{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RGDL2XFXD366VTPSOPKZNUZEEN","short_pith_number":"pith:RGDL2XFX","schema_version":"1.0","canonical_sha256":"8986bd5cb71efdeacdf273d596d3242348e1d2507716b829adea11b71a4bc207","source":{"kind":"arxiv","id":"2605.17565","version":1},"attestation_state":"computed","paper":{"title":"Generalization or Memorization? Brittleness Testing for Chess-Trained Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Ethan Tang","submitted_at":"2026-05-17T17:49:07Z","abstract_excerpt":"Recent work has fine-tuned language models on chess data and reported high benchmark scores as evidence that the resulting models can understand the rules of chess, play full chess games at a professional level, or generate human-readable explanations grounded in expert knowledge. We train KinGPT, a 25M-parameter character-level language model trained only on (position, best-move) pairs, who exceeds 3B-parameter ChessGPT on a 600-puzzle mate-in-N suite and 4B-parameter C1-4B over a 20-theme puzzle benchmark. We examine several claims made in existing literature regarding chess-trained language"},"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":"2605.17565","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-17T17:49:07Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e2120521c2e9ae103c1c51d05a6f28f95510e7f5fc756ec83a8739c1a12587f5","abstract_canon_sha256":"178cd2060633e831bd02328511c6722c727967e4dbd8031010b32dd5994eaf68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:46.228886Z","signature_b64":"Uw0NVs85jZpd1Sk4amC+hgtdESWt5sqOWK0XaLxvfMP6EZnFL9nE1Vs/t5krEo5WT6d9VttovH10yHwD82I5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8986bd5cb71efdeacdf273d596d3242348e1d2507716b829adea11b71a4bc207","last_reissued_at":"2026-05-20T00:04:46.228286Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:46.228286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalization or Memorization? Brittleness Testing for Chess-Trained Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Ethan Tang","submitted_at":"2026-05-17T17:49:07Z","abstract_excerpt":"Recent work has fine-tuned language models on chess data and reported high benchmark scores as evidence that the resulting models can understand the rules of chess, play full chess games at a professional level, or generate human-readable explanations grounded in expert knowledge. We train KinGPT, a 25M-parameter character-level language model trained only on (position, best-move) pairs, who exceeds 3B-parameter ChessGPT on a 600-puzzle mate-in-N suite and 4B-parameter C1-4B over a 20-theme puzzle benchmark. We examine several claims made in existing literature regarding chess-trained language"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17565","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/2605.17565/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.598676Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T21:21:57.530728Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"0f075694c7e3f2d84891b44e37a67ac10852bf24022b18f60013d096574053fb"},"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":"2605.17565","created_at":"2026-05-20T00:04:46.228398+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17565v1","created_at":"2026-05-20T00:04:46.228398+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17565","created_at":"2026-05-20T00:04:46.228398+00:00"},{"alias_kind":"pith_short_12","alias_value":"RGDL2XFXD366","created_at":"2026-05-20T00:04:46.228398+00:00"},{"alias_kind":"pith_short_16","alias_value":"RGDL2XFXD366VTPS","created_at":"2026-05-20T00:04:46.228398+00:00"},{"alias_kind":"pith_short_8","alias_value":"RGDL2XFX","created_at":"2026-05-20T00:04:46.228398+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/RGDL2XFXD366VTPSOPKZNUZEEN","json":"https://pith.science/pith/RGDL2XFXD366VTPSOPKZNUZEEN.json","graph_json":"https://pith.science/api/pith-number/RGDL2XFXD366VTPSOPKZNUZEEN/graph.json","events_json":"https://pith.science/api/pith-number/RGDL2XFXD366VTPSOPKZNUZEEN/events.json","paper":"https://pith.science/paper/RGDL2XFX"},"agent_actions":{"view_html":"https://pith.science/pith/RGDL2XFXD366VTPSOPKZNUZEEN","download_json":"https://pith.science/pith/RGDL2XFXD366VTPSOPKZNUZEEN.json","view_paper":"https://pith.science/paper/RGDL2XFX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17565&json=true","fetch_graph":"https://pith.science/api/pith-number/RGDL2XFXD366VTPSOPKZNUZEEN/graph.json","fetch_events":"https://pith.science/api/pith-number/RGDL2XFXD366VTPSOPKZNUZEEN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RGDL2XFXD366VTPSOPKZNUZEEN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RGDL2XFXD366VTPSOPKZNUZEEN/action/storage_attestation","attest_author":"https://pith.science/pith/RGDL2XFXD366VTPSOPKZNUZEEN/action/author_attestation","sign_citation":"https://pith.science/pith/RGDL2XFXD366VTPSOPKZNUZEEN/action/citation_signature","submit_replication":"https://pith.science/pith/RGDL2XFXD366VTPSOPKZNUZEEN/action/replication_record"}},"created_at":"2026-05-20T00:04:46.228398+00:00","updated_at":"2026-05-20T00:04:46.228398+00:00"}