{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ASX6PYDUHR3JIYMI6IVEZBJC3N","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":"5bc5db6acd66769163699baf67f86f5419fee969095efe22b50096b843892446","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-03T13:53:08Z","title_canon_sha256":"b7a27c650dfe5409e8d4304e6b4bc65b66e19dc266bcdeed27dc865814225eea"},"schema_version":"1.0","source":{"id":"2310.02054","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.02054","created_at":"2026-07-05T07:40:57Z"},{"alias_kind":"arxiv_version","alias_value":"2310.02054v2","created_at":"2026-07-05T07:40:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02054","created_at":"2026-07-05T07:40:57Z"},{"alias_kind":"pith_short_12","alias_value":"ASX6PYDUHR3J","created_at":"2026-07-05T07:40:57Z"},{"alias_kind":"pith_short_16","alias_value":"ASX6PYDUHR3JIYMI","created_at":"2026-07-05T07:40:57Z"},{"alias_kind":"pith_short_8","alias_value":"ASX6PYDU","created_at":"2026-07-05T07:40:57Z"}],"graph_snapshots":[{"event_id":"sha256:dd8393421dcd1ee929197a7ea2c428652f29c82fd45bc924d4b907ec515c5664","target":"graph","created_at":"2026-07-05T07:40:57Z","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/2310.02054/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligning agent behaviors with diverse human preferences remains a challenging problem in reinforcement learning (RL), owing to the inherent abstractness and mutability of human preferences. To address these issues, we propose AlignDiff, a novel framework that leverages RL from Human Feedback (RLHF) to quantify human preferences, covering abstractness, and utilizes them to guide diffusion planning for zero-shot behavior customizing, covering mutability. AlignDiff can accurately match user-customized behaviors and efficiently switch from one to another. To build the framework, we first establish","authors_text":"Changjie Fan, Fei Ni, Jianye Hao, Tangjie Lv, Yan Zheng, Yao Mu, Yifu Yuan, Yujing Hu, Zhipeng Hu, Zibin Dong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-03T13:53:08Z","title":"AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02054","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":"sha256:923c9444238f3985b89a6bdeb6198d182810143fcb37fff54c22bb5bb4f80c3f","target":"record","created_at":"2026-07-05T07:40:57Z","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":"5bc5db6acd66769163699baf67f86f5419fee969095efe22b50096b843892446","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-03T13:53:08Z","title_canon_sha256":"b7a27c650dfe5409e8d4304e6b4bc65b66e19dc266bcdeed27dc865814225eea"},"schema_version":"1.0","source":{"id":"2310.02054","kind":"arxiv","version":2}},"canonical_sha256":"04afe7e0743c76946188f22a4c8522db48d954e848be90f60549d2f923889e37","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04afe7e0743c76946188f22a4c8522db48d954e848be90f60549d2f923889e37","first_computed_at":"2026-07-05T07:40:57.726369Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:40:57.726369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RkOcMPpX/Jq0oMXH2gk75tC0KDWDEdNjJ9OWIcuMSVx33O5fLH2UhMQp4V+mcHCxazuFEYYi88elxu2+t0m0Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:40:57.726908Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.02054","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:923c9444238f3985b89a6bdeb6198d182810143fcb37fff54c22bb5bb4f80c3f","sha256:dd8393421dcd1ee929197a7ea2c428652f29c82fd45bc924d4b907ec515c5664"],"state_sha256":"0f9f731a61eb546f80667d030ace8e6a0651f4b37ff2361189b09038db04e15a"}