{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:G6C253PIK2ZU3TUZ2FPCTKW26P","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":"fbddf761c66040086436c0ac44e26671e763e2d32e4f7ccf849bedc06e2b949e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T03:52:35Z","title_canon_sha256":"98329a18db8e31306d4fc6ceb5f8fe00680d4aea3173c685f87e8ff4ac380174"},"schema_version":"1.0","source":{"id":"2406.18872","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.18872","created_at":"2026-07-05T09:45:50Z"},{"alias_kind":"arxiv_version","alias_value":"2406.18872v2","created_at":"2026-07-05T09:45:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18872","created_at":"2026-07-05T09:45:50Z"},{"alias_kind":"pith_short_12","alias_value":"G6C253PIK2ZU","created_at":"2026-07-05T09:45:50Z"},{"alias_kind":"pith_short_16","alias_value":"G6C253PIK2ZU3TUZ","created_at":"2026-07-05T09:45:50Z"},{"alias_kind":"pith_short_8","alias_value":"G6C253PI","created_at":"2026-07-05T09:45:50Z"}],"graph_snapshots":[{"event_id":"sha256:e75f3447b45896abcb523acd251d1bdcd4f7829b701620e20f1d9cbcef59aaa1","target":"graph","created_at":"2026-07-05T09:45:50Z","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/2406.18872/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Game-playing agents like AlphaGo have achieved superhuman performance through self-play, which is theoretically guaranteed to yield optimal policies in competitive games. However, most language tasks are partially or fully cooperative, so it is an open question whether techniques like self-play can effectively be used to improve language models. We empirically investigate this question in a negotiation game setting known as Deal or No Deal (DoND). Crucially, the objective in DoND can be modified to produce a fully cooperative game, a strictly competitive one, or anything in between. We finetun","authors_text":"Austen Liao, Dan Klein, Nicholas Tomlin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T03:52:35Z","title":"Efficacy of Language Model Self-Play in Non-Zero-Sum Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18872","kind":"arxiv","version":2},"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":"sha256:96d165c3c97e49d168e119059d15dc228ceb13de378675d2884a07385260b401","target":"record","created_at":"2026-07-05T09:45:50Z","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":"fbddf761c66040086436c0ac44e26671e763e2d32e4f7ccf849bedc06e2b949e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T03:52:35Z","title_canon_sha256":"98329a18db8e31306d4fc6ceb5f8fe00680d4aea3173c685f87e8ff4ac380174"},"schema_version":"1.0","source":{"id":"2406.18872","kind":"arxiv","version":2}},"canonical_sha256":"3785aeede856b34dce99d15e29aadaf3ef774fae8c94975e5cf30ff78380719f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3785aeede856b34dce99d15e29aadaf3ef774fae8c94975e5cf30ff78380719f","first_computed_at":"2026-07-05T09:45:50.812803Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:50.812803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0pc0A3rSODf2TeWir6TCX512lLQg3eoeq27XR+iJyd+esQ66XshRIBt9eKjqgT35rBZu3fx8Q9RPhIAD5uI9AA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:50.813257Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.18872","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96d165c3c97e49d168e119059d15dc228ceb13de378675d2884a07385260b401","sha256:e75f3447b45896abcb523acd251d1bdcd4f7829b701620e20f1d9cbcef59aaa1"],"state_sha256":"841cfdac8941c1a6f75214b05d6b7f179316794f97000eb4f1de6d44fc4262d9"}