{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:74LUSFA27WSJEXHLX3GKG5R2XH","short_pith_number":"pith:74LUSFA2","schema_version":"1.0","canonical_sha256":"ff1749141afda4925cebbecca3763ab9c0b3859549d593c2694d237334996c2d","source":{"kind":"arxiv","id":"2607.08984","version":1},"attestation_state":"computed","paper":{"title":"AlphaZero in Sparsely Rewarded Games: Limits and Auxiliary Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT","math.CO"],"primary_cat":"cs.LG","authors_text":"Brent Kong, Tejas Ram, Tony Yue Yu","submitted_at":"2026-07-09T23:17:17Z","abstract_excerpt":"AlphaZero has demonstrated that a neural-guided Monte Carlo Tree Search can achieve superhuman performance, but strong play does not necessarily imply perfect play. We study this gap in two oracle-evaluable domains with contrasting structure: Connect Four, a solved partisan game with exact game-theoretic values, and Chomp, an impartial game whose optimal play is governed by Grundy-number structure. Under a unified self-play $+$ MCTS pipeline, we compare vanilla AlphaZero, a multi-frame variant (limited to Chomp), and an AlphaZero Auxiliary Loss (AZAL) that adds oracle-derived policy supervisio"},"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":"2607.08984","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-09T23:17:17Z","cross_cats_sorted":["cs.AI","cs.GT","math.CO"],"title_canon_sha256":"7b3d5fbd0791f0edd5042eb317882536138af403e276ac1c8dafc39f9ae5c7be","abstract_canon_sha256":"fd8a192991168773a145a2289199b20cf521fec7caaae5a47f401570ae56afd5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T00:17:32.062024Z","signature_b64":"dTs30UBn1+TzqcT7OgqjFtPeOXw2Q+x+e5bGLNbYye7rISaZbO8XG6Th6JKRtZi1euSajOi/BEv6emhwgqc7CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff1749141afda4925cebbecca3763ab9c0b3859549d593c2694d237334996c2d","last_reissued_at":"2026-07-13T00:17:32.061046Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T00:17:32.061046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AlphaZero in Sparsely Rewarded Games: Limits and Auxiliary Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT","math.CO"],"primary_cat":"cs.LG","authors_text":"Brent Kong, Tejas Ram, Tony Yue Yu","submitted_at":"2026-07-09T23:17:17Z","abstract_excerpt":"AlphaZero has demonstrated that a neural-guided Monte Carlo Tree Search can achieve superhuman performance, but strong play does not necessarily imply perfect play. We study this gap in two oracle-evaluable domains with contrasting structure: Connect Four, a solved partisan game with exact game-theoretic values, and Chomp, an impartial game whose optimal play is governed by Grundy-number structure. Under a unified self-play $+$ MCTS pipeline, we compare vanilla AlphaZero, a multi-frame variant (limited to Chomp), and an AlphaZero Auxiliary Loss (AZAL) that adds oracle-derived policy supervisio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08984","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/2607.08984/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":"2607.08984","created_at":"2026-07-13T00:17:32.061549+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.08984v1","created_at":"2026-07-13T00:17:32.061549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08984","created_at":"2026-07-13T00:17:32.061549+00:00"},{"alias_kind":"pith_short_12","alias_value":"74LUSFA27WSJ","created_at":"2026-07-13T00:17:32.061549+00:00"},{"alias_kind":"pith_short_16","alias_value":"74LUSFA27WSJEXHL","created_at":"2026-07-13T00:17:32.061549+00:00"},{"alias_kind":"pith_short_8","alias_value":"74LUSFA2","created_at":"2026-07-13T00:17:32.061549+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/74LUSFA27WSJEXHLX3GKG5R2XH","json":"https://pith.science/pith/74LUSFA27WSJEXHLX3GKG5R2XH.json","graph_json":"https://pith.science/api/pith-number/74LUSFA27WSJEXHLX3GKG5R2XH/graph.json","events_json":"https://pith.science/api/pith-number/74LUSFA27WSJEXHLX3GKG5R2XH/events.json","paper":"https://pith.science/paper/74LUSFA2"},"agent_actions":{"view_html":"https://pith.science/pith/74LUSFA27WSJEXHLX3GKG5R2XH","download_json":"https://pith.science/pith/74LUSFA27WSJEXHLX3GKG5R2XH.json","view_paper":"https://pith.science/paper/74LUSFA2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.08984&json=true","fetch_graph":"https://pith.science/api/pith-number/74LUSFA27WSJEXHLX3GKG5R2XH/graph.json","fetch_events":"https://pith.science/api/pith-number/74LUSFA27WSJEXHLX3GKG5R2XH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/74LUSFA27WSJEXHLX3GKG5R2XH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/74LUSFA27WSJEXHLX3GKG5R2XH/action/storage_attestation","attest_author":"https://pith.science/pith/74LUSFA27WSJEXHLX3GKG5R2XH/action/author_attestation","sign_citation":"https://pith.science/pith/74LUSFA27WSJEXHLX3GKG5R2XH/action/citation_signature","submit_replication":"https://pith.science/pith/74LUSFA27WSJEXHLX3GKG5R2XH/action/replication_record"}},"created_at":"2026-07-13T00:17:32.061549+00:00","updated_at":"2026-07-13T00:17:32.061549+00:00"}