{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7PO4OVECGY3WNX7LPRQYSX7SNA","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":"3f8337a962b8bc3879fb509094acc886b4eb7dce3089c1eb720f37d995b0ac0c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-12T21:44:32Z","title_canon_sha256":"94333505da28d44dcbd781ff5d778826efe423c7e6d459cd74422365398586aa"},"schema_version":"1.0","source":{"id":"2402.08078","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.08078","created_at":"2026-07-05T07:44:26Z"},{"alias_kind":"arxiv_version","alias_value":"2402.08078v1","created_at":"2026-07-05T07:44:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08078","created_at":"2026-07-05T07:44:26Z"},{"alias_kind":"pith_short_12","alias_value":"7PO4OVECGY3W","created_at":"2026-07-05T07:44:26Z"},{"alias_kind":"pith_short_16","alias_value":"7PO4OVECGY3WNX7L","created_at":"2026-07-05T07:44:26Z"},{"alias_kind":"pith_short_8","alias_value":"7PO4OVEC","created_at":"2026-07-05T07:44:26Z"}],"graph_snapshots":[{"event_id":"sha256:815d9ca56f9880336c04d00103aa79a0ca05fd35be7b8f2f3e1fc16e0b0fc571","target":"graph","created_at":"2026-07-05T07:44:26Z","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/2402.08078/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"By formally defining the training processes of large language models (LLMs), which usually encompasses pre-training, supervised fine-tuning, and reinforcement learning with human feedback, within a single and unified machine learning paradigm, we can glean pivotal insights for advancing LLM technologies. This position paper delineates the parallels between the training methods of LLMs and the strategies employed for the development of agents in two-player games, as studied in game theory, reinforcement learning, and multi-agent systems. We propose a re-conceptualization of LLM learning process","authors_text":"Hang Li, Peng Sun, Yang Liu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-12T21:44:32Z","title":"Large Language Models as Agents in Two-Player Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08078","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:a0e0991575db9b0b4ee6867e984116124425083abaea078e51131121dd1fdd03","target":"record","created_at":"2026-07-05T07:44:26Z","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":"3f8337a962b8bc3879fb509094acc886b4eb7dce3089c1eb720f37d995b0ac0c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-12T21:44:32Z","title_canon_sha256":"94333505da28d44dcbd781ff5d778826efe423c7e6d459cd74422365398586aa"},"schema_version":"1.0","source":{"id":"2402.08078","kind":"arxiv","version":1}},"canonical_sha256":"fbddc75482363766dfeb7c61895ff2682a5d984b7f5b0b340458ab388ddcfc4b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fbddc75482363766dfeb7c61895ff2682a5d984b7f5b0b340458ab388ddcfc4b","first_computed_at":"2026-07-05T07:44:26.915383Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:44:26.915383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fvTcb+AgCHbLx9lBuGT0XFlchEhnf+GeTdPfMqs6AIbKk3dLu+1S0hVwIMQvO5Cvqwpb11syTCGvch8h3YHPAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:44:26.915790Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.08078","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0e0991575db9b0b4ee6867e984116124425083abaea078e51131121dd1fdd03","sha256:815d9ca56f9880336c04d00103aa79a0ca05fd35be7b8f2f3e1fc16e0b0fc571"],"state_sha256":"54d1b866744c99a15361b2c091103fa2bbe966f1fd622b5f6454a6ef8f89d5ca"}