{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2WCC3KF6AREIWIG2BE7QEO73SM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0aa54056eb47dd7e4febfb5217780a359cc81d324ca0cbb9ee5ae0d9ad5efc6e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T21:31:01Z","title_canon_sha256":"371aa93e9e951fafe2bc3c2d60d05297c0acdd75f7734587e170f7798f8397cd"},"schema_version":"1.0","source":{"id":"2608.04240","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.04240","created_at":"2026-08-06T01:31:44Z"},{"alias_kind":"arxiv_version","alias_value":"2608.04240v1","created_at":"2026-08-06T01:31:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04240","created_at":"2026-08-06T01:31:44Z"},{"alias_kind":"pith_short_12","alias_value":"2WCC3KF6AREI","created_at":"2026-08-06T01:31:44Z"},{"alias_kind":"pith_short_16","alias_value":"2WCC3KF6AREIWIG2","created_at":"2026-08-06T01:31:44Z"},{"alias_kind":"pith_short_8","alias_value":"2WCC3KF6","created_at":"2026-08-06T01:31:44Z"}],"graph_snapshots":[{"event_id":"sha256:d160f07373527ceb95a57e55319cc461582baeda3b45163507fecc42ddb2536e","target":"graph","created_at":"2026-08-06T01:31:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2608.04240/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Peiyao Sheng, Pramod Viswanath, S. Ashwin Hebbar, Sewoong Oh","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T21:31:01Z","title":"Hallucinations on the Board: Tool-Augmented Evaluation of LLM Chess Commentary"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04240","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0d175a14de2742684f7f07a2fb7369813b83616c410ac8476162fc953b4900d2","target":"record","created_at":"2026-08-06T01:31:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0aa54056eb47dd7e4febfb5217780a359cc81d324ca0cbb9ee5ae0d9ad5efc6e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T21:31:01Z","title_canon_sha256":"371aa93e9e951fafe2bc3c2d60d05297c0acdd75f7734587e170f7798f8397cd"},"schema_version":"1.0","source":{"id":"2608.04240","kind":"arxiv","version":1}},"canonical_sha256":"d5842da8be04488b20da093f023bfb933cf1d45c7b652c46516548cc6ee30b39","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5842da8be04488b20da093f023bfb933cf1d45c7b652c46516548cc6ee30b39","first_computed_at":"2026-08-06T01:31:44.027697Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-06T01:31:44.027697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AN/Gw16wUu9jQvdsm7xLEeOGtAZ8jPIK9ewJz4NaNtwFQIVpQLjO/GFLVJjTuDpVy9BntqPWM8KL1dL0o1JMCw==","signature_status":"signed_v1","signed_at":"2026-08-06T01:31:44.029146Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.04240","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d175a14de2742684f7f07a2fb7369813b83616c410ac8476162fc953b4900d2","sha256:d160f07373527ceb95a57e55319cc461582baeda3b45163507fecc42ddb2536e"],"state_sha256":"2a2535c0125440ee03faf0f59d4094e0a2a7e29572c13bba75b854c84c9447b4"}