{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YXZBOYLONQ52GSO6EGMYPPYJF3","short_pith_number":"pith:YXZBOYLO","schema_version":"1.0","canonical_sha256":"c5f217616e6c3ba349de219987bf092ed63e648bc9f4bb977a4cb17d7ec4aa4a","source":{"kind":"arxiv","id":"2608.09538","version":1},"attestation_state":"computed","paper":{"title":"TCS-BENCH: Benchmarking State-of-the-Art Generative AI Theoretical Computer Science Research Ability","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Adarsh Kumarappan, David Woodruff, Dimitris Paparas, Ernest van Wijland, Honghao Lin, Julien Canitrot-Paradis, Lalit Jain, Max Springer, Mislav Balunovic, Ola Svensson, Rajesh Jayaram, Rudrajit Das, Silvio Lattanzi, Theophane Weber, Vahab Mirrokni, Vincent Cohen-Addad","submitted_at":"2026-08-10T12:36:16Z","abstract_excerpt":"We introduce TCS-Bench, a benchmark for evaluating Large Language Models (LLMs) on research-level Theoretical Computer Science (TCS) proof generation. TCS-Bench consists of theorem-proving tasks from papers published at top theoretical computer science venues (STOC, FOCS, and SODA). Each task provides the necessary context to derive a self-contained proof for a target result. We evaluate state-of-the-art models on this benchmark. We verify the correctness of generated proofs via a verification agent, and further benchmark the verifier against human-expert proof judgements on a set of target st"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.09538","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-10T12:36:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c300f5a8f2564a81fd07a41ec54ca8e7c6c01d1207f7293b0658e3ed3eead7c5","abstract_canon_sha256":"9297e286be1bb99c4687d344eda848f5eea49d4c70bf405f581ad60c5bfb054c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T02:24:26.780942Z","signature_b64":"h+vta732Cs2uc5XcK0GLHkuT/MILzu/uwsMcAqu3ysJy4BXRtQooSK9uv1SO9ig/zEpz+S23wuJcOniTyZDOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5f217616e6c3ba349de219987bf092ed63e648bc9f4bb977a4cb17d7ec4aa4a","last_reissued_at":"2026-08-11T02:24:26.779232Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T02:24:26.779232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TCS-BENCH: Benchmarking State-of-the-Art Generative AI Theoretical Computer Science Research Ability","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Adarsh Kumarappan, David Woodruff, Dimitris Paparas, Ernest van Wijland, Honghao Lin, Julien Canitrot-Paradis, Lalit Jain, Max Springer, Mislav Balunovic, Ola Svensson, Rajesh Jayaram, Rudrajit Das, Silvio Lattanzi, Theophane Weber, Vahab Mirrokni, Vincent Cohen-Addad","submitted_at":"2026-08-10T12:36:16Z","abstract_excerpt":"We introduce TCS-Bench, a benchmark for evaluating Large Language Models (LLMs) on research-level Theoretical Computer Science (TCS) proof generation. TCS-Bench consists of theorem-proving tasks from papers published at top theoretical computer science venues (STOC, FOCS, and SODA). Each task provides the necessary context to derive a self-contained proof for a target result. We evaluate state-of-the-art models on this benchmark. We verify the correctness of generated proofs via a verification agent, and further benchmark the verifier against human-expert proof judgements on a set of target st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09538","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2608.09538/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.09538","created_at":"2026-08-11T02:24:26.779874+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.09538v1","created_at":"2026-08-11T02:24:26.779874+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09538","created_at":"2026-08-11T02:24:26.779874+00:00"},{"alias_kind":"pith_short_12","alias_value":"YXZBOYLONQ52","created_at":"2026-08-11T02:24:26.779874+00:00"},{"alias_kind":"pith_short_16","alias_value":"YXZBOYLONQ52GSO6","created_at":"2026-08-11T02:24:26.779874+00:00"},{"alias_kind":"pith_short_8","alias_value":"YXZBOYLO","created_at":"2026-08-11T02:24:26.779874+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YXZBOYLONQ52GSO6EGMYPPYJF3","json":"https://pith.science/pith/YXZBOYLONQ52GSO6EGMYPPYJF3.json","graph_json":"https://pith.science/api/pith-number/YXZBOYLONQ52GSO6EGMYPPYJF3/graph.json","events_json":"https://pith.science/api/pith-number/YXZBOYLONQ52GSO6EGMYPPYJF3/events.json","paper":"https://pith.science/paper/YXZBOYLO"},"agent_actions":{"view_html":"https://pith.science/pith/YXZBOYLONQ52GSO6EGMYPPYJF3","download_json":"https://pith.science/pith/YXZBOYLONQ52GSO6EGMYPPYJF3.json","view_paper":"https://pith.science/paper/YXZBOYLO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.09538&json=true","fetch_graph":"https://pith.science/api/pith-number/YXZBOYLONQ52GSO6EGMYPPYJF3/graph.json","fetch_events":"https://pith.science/api/pith-number/YXZBOYLONQ52GSO6EGMYPPYJF3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YXZBOYLONQ52GSO6EGMYPPYJF3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YXZBOYLONQ52GSO6EGMYPPYJF3/action/storage_attestation","attest_author":"https://pith.science/pith/YXZBOYLONQ52GSO6EGMYPPYJF3/action/author_attestation","sign_citation":"https://pith.science/pith/YXZBOYLONQ52GSO6EGMYPPYJF3/action/citation_signature","submit_replication":"https://pith.science/pith/YXZBOYLONQ52GSO6EGMYPPYJF3/action/replication_record"}},"created_at":"2026-08-11T02:24:26.779874+00:00","updated_at":"2026-08-11T02:24:26.779874+00:00"}