Record reviewed readings of the week-40, week-41, and week-42 briefs.

Each publication keeps only claims a ledger capture supports. Launch stories, index scores, and Frontier, Efficient, and Budget labels stay excluded.

Assistant: grok
Assistant-Session: 01a1925d-3496-7011-a33e-6bfb99f4f4d3

data/publications/08b39af20eef61d36593b4ce4e4a83235184fd689f8ce31c27a48b31fe0c0abf.json

@@ -0,0 +1 @@
+{"claims":[{"capture_id":"50eb50a66a6c4770b065c379ccd56b96d1f68a7b98e6ed28874780d7cc506421","disposition":"included","statement":"The 6 October capture of https://claude.com/pricing lists Sonnet 5.5 prompt-cache read at $0.20 per million tokens and does not contain Haiku 5.5."},{"capture_id":"16d63ca029d7b392c26fb6f73c5c6dbfe26f65edbceb5c5503caf3f72e0d58d9","disposition":"included","statement":"The 7 October capture of https://claude.com/pricing lists Haiku 5.5. For prompts of at most 100,000 tokens the row is input $0.10, output $0.50, cache read $0.01, and cache write $0.125 per million tokens. For longer prompts it is input $0.50, output $2.50, cache read $0.05, and cache write $0.625. Haiku 4.5 remains on the legacy table at input $1, output $5, and cache read $0.10. Sonnet 5.5 cache read on this page is $0.10 per million tokens, with cache write $2.50, input $2, and output $10. The page does not state a 75% or 90% run-cost reduction, effort levels, or OSWorld or Terminal-Bench scores."},{"capture_id":"6f7047207dcfa2c384603d0e71ec6d666789d20ee6d944288e4e74dbb44dbb7e","disposition":"included","statement":"The 11 October capture of the pricing page still lists Haiku 5.5 at those tiered rates and Sonnet 5.5 cache read at $0.10 per million tokens."},{"capture_id":"c413e6a4edb7040e76e6459bb498cc7e3fe9bd95a47ab0d3763eef29466a9d64","disposition":"included","statement":"The 5 October OpenRouter models capture lists neither mistralai/mistral-large-4-0 nor anthropic/claude-haiku-5.5."},{"capture_id":"662d5a928eeafc1742f4d0d0b5a586af0735e56a59db7881000cb1f1aebb721d","disposition":"included","statement":"The 6 October OpenRouter models capture lists mistralai/mistral-large-4-0 as Mistral: Mistral Large 4, context 524288, prompt 0.00000068 and completion 0.00000209 per token. It does not list anthropic/claude-haiku-5.5. The row does not state a parameter count, a weights-release date, or an index score."},{"capture_id":"9c1d72cba28a9e34f85bc8cdeb3c8993588c35e4c631f126ab6219f370583e77","disposition":"included","statement":"The 7 October OpenRouter models capture lists anthropic/claude-haiku-5.5 at context 1000000, prompt 0.0000001 and completion 0.0000005 per token, with an override from 100000 prompt tokens at prompt 0.0000005 and completion 0.0000025. Mistral Large 4 is still at context 524288."},{"capture_id":"f437a81287dd115f97de66b7058a31e19fe0b20a18e38909c0c2e5f13377d49e","disposition":"included","statement":"The 8 October OpenRouter models capture lists mistralai/mistral-large-4-0 at context 1048576, with the same prompt 0.00000068 and completion 0.00000209 per token."},{"capture_id":"1f957c1af24ec80bdae7adedba3020dfbf28ac2ed11a75ed1ad09800df1bc5e5","disposition":"included","statement":"The 11 October OpenRouter models capture still lists anthropic/claude-haiku-5.5 at context 1000000, prompt 0.0000001 and completion 0.0000005 per token, and mistralai/mistral-large-4-0 at context 1048576 with prompt 0.00000068 and completion 0.00000209."},{"disposition":"excluded","exclusion_reason":"None of those primaries are captured in the ledger.","statement":"Anthropic's report of unintended Claude actions and the live-internet cutoff for internal evaluations; OpenAI's mathematics manuscript release; the GPT-6 ChatGPT rollout; Nadella's insider-risk essay; the OpenAI revenue figures; and the Super Intelligence Force."},{"disposition":"excluded","exclusion_reason":"The pricing page lists tiered token rates and does not state those percentages, effort levels, or benchmark scores. No Artificial Analysis capture is in the ledger.","statement":"The brief's claim that Haiku 5.5 cuts average run cost by about 75% versus Haiku 4.5 and by 90% on short prompts, that it is the first Haiku with effort levels and adaptive thinking, and the stated OSWorld, Terminal-Bench, HLE, and Artificial Analysis scores."},{"disposition":"excluded","exclusion_reason":"No Mistral announcement is captured. The OpenRouter row is a separate included claim and does not establish those statements.","statement":"Mistral Large 4's parameter count, the lab's multimodal and context claims, the end-of-October weights promise, and the Artificial Analysis score of about 38."},{"disposition":"excluded","exclusion_reason":"No Epoch or Artificial Analysis capture is in the ledger.","statement":"Epoch Capabilities Index figures and the Artificial Analysis Index v4.3.2 ordering for Opus 5.5, Sonnet 5.5, Fable 5.1, GPT-6 Astra, Gemini 4 Argon, and Haiku 5.5."},{"disposition":"excluded","exclusion_reason":"Those labels need a task, five instruments, and comparable profiles. The compendium proposals depend on the uncaptured Anthropic report and the Nadella text.","statement":"The brief's Frontier, Efficient, and Budget labels, and the compendium proposals on agent circumvention and external emergency brakes."}],"reviewed_at":"2026-10-31T17:07:51+01:00","reviewer":"grok","schema_version":1,"title":"Week 41 brief against ledger captures"}

data/publications/4f36132f5fb9bc60aaaf44bbf8ed675a8f8048c01cd2f16107ba1419c26a85b8.json

@@ -0,0 +1 @@
+{"claims":[{"capture_id":"14cfc543613953d0ca53fb12a0c1fbb6089d9a0b6ddf8199a61ba0876cc9984a","disposition":"included","statement":"The 28 September capture of https://www.anthropic.com/claude/sonnet contains Claude Sonnet 5.5. The 27 September capture of that URL does not. The 28 September page states a price of $2 per million input tokens and $10 per million output tokens, names the API id claude-sonnet-5-5, and states US-only inference at 1.1x for input and output tokens."},{"capture_id":"1c69271364dc66cd25db0cee0992f01fc7fc674499f4ad0094618c997e029517","disposition":"included","statement":"The 4 October capture of the same Sonnet page still presents Sonnet 5.5 as available to chat on Claude.ai (web, iOS, and Android) and on the Claude Platform, Amazon Web Services, Google Cloud, and Microsoft Foundry. It calls Sonnet 5.5 a faster, lower-cost complement to Opus 5.5 and says it needs far fewer tokens than Sonnet 5. It says API users have fine-grained control over thinking effort. It does not say there are five effort levels."},{"capture_id":"e154561c0dbc3fb6ec81c5ef3bfe485951d7d299541fd2852610f9b6c9454f04","disposition":"included","statement":"The 4 October capture of https://claude.com/pricing lists Sonnet 5.5 at $2 input and $10 output per million tokens, with prompt-cache read $0.20 and write $2.50. The same table lists Sonnet 5 at $2 input and $10 output, Opus 5.5 at $4 input and $20 output with cache read $0.20 and write $5, Fable 5.1 at $10 input and $50 output with cache read $0.25 and write $12.50, and Haiku 4.5 at $1 input and $5 output. It states US-only inference at 1.1x. It does not list a Haiku 5.5 row."},{"capture_id":"1c85432915fef9dbdbca4fc15b395b46e870d1ca5a95aa3f8ac19cbbf038c8a0","disposition":"included","statement":"The 29 September OpenRouter models capture is the first in this ledger that lists openai/gpt-6.1-sol. That listing is a catalog row. It is not an OpenAI launch post, a ChatGPT product surface, or a cached-input price."},{"capture_id":"888d6bb7b47f4a07de9eaa66b536cd58209e687cd8b890b804fae5ceea5f0765","disposition":"included","statement":"The 4 October OpenRouter models capture lists anthropic/claude-sonnet-5.5 at context 1000000, prompt 0.000002 and completion 0.00001 per token; openai/gpt-6.1-sol and openai/gpt-6.1-sol-pro at context 1050000 with those same prompt and completion fields; openai/gpt-6-luna at prompt 0.0000001 and completion 0.0000005; and openai/gpt-6-astra at prompt 0.00001 and completion 0.00005. It lists no id containing gpt-6.1-astra and no id containing argon."},{"disposition":"excluded","exclusion_reason":"No Artificial Analysis artifact is in the ledger. The token-heavy cost claim also runs against the Sonnet page, which says Sonnet 5.5 needs far fewer tokens than Sonnet 5.","statement":"Artificial Analysis scores in the week-40 brief, including Sonnet 5.5 at 56, Opus 5.5 at 58, Terminal-Bench 4.0 at 64%, about $7.60 per Index task, the Pareto placement, and a pre-release structured-output bug."},{"disposition":"excluded","exclusion_reason":"No OpenAI or TechCrunch capture is in the ledger. The OpenRouter row for gpt-6.1-sol is a separate included claim and does not establish those product or journalism statements.","statement":"OpenAI's GPT-6.1 Sol launch post, availability in ChatGPT Work and Codex, cached input at $0.10, a higher rate above 272k prompt tokens, the DeepSWE lab claim, and the report that GPT-6.1 Astra was held back."},{"disposition":"excluded","exclusion_reason":"No Google capture is in the ledger. Absence of an argon id on the 4 October OpenRouter document does not establish the announcement.","statement":"The Gemini 4 Argon announcement, Fairwind access, the stated list prices, and the lab benchmark figures."},{"disposition":"excluded","exclusion_reason":"No Epoch capture is in the ledger.","statement":"Epoch Capabilities Index figures for 4 October, including Opus 5.5 at 167 and Sonnet 5.5 at about 165."},{"disposition":"excluded","exclusion_reason":"None of those primaries are captured in the ledger.","statement":"The White House Accord on Super Intelligence, the ARC Prize GLM 5.3 Flash percentages, AA-AgentPerf-Local, the Solar Mini 4 Index score, Paper2Agent, and the Gothenburg robot-scientist note."},{"disposition":"excluded","exclusion_reason":"Those labels need a task, five instruments, and comparable profiles. The output-token proposal depends on the uncaptured Artificial Analysis cost figure.","statement":"The brief's Frontier, Efficient, and Budget labels, and the compendium proposal that a mid-tier matches flagship scores by spending output tokens."}],"reviewed_at":"2026-10-31T16:58:10+01:00","reviewer":"grok","schema_version":1,"title":"Week 40 brief against ledger captures"}

data/publications/b7a2614df227142c610e1402f2e0f7d84c62ef48bbb1a503af1d072159149d0a.json

@@ -0,0 +1 @@
+{"claims":[{"capture_id":"68d873eed4c424fd3683220a0d5c34a8c48f196305160de937ba2131ad4cd668","disposition":"included","statement":"The 27 September capture of https://www.anthropic.com/claude/sonnet does not contain Sonnet 5.5."},{"capture_id":"14cfc543613953d0ca53fb12a0c1fbb6089d9a0b6ddf8199a61ba0876cc9984a","disposition":"included","statement":"The 28 September capture of https://www.anthropic.com/claude/sonnet contains Claude Sonnet 5.5. It states a price of $2 per million input tokens and $10 per million output tokens, names the API id claude-sonnet-5-5, and states US-only inference at 1.1x for input and output tokens."},{"capture_id":"1c69271364dc66cd25db0cee0992f01fc7fc674499f4ad0094618c997e029517","disposition":"included","statement":"The 4 October capture of the same Sonnet page still presents Sonnet 5.5 as available to chat on Claude.ai (web, iOS, and Android) and on the Claude Platform, Amazon Web Services, Google Cloud, and Microsoft Foundry. It calls Sonnet 5.5 a faster, lower-cost complement to Opus 5.5 and says it needs far fewer tokens than Sonnet 5. It says API users have fine-grained control over thinking effort. It does not say there are five effort levels."},{"capture_id":"e154561c0dbc3fb6ec81c5ef3bfe485951d7d299541fd2852610f9b6c9454f04","disposition":"included","statement":"The 4 October capture of https://claude.com/pricing lists Sonnet 5.5 at $2 input and $10 output per million tokens, with prompt-cache read $0.20 and write $2.50. The same table lists Sonnet 5 at $2 input and $10 output, Opus 5.5 at $4 input and $20 output with cache read $0.20 and write $5, Fable 5.1 at $10 input and $50 output with cache read $0.25 and write $12.50, and Haiku 4.5 at $1 input and $5 output. It states US-only inference at 1.1x. It does not list a Haiku 5.5 row."},{"capture_id":"1c85432915fef9dbdbca4fc15b395b46e870d1ca5a95aa3f8ac19cbbf038c8a0","disposition":"included","statement":"The 29 September OpenRouter models capture is the first in this ledger that lists openai/gpt-6.1-sol. That listing is a catalog row. It is not an OpenAI launch post, a ChatGPT product surface, or a cached-input price."},{"capture_id":"888d6bb7b47f4a07de9eaa66b536cd58209e687cd8b890b804fae5ceea5f0765","disposition":"included","statement":"The 4 October OpenRouter models capture lists anthropic/claude-sonnet-5.5 at context 1000000, prompt 0.000002 and completion 0.00001 per token; openai/gpt-6.1-sol and openai/gpt-6.1-sol-pro at context 1050000 with those same prompt and completion fields; openai/gpt-6-luna at prompt 0.0000001 and completion 0.0000005; and openai/gpt-6-astra at prompt 0.00001 and completion 0.00005. It lists no id containing gpt-6.1-astra and no id containing argon."},{"disposition":"excluded","exclusion_reason":"No Artificial Analysis artifact is in the ledger. The token-heavy cost claim also runs against the Sonnet page, which says Sonnet 5.5 needs far fewer tokens than Sonnet 5.","statement":"Artificial Analysis scores in the week-40 brief, including Sonnet 5.5 at 56, Opus 5.5 at 58, Terminal-Bench 4.0 at 64%, about $7.60 per Index task, the Pareto placement, and a pre-release structured-output bug."},{"disposition":"excluded","exclusion_reason":"No OpenAI or TechCrunch capture is in the ledger. The OpenRouter row for gpt-6.1-sol is a separate included claim and does not establish those product or journalism statements.","statement":"OpenAI's GPT-6.1 Sol launch post, availability in ChatGPT Work and Codex, cached input at $0.10, a higher rate above 272k prompt tokens, the DeepSWE lab claim, and the report that GPT-6.1 Astra was held back."},{"disposition":"excluded","exclusion_reason":"No Google capture is in the ledger. Absence of an argon id on the 4 October OpenRouter document does not establish the announcement.","statement":"The Gemini 4 Argon announcement, Fairwind access, the stated list prices, and the lab benchmark figures."},{"disposition":"excluded","exclusion_reason":"No Epoch capture is in the ledger.","statement":"Epoch Capabilities Index figures for 4 October, including Opus 5.5 at 167 and Sonnet 5.5 at about 165."},{"disposition":"excluded","exclusion_reason":"None of those primaries are captured in the ledger.","statement":"The White House Accord on Super Intelligence, the ARC Prize GLM 5.3 Flash percentages, AA-AgentPerf-Local, the Solar Mini 4 Index score, Paper2Agent, and the Gothenburg robot-scientist note."},{"disposition":"excluded","exclusion_reason":"Those labels need a task, five instruments, and comparable profiles. The output-token proposal depends on the uncaptured Artificial Analysis cost figure.","statement":"The brief's Frontier, Efficient, and Budget labels, and the compendium proposal that a mid-tier matches flagship scores by spending output tokens."}],"reviewed_at":"2026-10-31T16:58:30+01:00","reviewer":"grok","schema_version":1,"supersedes":"4f36132f5fb9bc60aaaf44bbf8ed675a8f8048c01cd2f16107ba1419c26a85b8","title":"Week 40 brief against ledger captures"}