{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:74LUSFA27WSJEXHLX3GKG5R2XH","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":"fd8a192991168773a145a2289199b20cf521fec7caaae5a47f401570ae56afd5","cross_cats_sorted":["cs.AI","cs.GT","math.CO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-09T23:17:17Z","title_canon_sha256":"7b3d5fbd0791f0edd5042eb317882536138af403e276ac1c8dafc39f9ae5c7be"},"schema_version":"1.0","source":{"id":"2607.08984","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08984","created_at":"2026-07-13T00:17:32Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08984v1","created_at":"2026-07-13T00:17:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08984","created_at":"2026-07-13T00:17:32Z"},{"alias_kind":"pith_short_12","alias_value":"74LUSFA27WSJ","created_at":"2026-07-13T00:17:32Z"},{"alias_kind":"pith_short_16","alias_value":"74LUSFA27WSJEXHL","created_at":"2026-07-13T00:17:32Z"},{"alias_kind":"pith_short_8","alias_value":"74LUSFA2","created_at":"2026-07-13T00:17:32Z"}],"graph_snapshots":[{"event_id":"sha256:65c0b983fcd8de2c448a2575e2a1e2c6d34de7c2a51422bcb3926a304ba4594d","target":"graph","created_at":"2026-07-13T00:17:32Z","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/2607.08984/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Brent Kong, Tejas Ram, Tony Yue Yu","cross_cats":["cs.AI","cs.GT","math.CO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-09T23:17:17Z","title":"AlphaZero in Sparsely Rewarded Games: Limits and Auxiliary Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08984","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":"sha256:8eedabb9f455ced07d4876973a7ee350f87cbb1b55dd8b036a3b741a89018281","target":"record","created_at":"2026-07-13T00:17:32Z","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":"fd8a192991168773a145a2289199b20cf521fec7caaae5a47f401570ae56afd5","cross_cats_sorted":["cs.AI","cs.GT","math.CO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-09T23:17:17Z","title_canon_sha256":"7b3d5fbd0791f0edd5042eb317882536138af403e276ac1c8dafc39f9ae5c7be"},"schema_version":"1.0","source":{"id":"2607.08984","kind":"arxiv","version":1}},"canonical_sha256":"ff1749141afda4925cebbecca3763ab9c0b3859549d593c2694d237334996c2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff1749141afda4925cebbecca3763ab9c0b3859549d593c2694d237334996c2d","first_computed_at":"2026-07-13T00:17:32.061046Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-13T00:17:32.061046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dTs30UBn1+TzqcT7OgqjFtPeOXw2Q+x+e5bGLNbYye7rISaZbO8XG6Th6JKRtZi1euSajOi/BEv6emhwgqc7CQ==","signature_status":"signed_v1","signed_at":"2026-07-13T00:17:32.062024Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.08984","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8eedabb9f455ced07d4876973a7ee350f87cbb1b55dd8b036a3b741a89018281","sha256:65c0b983fcd8de2c448a2575e2a1e2c6d34de7c2a51422bcb3926a304ba4594d"],"state_sha256":"df7e000a5022e245e50c0c1af797edf2b8673b407c5e7f33a2beb29709e731f0"}