{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XT445SZJ6BJ6F7COBR67ECJNU2","short_pith_number":"pith:XT445SZJ","schema_version":"1.0","canonical_sha256":"bcf9cecb29f053e2fc4e0c7df2092da692d52035d03b811d825ce62fba9382de","source":{"kind":"arxiv","id":"2603.00374","version":2},"attestation_state":"computed","paper":{"title":"Conservative Equilibrium Discovery in Offline Game-Theoretic Multiagent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Austin A. Nguyen, Michael P. Wellman","submitted_at":"2026-02-27T23:24:02Z","abstract_excerpt":"Offline learning of strategies takes data efficiency to its extreme by restricting algorithms to a fixed dataset of state-action trajectories. We consider the problem in a mixed-motive multiagent setting, where the goal is to solve a game under the offline learning constraint. We first frame this problem in terms of selecting among candidate equilibria. Since datasets may inform only a small fraction of game dynamics, it is generally infeasible in offline game-solving to even verify a proposed solution is a true equilibrium. Therefore, we consider the relative probability of low regret (i.e., "},"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":"2603.00374","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-27T23:24:02Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"114045c00bdd9df76312c39d4e184ead159d2728ef58ba0748038dd8f74a9516","abstract_canon_sha256":"7d98600768a3514745b21963dd4d03baf21d251c7ae01b3ba1e06ff62871e3c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T00:14:02.527477Z","signature_b64":"1x+6s6kpirZ3fEW3czbXbqUh0BuyMV7r8z2mYosBFxxdSzaHHRNqJyd60zpBbzsX3YAJ6V3M2SGY16b3hUU+Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcf9cecb29f053e2fc4e0c7df2092da692d52035d03b811d825ce62fba9382de","last_reissued_at":"2026-06-29T00:14:02.526900Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T00:14:02.526900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conservative Equilibrium Discovery in Offline Game-Theoretic Multiagent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Austin A. Nguyen, Michael P. Wellman","submitted_at":"2026-02-27T23:24:02Z","abstract_excerpt":"Offline learning of strategies takes data efficiency to its extreme by restricting algorithms to a fixed dataset of state-action trajectories. We consider the problem in a mixed-motive multiagent setting, where the goal is to solve a game under the offline learning constraint. We first frame this problem in terms of selecting among candidate equilibria. Since datasets may inform only a small fraction of game dynamics, it is generally infeasible in offline game-solving to even verify a proposed solution is a true equilibrium. Therefore, we consider the relative probability of low regret (i.e., "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.00374","kind":"arxiv","version":2},"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/2603.00374/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":"2603.00374","created_at":"2026-06-29T00:14:02.526962+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.00374v2","created_at":"2026-06-29T00:14:02.526962+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.00374","created_at":"2026-06-29T00:14:02.526962+00:00"},{"alias_kind":"pith_short_12","alias_value":"XT445SZJ6BJ6","created_at":"2026-06-29T00:14:02.526962+00:00"},{"alias_kind":"pith_short_16","alias_value":"XT445SZJ6BJ6F7CO","created_at":"2026-06-29T00:14:02.526962+00:00"},{"alias_kind":"pith_short_8","alias_value":"XT445SZJ","created_at":"2026-06-29T00:14:02.526962+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/XT445SZJ6BJ6F7COBR67ECJNU2","json":"https://pith.science/pith/XT445SZJ6BJ6F7COBR67ECJNU2.json","graph_json":"https://pith.science/api/pith-number/XT445SZJ6BJ6F7COBR67ECJNU2/graph.json","events_json":"https://pith.science/api/pith-number/XT445SZJ6BJ6F7COBR67ECJNU2/events.json","paper":"https://pith.science/paper/XT445SZJ"},"agent_actions":{"view_html":"https://pith.science/pith/XT445SZJ6BJ6F7COBR67ECJNU2","download_json":"https://pith.science/pith/XT445SZJ6BJ6F7COBR67ECJNU2.json","view_paper":"https://pith.science/paper/XT445SZJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.00374&json=true","fetch_graph":"https://pith.science/api/pith-number/XT445SZJ6BJ6F7COBR67ECJNU2/graph.json","fetch_events":"https://pith.science/api/pith-number/XT445SZJ6BJ6F7COBR67ECJNU2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XT445SZJ6BJ6F7COBR67ECJNU2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XT445SZJ6BJ6F7COBR67ECJNU2/action/storage_attestation","attest_author":"https://pith.science/pith/XT445SZJ6BJ6F7COBR67ECJNU2/action/author_attestation","sign_citation":"https://pith.science/pith/XT445SZJ6BJ6F7COBR67ECJNU2/action/citation_signature","submit_replication":"https://pith.science/pith/XT445SZJ6BJ6F7COBR67ECJNU2/action/replication_record"}},"created_at":"2026-06-29T00:14:02.526962+00:00","updated_at":"2026-06-29T00:14:02.526962+00:00"}