{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QYOOQNAWFPMRA2I74FZRHQSLXX","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":"0c9871474c23c1c550740cc4b7c9cb00f377afcccac362b750a0eb579dba2c8e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-07T11:20:32Z","title_canon_sha256":"bf81e6f077943feeb7e7f980b5ccdea1a19405b1eaffced74eabcfe7bce28847"},"schema_version":"1.0","source":{"id":"2404.04920","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.04920","created_at":"2026-07-05T09:18:24Z"},{"alias_kind":"arxiv_version","alias_value":"2404.04920v2","created_at":"2026-07-05T09:18:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04920","created_at":"2026-07-05T09:18:24Z"},{"alias_kind":"pith_short_12","alias_value":"QYOOQNAWFPMR","created_at":"2026-07-05T09:18:24Z"},{"alias_kind":"pith_short_16","alias_value":"QYOOQNAWFPMRA2I7","created_at":"2026-07-05T09:18:24Z"},{"alias_kind":"pith_short_8","alias_value":"QYOOQNAW","created_at":"2026-07-05T09:18:24Z"}],"graph_snapshots":[{"event_id":"sha256:3ffbe82dd9647e750d8ad8efc166f272a88f452c6dcb59b99661f797a7d32b07","target":"graph","created_at":"2026-07-05T09:18:24Z","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/2404.04920/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sequential decision-making is desired to align with human intents and exhibit versatility across various tasks. Previous methods formulate it as a conditional generation process, utilizing return-conditioned diffusion models to directly model trajectory distributions. Nevertheless, the return-conditioned paradigm relies on pre-defined reward functions, facing challenges when applied in multi-task settings characterized by varying reward functions (versatility) and showing limited controllability concerning human preferences (alignment). In this work, we adopt multi-task preferences as a unifie","authors_text":"Changhong Wang, Chenjia Bai, Haoran He, Xudong Yu, Xuelong Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-07T11:20:32Z","title":"Regularized Conditional Diffusion Model for Multi-Task Preference Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04920","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:b04ef9d37c10ba7427cb5463e227ff7eac32fd354573d5e1103392ba7f82d989","target":"record","created_at":"2026-07-05T09:18:24Z","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":"0c9871474c23c1c550740cc4b7c9cb00f377afcccac362b750a0eb579dba2c8e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-07T11:20:32Z","title_canon_sha256":"bf81e6f077943feeb7e7f980b5ccdea1a19405b1eaffced74eabcfe7bce28847"},"schema_version":"1.0","source":{"id":"2404.04920","kind":"arxiv","version":2}},"canonical_sha256":"861ce834162bd910691fe17313c24bbdd19b606c790445656d1b2020bfa10700","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"861ce834162bd910691fe17313c24bbdd19b606c790445656d1b2020bfa10700","first_computed_at":"2026-07-05T09:18:24.560604Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:24.560604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"scUBySOMr2aHJIYnryRak6H+73Yh9AMTiLaciTrNVR5FzvaFEiNkG8UloHA7FEJ8byPa2LcZzrz1Om/8pcgeCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:24.561222Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.04920","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b04ef9d37c10ba7427cb5463e227ff7eac32fd354573d5e1103392ba7f82d989","sha256:3ffbe82dd9647e750d8ad8efc166f272a88f452c6dcb59b99661f797a7d32b07"],"state_sha256":"b81e37604a076b24e87e0b800f31c9d3760dd575f4aefecd936b1ebcf8963fef"}