{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GXFSMDCR4HYFEG4QCDGPGYBOVS","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":"e371d954fb55b8145272b0ef908669836e9526183454433387899b730bc745da","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2025-03-06T18:22:29Z","title_canon_sha256":"d5c22d5278e4cbb8a7e4520bc22d18ad9f603212efcdc828cb6ef62c6995035a"},"schema_version":"1.0","source":{"id":"2503.04679","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.04679","created_at":"2026-07-05T10:25:45Z"},{"alias_kind":"arxiv_version","alias_value":"2503.04679v1","created_at":"2026-07-05T10:25:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04679","created_at":"2026-07-05T10:25:45Z"},{"alias_kind":"pith_short_12","alias_value":"GXFSMDCR4HYF","created_at":"2026-07-05T10:25:45Z"},{"alias_kind":"pith_short_16","alias_value":"GXFSMDCR4HYFEG4Q","created_at":"2026-07-05T10:25:45Z"},{"alias_kind":"pith_short_8","alias_value":"GXFSMDCR","created_at":"2026-07-05T10:25:45Z"}],"graph_snapshots":[{"event_id":"sha256:5326bfc8f40fa47c9d9004226e4fa28cd91989f0cfe6c0b1bb0e535627e4dbcc","target":"graph","created_at":"2026-07-05T10:25:45Z","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/2503.04679/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When reward functions are hand-designed, deep reinforcement learning algorithms often suffer from reward misspecification, causing them to learn suboptimal policies in terms of the intended task objectives. In the single-agent case, inverse reinforcement learning (IRL) techniques attempt to address this issue by inferring the reward function from expert demonstrations. However, in multi-agent problems, misalignment between the learned and true objectives is exacerbated due to increased environment non-stationarity and variance that scales with multiple agents. As such, in multi-agent general-s","authors_text":"Adam Khoja, Dhruv Kumar, Erdem B{\\i}y{\\i}k, Nathaniel Haynam, Vivek Myers","cross_cats":["cs.AI","cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2025-03-06T18:22:29Z","title":"Multi-Agent Inverse Q-Learning from Demonstrations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04679","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:ba2c5425ca4de70f33143e5aedcd8f087279719af1dab10aaa9169bbee196461","target":"record","created_at":"2026-07-05T10:25:45Z","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":"e371d954fb55b8145272b0ef908669836e9526183454433387899b730bc745da","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2025-03-06T18:22:29Z","title_canon_sha256":"d5c22d5278e4cbb8a7e4520bc22d18ad9f603212efcdc828cb6ef62c6995035a"},"schema_version":"1.0","source":{"id":"2503.04679","kind":"arxiv","version":1}},"canonical_sha256":"35cb260c51e1f0521b9010ccf3602eac8835770ac2109ea04958ce2da0c120c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35cb260c51e1f0521b9010ccf3602eac8835770ac2109ea04958ce2da0c120c0","first_computed_at":"2026-07-05T10:25:45.013956Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:25:45.013956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"psNPjI8vMD58JyDb8k7BuC758elRB/aI+DjAknd+/NgBXWKZ2MiV3lT/73knsJ99pNBAlaJAzelRaJ9GIBdUAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:25:45.014403Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.04679","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba2c5425ca4de70f33143e5aedcd8f087279719af1dab10aaa9169bbee196461","sha256:5326bfc8f40fa47c9d9004226e4fa28cd91989f0cfe6c0b1bb0e535627e4dbcc"],"state_sha256":"299a538a8492c9ea88d8695fad02b0c3e87e62bcc0066c52130c6f3b9ce1c45a"}