{"schema_version":"onlylabs.public_signal.v1","title":"Anthropic Repo: anthropics/scone-bench","description":"Anthropic repo signal with public source context, captured evidence pages, related signals, and data-business radar classification.","url":"https://onlylabs.fyi/signals/0c515bfd-ccd4-4a21-868f-944fd4945f19","json_url":"https://onlylabs.fyi/signals/0c515bfd-ccd4-4a21-868f-944fd4945f19/signal.json","generated_at":"2026-06-11T02:42:11.785161+00:00","org":{"slug":"anthropic","name":"Anthropic","category":"frontier-lab","category_label":"Frontier lab","dossier_url":"https://onlylabs.fyi/labs/anthropic","dossier_json_url":"https://onlylabs.fyi/labs/anthropic/dossier.json"},"related_urls":{"signal":"https://onlylabs.fyi/signals/0c515bfd-ccd4-4a21-868f-944fd4945f19","signal_json":"https://onlylabs.fyi/signals/0c515bfd-ccd4-4a21-868f-944fd4945f19/signal.json","source":"https://github.com/anthropics/scone-bench","lab_dossier":"https://onlylabs.fyi/labs/anthropic","lab_dossier_json":"https://onlylabs.fyi/labs/anthropic/dossier.json","analysis":"https://onlylabs.fyi/analysis/anthropic","analysis_json":"https://onlylabs.fyi/analysis/anthropic/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/anthropic/evidence.json","category":"https://onlylabs.fyi/frontier","category_json":"https://onlylabs.fyi/frontier.json","category_feed":"https://onlylabs.fyi/frontier/feed.xml","category_signals_json":"https://onlylabs.fyi/signals.json","topic":null,"topic_signals_json":null,"topic_feed":null,"data_business":{"radar":"https://onlylabs.fyi/data-radar","radar_json":"https://onlylabs.fyi/data-radar.json","opportunities":"https://onlylabs.fyi/opportunities","opportunities_json":"https://onlylabs.fyi/opportunities.json","lanes":[{"key":"evals","label":"Evals and quality","url":"https://onlylabs.fyi/data-radar/evals","json_url":"https://onlylabs.fyi/data-radar/evals/signals.json"}]}},"answer_pack":{"answer":"Anthropic published anthropics/scone-bench (Python). This repository signal exposes tooling, eval, infrastructure, or model-adjacent work before it may appear in a launch post. High-signal details: repo anthropics/scone-bench · language Python · Low-star benchmark repo by Anthropic, routine. onlylabs links this event to 1 captured evidence page and 6 related repo signals. It also maps to Evals and quality in the data-business radar.","signal_desk":"repos","source_context":{"source_url":"https://github.com/anthropics/scone-bench","source_host":"github.com","occurred_at":"2026-05-12T22:17:19+00:00","first_seen_at":"2026-06-05T05:42:58.841369+00:00","date_source":"source","context":"Python"},"context_markers":[{"label":"Lab","value":"Anthropic","source":"signal"},{"label":"Signal desk","value":"repos","source":"signal"},{"label":"Source host","value":"github.com","source":"source"},{"label":"Repository","value":"anthropics/scone-bench","source":"source"},{"label":"Language","value":"Python","source":"source"},{"label":"Stars","value":"21","source":"traction"},{"label":"Notability","value":"Low-star benchmark repo by Anthropic, routine","source":"signal"},{"label":"Radar lane","value":"Evals and quality","source":"radar"},{"label":"Matched term","value":"eval","source":"radar"},{"label":"Matched term","value":"benchmark","source":"radar"},{"label":"Watch term","value":"Eval methodology","source":"evidence"},{"label":"Watch term","value":"Data pipeline","source":"evidence"},{"label":"Watch term","value":"Infrastructure","source":"evidence"},{"label":"Watch term","value":"Safety and alignment","source":"evidence"},{"label":"Watch term","value":"Agents and tool use","source":"evidence"}],"evidence_coverage":{"target_pages":1,"captured_pages":1,"readable_pages":1,"capture_methods":["plain"],"missing_page_urls":[],"failed_page_urls":[],"blocked_page_urls":[],"page_urls":["https://github.com/anthropics/scone-bench"],"related_signals":6,"has_source_url":true,"latest_page_fetched_at":"2026-06-11T02:42:11.785161+00:00"},"data_business":{"matches":true,"lanes":[{"key":"evals","label":"Evals and quality","url":"https://onlylabs.fyi/data-radar/evals","json_url":"https://onlylabs.fyi/data-radar/evals/signals.json"}],"matched_terms":["eval","benchmark"],"score":16,"reason":"Anthropic has a repo signal matching evals and quality."},"agent_handoff":{"signal_json":"https://onlylabs.fyi/signals/0c515bfd-ccd4-4a21-868f-944fd4945f19/signal.json","dossier_json":"https://onlylabs.fyi/labs/anthropic/dossier.json","analysis_json":"https://onlylabs.fyi/analysis/anthropic/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/anthropic/evidence.json","topic_signals_json":null,"topic_feed":null,"category_signals_json":"https://onlylabs.fyi/signals.json","data_radar_json":"https://onlylabs.fyi/data-radar.json","opportunities_json":"https://onlylabs.fyi/opportunities.json"},"analysis_playbook":{"objective":"Turn new repository signals into early evidence of tooling, eval, infrastructure, model-adjacent, or product work before it appears in polished launch channels.","evidence_focus":["repo name","owner","description","language","stars","source URL","first seen time","data, eval, infra, safety, and product terms"],"extraction_questions":["What technical area does this repository expose?","Does the repo imply eval, data, infrastructure, agent, or deployment work?","Is the repo new evidence for a lab direction that is not yet in writing or releases?","Which related signals should an analyst inspect next?"],"signal_questions":["What does this new repository reveal before a formal announcement exists?","What technical area does this repository expose?","Does the repo imply eval, data, infrastructure, agent, or deployment work?","Which data-business lane explains this signal: Evals and quality?","Do the 6 related repo signals show a repeated pattern?"],"output_fields":["org","repo","technical_theme","data_business_lane","evidence_url"],"data_business_relevance":"New repositories can expose organization build priorities early, especially around internal tooling, eval infrastructure, data systems, deployment, and agent workflows.","required_sources":[{"label":"signal_json","url":"https://onlylabs.fyi/signals/0c515bfd-ccd4-4a21-868f-944fd4945f19/signal.json","required":true},{"label":"source","url":"https://github.com/anthropics/scone-bench","required":true},{"label":"dossier_json","url":"https://onlylabs.fyi/labs/anthropic/dossier.json","required":true},{"label":"analysis_evidence_json","url":"https://onlylabs.fyi/analysis/anthropic/evidence.json","required":true},{"label":"topic_signals_json","url":null,"required":false},{"label":"data_radar_json","url":"https://onlylabs.fyi/data-radar.json","required":true}],"expected_output":["one-paragraph source-grounded interpretation","data-business implication","confidence and missing evidence","recommended next source to inspect"],"prompt_seed":"Using only the linked onlylabs JSON, captured source context, and cited evidence, analyze Anthropic's repo signal \"anthropics/scone-bench\" for frontier lab strategy and data-business implications."},"semantic_triples":[{"subject":"Anthropic","predicate":"published repo","object":"anthropics/scone-bench","text":"Anthropic published repo anthropics/scone-bench."},{"subject":"anthropics/scone-bench","predicate":"is classified as","object":"repo signal","text":"anthropics/scone-bench is classified as repo signal."},{"subject":"anthropics/scone-bench","predicate":"belongs to","object":"repos desk","text":"anthropics/scone-bench belongs to repos desk."},{"subject":"anthropics/scone-bench","predicate":"has context","object":"Python","text":"anthropics/scone-bench has context Python."},{"subject":"anthropics/scone-bench","predicate":"has evidence coverage","object":"1 captured evidence page","text":"anthropics/scone-bench has evidence coverage 1 captured evidence page."},{"subject":"anthropics/scone-bench","predicate":"matches data-business lanes","object":"Evals and quality","text":"anthropics/scone-bench matches data-business lanes Evals and quality."},{"subject":"anthropics/scone-bench","predicate":"has captured page count","object":"1","text":"anthropics/scone-bench has captured page count 1."},{"subject":"anthropics/scone-bench","predicate":"has readable page count","object":"1","text":"anthropics/scone-bench has readable page count 1."},{"subject":"anthropics/scone-bench","predicate":"has related signal count","object":"6","text":"anthropics/scone-bench has related signal count 6."},{"subject":"anthropics/scone-bench","predicate":"has analysis playbook objective","object":"Turn new repository signals into early evidence of tooling, eval, infrastructure, model-adjacent, or product work before it appears in polished launch channels.","text":"anthropics/scone-bench has analysis playbook objective Turn new repository signals into early evidence of tooling, eval, infrastructure, model-adjacent, or product work before it appears in polished launch channels.."},{"subject":"anthropics/scone-bench","predicate":"has source host","object":"github.com","text":"anthropics/scone-bench has source host github.com."},{"subject":"anthropics/scone-bench","predicate":"has lab","object":"Anthropic","text":"anthropics/scone-bench has lab Anthropic."},{"subject":"anthropics/scone-bench","predicate":"has signal desk","object":"repos","text":"anthropics/scone-bench has signal desk repos."},{"subject":"anthropics/scone-bench","predicate":"has source host","object":"github.com","text":"anthropics/scone-bench has source host github.com."},{"subject":"anthropics/scone-bench","predicate":"has repository","object":"anthropics/scone-bench","text":"anthropics/scone-bench has repository anthropics/scone-bench."},{"subject":"anthropics/scone-bench","predicate":"has language","object":"Python","text":"anthropics/scone-bench has language Python."},{"subject":"anthropics/scone-bench","predicate":"has stars","object":"21","text":"anthropics/scone-bench has stars 21."},{"subject":"anthropics/scone-bench","predicate":"has notability","object":"Low-star benchmark repo by Anthropic, routine","text":"anthropics/scone-bench has notability Low-star benchmark repo by Anthropic, routine."},{"subject":"anthropics/scone-bench","predicate":"has radar lane","object":"Evals and quality","text":"anthropics/scone-bench has radar lane Evals and quality."}]},"intelligence":{"signal_desk":"repos","answer":"Anthropic published anthropics/scone-bench (Python). This repository signal exposes tooling, eval, infrastructure, or model-adjacent work before it may appear in a launch post. High-signal details: repo anthropics/scone-bench · language Python · Low-star benchmark repo by Anthropic, routine. onlylabs links this event to 1 captured evidence page and 6 related repo signals. It also maps to Evals and quality in the data-business radar.","semantic_triples":[{"subject":"Anthropic","predicate":"published repo","object":"anthropics/scone-bench","text":"Anthropic published repo anthropics/scone-bench."},{"subject":"anthropics/scone-bench","predicate":"is classified as","object":"repo signal","text":"anthropics/scone-bench is classified as repo signal."},{"subject":"anthropics/scone-bench","predicate":"belongs to","object":"repos desk","text":"anthropics/scone-bench belongs to repos desk."},{"subject":"anthropics/scone-bench","predicate":"has context","object":"Python","text":"anthropics/scone-bench has context Python."},{"subject":"anthropics/scone-bench","predicate":"has evidence coverage","object":"1 captured evidence page","text":"anthropics/scone-bench has evidence coverage 1 captured evidence page."},{"subject":"anthropics/scone-bench","predicate":"matches data-business lanes","object":"Evals and quality","text":"anthropics/scone-bench matches data-business lanes Evals and quality."}]},"signal":{"id":"0c515bfd-ccd4-4a21-868f-944fd4945f19","url":"https://onlylabs.fyi/signals/0c515bfd-ccd4-4a21-868f-944fd4945f19","json_url":"https://onlylabs.fyi/signals/0c515bfd-ccd4-4a21-868f-944fd4945f19/signal.json","source_url":"https://github.com/anthropics/scone-bench","title":"anthropics/scone-bench","summary":"Anthropic published a new repository. onlylabs watches repos for tooling, eval, infra, and model-adjacent work.","context":"Python","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"anthropic","name":"Anthropic","category":"frontier-lab"},"occurred_at":"2026-05-12T22:17:19+00:00","first_seen_at":"2026-06-05T05:42:58.841369+00:00","date_source":"source","evidence_coverage":{"target_pages":1,"captured_pages":1,"readable_pages":1,"capture_methods":["plain"],"missing_page_urls":[],"failed_page_urls":[],"blocked_page_urls":[],"page_urls":["https://github.com/anthropics/scone-bench"]},"facets":{"repo":"anthropics/scone-bench","language":"Python"},"traction":{"github_stars":21,"hn_points":null,"hn_comments":null,"hn_story_id":null,"hf_downloads":null,"hf_likes":null},"data_radar":{"lanes":[{"key":"evals","label":"Evals and quality","url":"https://onlylabs.fyi/data-radar/evals"}],"score":16,"matched_terms":["eval","benchmark"],"reason":"Anthropic has a repo signal matching evals and quality."}},"primary_evidence_page":{"url":"https://github.com/anthropics/scone-bench","final_url":"https://github.com/anthropics/scone-bench","title":"anthropics/scone-bench repository metadata","http_status":200,"content_type":"application/json","capture_method":"plain","fetched_at":"2026-06-11T02:42:11.785161+00:00","bytes":13281,"raw_path":"cdf62c153e2116a43b31a1b908d65ac53dc808a41760aa153912215887a47fa3.json","content_hash":"491929bedf90624fee25be6ce0116da9b3bba5f22d20979f60bcd5f037aea01f","excerpt_chars":1200,"truncated":true,"excerpt":"anthropics/scone-bench Description: Benchmark for evaluating LLM agents on smart-contract vulnerability discovery and exploitation Language: Python License: Apache-2.0 Stars: 21 Forks: 8 Open issues: 0 Created: 2026-05-12T22:17:19Z Pushed: 2026-05-19T03:42:55Z Default branch: main Fork: no Archived: no README: scone-bench > **Benchmark.** Not maintained and not accepting contributions. A benchmark for evaluating LLM agents on **smart-contract vulnerability discovery and exploitation**. Each of the 417 tasks presents the agent with a real EVM contract (forked at a historical block on a local [anvil](https://book.getfoundry.sh/anvil/) node) and asks it to find a flaw and write a Solidity `FlawVerifier` whose `executeOnOpportunity()` extracts ≥0.1 native token of profit. The tasks are drawn from publicly documented historical DeFi incidents (re-entrancy, price-oracle manipulation, access-control bugs, arithmetic errors, etc.), sourced largely from the [DeFiHackLabs](https://github.com/SunWeb3Sec/DeFiHackLabs) incident catalog. Because the agent works against a local fork, no mainnet funds are ever at risk. How it works ``` ┌─────────┐ MCP/stdio ┌──────────────────────── docker..."},"evidence_pages":[{"url":"https://github.com/anthropics/scone-bench","final_url":"https://github.com/anthropics/scone-bench","title":"anthropics/scone-bench repository metadata","http_status":200,"content_type":"application/json","capture_method":"plain","fetched_at":"2026-06-11T02:42:11.785161+00:00","bytes":13281,"raw_path":"cdf62c153e2116a43b31a1b908d65ac53dc808a41760aa153912215887a47fa3.json","content_hash":"491929bedf90624fee25be6ce0116da9b3bba5f22d20979f60bcd5f037aea01f","excerpt_chars":1200,"truncated":true,"excerpt":"anthropics/scone-bench Description: Benchmark for evaluating LLM agents on smart-contract vulnerability discovery and exploitation Language: Python License: Apache-2.0 Stars: 21 Forks: 8 Open issues: 0 Created: 2026-05-12T22:17:19Z Pushed: 2026-05-19T03:42:55Z Default branch: main Fork: no Archived: no README: scone-bench > **Benchmark.** Not maintained and not accepting contributions. A benchmark for evaluating LLM agents on **smart-contract vulnerability discovery and exploitation**. Each of the 417 tasks presents the agent with a real EVM contract (forked at a historical block on a local [anvil](https://book.getfoundry.sh/anvil/) node) and asks it to find a flaw and write a Solidity `FlawVerifier` whose `executeOnOpportunity()` extracts ≥0.1 native token of profit. The tasks are drawn from publicly documented historical DeFi incidents (re-entrancy, price-oracle manipulation, access-control bugs, arithmetic errors, etc.), sourced largely from the [DeFiHackLabs](https://github.com/SunWeb3Sec/DeFiHackLabs) incident catalog. Because the agent works against a local fork, no mainnet funds are ever at risk. How it works ``` ┌─────────┐ MCP/stdio ┌──────────────────────── docker..."}],"related_signals":[{"id":"d655a3de-1616-4e38-b9a0-27254762c1f0","url":"https://onlylabs.fyi/signals/d655a3de-1616-4e38-b9a0-27254762c1f0","source_url":"https://github.com/anthropics/defending-code-reference-harness","title":"anthropics/defending-code-reference-harness","context":"Python","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"anthropic","name":"Anthropic","category":"frontier-lab"},"occurred_at":"2026-05-22T16:00:56+00:00","first_seen_at":"2026-06-05T05:42:58.841369+00:00","date_source":"source"},{"id":"f91bba87-e295-4641-8aa0-9fa254e149b1","url":"https://onlylabs.fyi/signals/f91bba87-e295-4641-8aa0-9fa254e149b1","source_url":"https://github.com/anthropics/ClaudeForFoundationModels","title":"anthropics/ClaudeForFoundationModels","context":"Swift","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"anthropic","name":"Anthropic","category":"frontier-lab"},"occurred_at":"2026-05-20T15:41:18+00:00","first_seen_at":"2026-06-09T07:00:07.44979+00:00","date_source":"source"},{"id":"7f417861-19b7-493f-b6d7-bf9ef54a9a1f","url":"https://onlylabs.fyi/signals/7f417861-19b7-493f-b6d7-bf9ef54a9a1f","source_url":"https://github.com/anthropics/cargo-nix-plugin","title":"anthropics/cargo-nix-plugin","context":"Rust","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"anthropic","name":"Anthropic","category":"frontier-lab"},"occurred_at":"2026-05-19T17:07:44+00:00","first_seen_at":"2026-06-05T05:42:58.841369+00:00","date_source":"source"},{"id":"7f529da9-d1d8-4424-aaf5-face018ae4f8","url":"https://onlylabs.fyi/signals/7f529da9-d1d8-4424-aaf5-face018ae4f8","source_url":"https://github.com/anthropics/html-effectiveness","title":"anthropics/html-effectiveness","context":"HTML","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"anthropic","name":"Anthropic","category":"frontier-lab"},"occurred_at":"2026-05-12T06:25:16+00:00","first_seen_at":"2026-06-05T05:42:58.841369+00:00","date_source":"source"},{"id":"3ea41c6f-444c-4f24-a8f7-ad037263bde0","url":"https://onlylabs.fyi/signals/3ea41c6f-444c-4f24-a8f7-ad037263bde0","source_url":"https://github.com/anthropics/cwc-workshops","title":"anthropics/cwc-workshops","context":"TypeScript","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"anthropic","name":"Anthropic","category":"frontier-lab"},"occurred_at":"2026-05-06T03:53:01+00:00","first_seen_at":"2026-06-05T05:42:58.841369+00:00","date_source":"source"},{"id":"12b8bd94-008c-4337-9e18-dfc96f1931cc","url":"https://onlylabs.fyi/signals/12b8bd94-008c-4337-9e18-dfc96f1931cc","source_url":"https://github.com/anthropics/cwc-long-running-agents","title":"anthropics/cwc-long-running-agents","context":"Shell","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"anthropic","name":"Anthropic","category":"frontier-lab"},"occurred_at":"2026-05-06T00:23:37+00:00","first_seen_at":"2026-06-05T05:42:58.841369+00:00","date_source":"source"}]}