{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2WCC3KF6AREIWIG2BE7QEO73SM","short_pith_number":"pith:2WCC3KF6","schema_version":"1.0","canonical_sha256":"d5842da8be04488b20da093f023bfb933cf1d45c7b652c46516548cc6ee30b39","source":{"kind":"arxiv","id":"2608.04240","version":1},"attestation_state":"computed","paper":{"title":"Hallucinations on the Board: Tool-Augmented Evaluation of LLM Chess Commentary","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Peiyao Sheng, Pramod Viswanath, S. Ashwin Hebbar, Sewoong Oh","submitted_at":"2026-08-04T21:31:01Z","abstract_excerpt":"Superhuman game engines in domains like chess have made expert-level evaluations easily accessible, yet they communicate what is true without the natural-language explanations that make such expertise educationally useful to experts and non-experts alike. Large language models could, in principle, bridge this gap, but they frequently hallucinate due to limited domain-specific knowledge, and standard reference-based or LLM-as-a-judge frameworks cannot reliably detect these errors. In this work, we present ACT-Eval, an evaluation framework that decomposes chess commentary into atomic claims and "},"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":"2608.04240","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T21:31:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"371aa93e9e951fafe2bc3c2d60d05297c0acdd75f7734587e170f7798f8397cd","abstract_canon_sha256":"0aa54056eb47dd7e4febfb5217780a359cc81d324ca0cbb9ee5ae0d9ad5efc6e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:31:44.029146Z","signature_b64":"AN/Gw16wUu9jQvdsm7xLEeOGtAZ8jPIK9ewJz4NaNtwFQIVpQLjO/GFLVJjTuDpVy9BntqPWM8KL1dL0o1JMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5842da8be04488b20da093f023bfb933cf1d45c7b652c46516548cc6ee30b39","last_reissued_at":"2026-08-06T01:31:44.027697Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:31:44.027697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hallucinations on the Board: Tool-Augmented Evaluation of LLM Chess Commentary","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Peiyao Sheng, Pramod Viswanath, S. Ashwin Hebbar, Sewoong Oh","submitted_at":"2026-08-04T21:31:01Z","abstract_excerpt":"Superhuman game engines in domains like chess have made expert-level evaluations easily accessible, yet they communicate what is true without the natural-language explanations that make such expertise educationally useful to experts and non-experts alike. Large language models could, in principle, bridge this gap, but they frequently hallucinate due to limited domain-specific knowledge, and standard reference-based or LLM-as-a-judge frameworks cannot reliably detect these errors. In this work, we present ACT-Eval, an evaluation framework that decomposes chess commentary into atomic claims and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04240","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/2608.04240/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":"2608.04240","created_at":"2026-08-06T01:31:44.029540+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.04240v1","created_at":"2026-08-06T01:31:44.029540+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04240","created_at":"2026-08-06T01:31:44.029540+00:00"},{"alias_kind":"pith_short_12","alias_value":"2WCC3KF6AREI","created_at":"2026-08-06T01:31:44.029540+00:00"},{"alias_kind":"pith_short_16","alias_value":"2WCC3KF6AREIWIG2","created_at":"2026-08-06T01:31:44.029540+00:00"},{"alias_kind":"pith_short_8","alias_value":"2WCC3KF6","created_at":"2026-08-06T01:31:44.029540+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/2WCC3KF6AREIWIG2BE7QEO73SM","json":"https://pith.science/pith/2WCC3KF6AREIWIG2BE7QEO73SM.json","graph_json":"https://pith.science/api/pith-number/2WCC3KF6AREIWIG2BE7QEO73SM/graph.json","events_json":"https://pith.science/api/pith-number/2WCC3KF6AREIWIG2BE7QEO73SM/events.json","paper":"https://pith.science/paper/2WCC3KF6"},"agent_actions":{"view_html":"https://pith.science/pith/2WCC3KF6AREIWIG2BE7QEO73SM","download_json":"https://pith.science/pith/2WCC3KF6AREIWIG2BE7QEO73SM.json","view_paper":"https://pith.science/paper/2WCC3KF6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.04240&json=true","fetch_graph":"https://pith.science/api/pith-number/2WCC3KF6AREIWIG2BE7QEO73SM/graph.json","fetch_events":"https://pith.science/api/pith-number/2WCC3KF6AREIWIG2BE7QEO73SM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2WCC3KF6AREIWIG2BE7QEO73SM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2WCC3KF6AREIWIG2BE7QEO73SM/action/storage_attestation","attest_author":"https://pith.science/pith/2WCC3KF6AREIWIG2BE7QEO73SM/action/author_attestation","sign_citation":"https://pith.science/pith/2WCC3KF6AREIWIG2BE7QEO73SM/action/citation_signature","submit_replication":"https://pith.science/pith/2WCC3KF6AREIWIG2BE7QEO73SM/action/replication_record"}},"created_at":"2026-08-06T01:31:44.029540+00:00","updated_at":"2026-08-06T01:31:44.029540+00:00"}