{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TGTLWJTBFRLTEXNVEEKFPPOCYI","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":"a5b2380e5441225390647836d9e33c5c0b36082000c3f766304870cacd6810e4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-18T23:31:01Z","title_canon_sha256":"418e4aba633311c87da4e07a729aa12f0453c9eafb56c5fdd2954e43c232d6d1"},"schema_version":"1.0","source":{"id":"2312.11752","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.11752","created_at":"2026-07-05T10:14:02Z"},{"alias_kind":"arxiv_version","alias_value":"2312.11752v5","created_at":"2026-07-05T10:14:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11752","created_at":"2026-07-05T10:14:02Z"},{"alias_kind":"pith_short_12","alias_value":"TGTLWJTBFRLT","created_at":"2026-07-05T10:14:02Z"},{"alias_kind":"pith_short_16","alias_value":"TGTLWJTBFRLTEXNV","created_at":"2026-07-05T10:14:02Z"},{"alias_kind":"pith_short_8","alias_value":"TGTLWJTB","created_at":"2026-07-05T10:14:02Z"}],"graph_snapshots":[{"event_id":"sha256:fc3a2955b8684321aa261444469928bf003b43badec2e62a10a9a1552274f773","target":"graph","created_at":"2026-07-05T10:14:02Z","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/2312.11752/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models have become a popular choice for representing actor policies in behavior cloning and offline reinforcement learning. This is due to their natural ability to optimize an expressive class of distributions over a continuous space. However, previous works fail to exploit the score-based structure of diffusion models, and instead utilize a simple behavior cloning term to train the actor, limiting their ability in the actor-critic setting. In this paper, we present a theoretical framework linking the structure of diffusion model policies to a learned Q-function, by linking the struc","authors_text":"Alejandro Escontrela, Michael Psenka, Pieter Abbeel, Yi Ma","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-18T23:31:01Z","title":"Learning a Diffusion Model Policy from Rewards via Q-Score Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11752","kind":"arxiv","version":5},"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:e1d1791da1a84f1c5e6a60840049761c89975228cdd5fb8dffbfc90d357ac809","target":"record","created_at":"2026-07-05T10:14:02Z","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":"a5b2380e5441225390647836d9e33c5c0b36082000c3f766304870cacd6810e4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-18T23:31:01Z","title_canon_sha256":"418e4aba633311c87da4e07a729aa12f0453c9eafb56c5fdd2954e43c232d6d1"},"schema_version":"1.0","source":{"id":"2312.11752","kind":"arxiv","version":5}},"canonical_sha256":"99a6bb26612c57325db5211457bdc2c22829da21838d32282bad9beebc364dcc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"99a6bb26612c57325db5211457bdc2c22829da21838d32282bad9beebc364dcc","first_computed_at":"2026-07-05T10:14:02.309973Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:02.309973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wHRGkWcJ+e4rSSVYnjv2v2eUlBDv+eaFIAsJ0aBTFfEHVk/EjL/LTnpGrwA+/8dqDY8LdHihyY/+bjH7ADV4Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:02.310468Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.11752","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1d1791da1a84f1c5e6a60840049761c89975228cdd5fb8dffbfc90d357ac809","sha256:fc3a2955b8684321aa261444469928bf003b43badec2e62a10a9a1552274f773"],"state_sha256":"1eedde410378ac2a669da52b366eeb8a1d7b1c49e9cb3e6db672ffa087ae16e5"}