the architectural payoff that justifies the eight sub-cards.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In @.claude/knowledge/pr-x12-substrate-merged-canon.md at line 303, The Markdown has code spans with extra spaces inside the backticks (e.g. "` trait PredictiveSignal`", "` trait LinearReduce<Basis>`", "` trait CurveOrder<const N: usize>`"); remove the leading/trailing spaces inside each inline code span so the identifiers are exactly `PredictiveSignal`, `LinearReduce<Basis>`, and `CurveOrder<const N: usize>` (and any other similarly spaced inline spans) to satisfy MD038.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Duplicate comments:
In @.claude/knowledge/pr-x12-substrate-merged-canon.md:
- Line 303: The Markdown has code spans with extra spaces inside the backticks
(e.g. "` trait PredictiveSignal`", "` trait LinearReduce<Basis>`", "` trait
CurveOrder<const N: usize>`"); remove the leading/trailing spaces inside each
inline code span so the identifiers are exactly `PredictiveSignal`,
`LinearReduce<Basis>`, and `CurveOrder<const N: usize>` (and any other similarly
spaced inline spans) to satisfy MD038.
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro Plus
Run ID: ef891cf5-d46e-4871-b359-fbfb1a22b534
📒 Files selected for processing (2)
.claude/knowledge/pr-x12-codec-cognitive-substrate-mapping.md.claude/knowledge/pr-x12-substrate-merged-canon.md
✅ Files skipped from review due to trivial changes (1)
- .claude/knowledge/pr-x12-codec-cognitive-substrate-mapping.md
… codebook PR #195's follow-up commit 2423298 resolved the BASIN_NONE/MAX_BASIN_IDX collision by shrinking MAX_BASIN_IDX to 4094 with BASIN_NONE = 4095 as a distinct sentinel. The shrink was the wrong fix — the sentinel itself was the bug. Reference (the authoritative source the code drifted from): src/hpc/ogit_bridge/assets/cognitive/entities/Leaf.ttl — the HHTL ontology defines the codebook as 16 Hips × 16 Twigs × 16 Leaves = 4096 Leaves per Heel, every Leaf carrying a real basinSignature. No slot is reserved for absence; the ontology forbids "no basin". What BASIN_NONE actually was: authoring-time epistemic uncertainty ("encoder hasn't decided yet for this cell") smuggled into wire-format ontological uncertainty ("this cell exists but has no basin"). A category error — Rust's idiom would have surfaced this as Option<u16> in the encoder's transient scratch state and a plain u16 on the persistent record. The sentinel value bypassed that hygiene by hiding optionality inside a magic u16, invisible to the typechecker. Confirmation that the sentinel was load-bearing for nothing: full audit of BASIN_NONE producers across src/ found zero — no LeafCu::skip(...), no basin_idx: BASIN_NONE anywhere. The only references were the const definition, a re-export, one regression test that constructed it, and predict.rs:is_no_basin (a predicate with no callers that emit BASIN_NONE leaves). Defensive infrastructure for a feature the ontology forbids and the implementation never used. Changes: - mode.rs: MAX_BASIN_IDX = (1 << 12) - 1 = 4095 (full 12-bit range, 4096 real basins). BASIN_NONE deleted. The 2 sentinel-distinctness regression tests replaced with one test asserting the full range. Docs reframed around the HHTL ontology + the Option<u16> scratch-state contract. - predict.rs: is_no_basin deleted; its only doctest+test deleted. BASIN_NONE import dropped. - mod.rs: BASIN_NONE and is_no_basin removed from re-exports. - pr-x12-codec-cognitive-substrate-mapping.md §4.1/§4.3/§10.1/§12: framing updated. §4.3 now records the full arc (collision → shrink → delete) as design archeology rather than as an open issue. Validation: - cargo check --features codec --lib → clean - cargo clippy --features codec --lib -- -D warnings → clean - cargo test --features codec --lib hpc::codec → 54 tests pass - cargo test --features codec --doc hpc::codec → 13 doctests pass Net diff: -77, +38 lines. Pure subtraction modulo doc reframe.
Drops the forensic call-outs and walks the docs back to the positive design statement: the codebook is 16 × 16 × 16 = 4096 Leaves per Heel (per Leaf.ttl), MAX_BASIN_IDX = 4095 addresses the full range. No narrative arc; no archeology subsection.
Two-layer rule sitting above MAX_BASIN_IDX: - encoder scratch state → Option<u16> - wire format / persisted → plain u16, every value real So the next editor doesn't reach for a magic value when what they actually want is type-level optionality.
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@src/hpc/codec/mode.rs`:
- Around line 62-79: The change makes 0xFFF a real basin value but breaks
compatibility with older payloads that used 0xFFF as a sentinel; update the
(de)serialization path in src/hpc/codec/mode.rs—specifically in the functions
that pack/unpack the 12-bit basin field (look for pack_leaf, unpack_leaf,
encode_leaf, decode_leaf or the Leaf struct's (de)serialize impl) to gate
behavior by an explicit format/version flag: when format < NEW_VERSION treat
0xFFF as the old sentinel and map it to Option::None (or the prior semantics),
and when format >= NEW_VERSION treat 0xFFF as basin 4095; alternatively add a
compatibility branch that rewrites incoming 0xFFF to the prior sentinel before
normal decoding and ensure outgoing encoders include the format version header
so older decoders can retain original behavior.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro Plus
Run ID: af51558f-a67b-440e-9121-2e08cd757521
📒 Files selected for processing (1)
src/hpc/codec/mode.rs
Comment on lines
+62
to
+79
| // ── Design invariant ──────────────────────────────────────────────── | ||
| // | ||
| // The 12-bit basin field addresses exactly one of 4096 real Leaves | ||
| // (HHTL ontology, see `src/hpc/ogit_bridge/assets/cognitive/entities/Leaf.ttl`: | ||
| // 16 Hips × 16 Twigs × 16 Leaves per Heel, every Leaf carries a real | ||
| // `basinSignature`). Do NOT reserve a value as a "no basin" / | ||
| // "not yet decided" sentinel. | ||
| // | ||
| // Rationale: that's authoring-time uncertainty (encoder mid-decision) | ||
| // leaking into wire-format ontological state. Keep optionality in the | ||
| // type, not in a magic value: | ||
| // | ||
| // - encoder scratch state → `Option<u16>` (Some = committed, None = TBD) | ||
| // - persisted / wire-format → plain `u16`, every value real | ||
| // | ||
| // The doubt must collapse to Some(basin) before the leaf is packed. | ||
| // Once a leaf reaches the wire it has a basin, period. | ||
|
|
Contributor
There was a problem hiding this comment.
Preserve compatibility for the reclaimed 0xFFF header value.
This change redefines a previously reserved wire value as a real basin. That means any pre-change payload containing 0xFFF will now deserialize as basin 4095, and any new payload using basin 4095 will be misread by older decoders as the old sentinel. Please gate this behind an explicit format version or add a compatibility path before changing the on-wire meaning.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@src/hpc/codec/mode.rs` around lines 62 - 79, The change makes 0xFFF a real
basin value but breaks compatibility with older payloads that used 0xFFF as a
sentinel; update the (de)serialization path in
src/hpc/codec/mode.rs—specifically in the functions that pack/unpack the 12-bit
basin field (look for pack_leaf, unpack_leaf, encode_leaf, decode_leaf or the
Leaf struct's (de)serialize impl) to gate behavior by an explicit format/version
flag: when format < NEW_VERSION treat 0xFFF as the old sentinel and map it to
Option::None (or the prior semantics), and when format >= NEW_VERSION treat
0xFFF as basin 4095; alternatively add a compatibility branch that rewrites
incoming 0xFFF to the prior sentinel before normal decoding and ensure outgoing
encoders include the format version header so older decoders can retain original
behavior.
9 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Pure-docs PR (no code changes). Lands two architecture docs on top of master:
pr-x12-codec-cognitive-substrate-mapping.md(+576 lines) — session A canonical (this thread, opus 4.7). Cross-stack mapping of PR-X12 codec primitives against four loads: x265 / 3D Gaussian splat / cognitive shaders / blasgraph-MKL gradient compression. 15 numbered epiphanies (E-1..E-15), 7 holy-grail claims (H-1..H-7), 23 technical-debt items (T-1..T-23), integration plan per sub-card (A4 / A6 / A7 / A8).pr-x12-substrate-merged-canon.md(+621 lines) — merged synthesis. Consolidates session A (this branch) and session B (pr-x12-cross-domain-synergies.md, already on master via PR feat(codec): PR-X12 A2 mode bit-pack + A3-intra prediction kernel #195 commit01c77ccc). Includes 10 merge-only epiphanies (M:E-A..M:E-J), 2 new holy-grail claims (M:H-NEW-1, M:H-NEW-2), 3 new integration plans (Plan G bench harness, Plan Hndarray-codeccrate extraction, Plan IPredictiveSignaltrait), and resolves 4 disagreements between A and B..claude/board/AGENT_LOG.md(+73 lines) — session-log entries documenting the architecture sessions.The doc family (read order)
The merged-canon's §9 names the canonical read order:
.claude/knowledge/pr-x12-codec-x265-design.md.claude/knowledge/pr-x12-substrate-merged-canon.md.claude/knowledge/pr-x12-codec-cognitive-substrate-mapping.md.claude/knowledge/pr-x12-cross-domain-synergies.mdThe architectural claim (testable)
PR-X12 is the universal predictive-coder substrate factored into three traits:
Net density claim (M:H-NEW-2): ~1.5 KLoC generic codec glue + ~200 LoC per domain consumer compresses video / Gaussian splats / LLM gradients / KV-cache through one Lance-backed wire format. The bench harness (Plan G, 2 weeks) is the falsifiability test — Plan G must ship before A7 rANS lands.
Reviewer invitation
This PR is here to attract scrutiny from multiple reviewers in parallel:
H-N/M:H-NEW-Nshould reduce to a buildable bench or be flagged speculative); (2) brokenfile:linereferences — the docs cite e.g.src/hpc/codec/mode.rs:194,src/hpc/codec/predict.rs:*,src/aabb.rs,src/palette_codec.rs; (3) citation-ID drift between the three docs (A:E-N vs B:E-N vs M:E-X must be 1-to-1 stable); (4) any new PR feat(codec): PR-X12 A2 mode bit-pack + A3-intra prediction kernel #195-style invariants (BASIN_NONE collision, non-bijective pack) that the docs miss for the four cross-domain consumers.Ctu<const N>; lossy Escape as feature vs debt; cross-repo dep direction via crate extraction). The reasoning is in §8 with named winners; counter-arguments welcome.pr-x12-cross-domain-synergies.mdgot dropped or mis-cited, flag it.Test plan
cargo check --features codec --lib— clean post-merge with masterfile:linerefs in the docs point at paths that exist on this branch after the master mergesrc/changes; pure.claude/additionsndarray-codeccrate extraction) doesn't break PR feat(codec): PR-X12 A2 mode bit-pack + A3-intra prediction kernel #195'ssrc/hpc/codec/module path during transitionThis PR is intentionally a docs-only landing so the architectural claims can be reviewed independently of any code change. No
src/mutation; the codec code is exactly what PR #195 shipped.Generated by Claude Code
Summary by CodeRabbit