{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MZ7B3ZTCU56GKZZ3N3BKZ67WF6","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":"d9208bbec68b38fd95da5bb6dc9263892f7b7cf1e0ab9d032384b6feb277cf1e","cross_cats_sorted":["cs.AI","cs.CV","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-07T15:12:01Z","title_canon_sha256":"769ae352ab00c57ee20b135c40a9cc763b575b848dd86323ade73ec7eac3913e"},"schema_version":"1.0","source":{"id":"2410.05116","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.05116","created_at":"2026-07-05T10:30:24Z"},{"alias_kind":"arxiv_version","alias_value":"2410.05116v3","created_at":"2026-07-05T10:30:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05116","created_at":"2026-07-05T10:30:24Z"},{"alias_kind":"pith_short_12","alias_value":"MZ7B3ZTCU56G","created_at":"2026-07-05T10:30:24Z"},{"alias_kind":"pith_short_16","alias_value":"MZ7B3ZTCU56GKZZ3","created_at":"2026-07-05T10:30:24Z"},{"alias_kind":"pith_short_8","alias_value":"MZ7B3ZTC","created_at":"2026-07-05T10:30:24Z"}],"graph_snapshots":[{"event_id":"sha256:1be4432b4f0e063acd25f7c0eb4b09786ac5fda07b87ecb5ce3870fef5d7cbe9","target":"graph","created_at":"2026-07-05T10:30:24Z","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/2410.05116/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Controllable generation through Stable Diffusion (SD) fine-tuning aims to improve fidelity, safety, and alignment with human guidance. Existing reinforcement learning from human feedback methods usually rely on predefined heuristic reward functions or pretrained reward models built on large-scale datasets, limiting their applicability to scenarios where collecting such data is costly or difficult. To effectively and efficiently utilize human feedback, we develop a framework, HERO, which leverages online human feedback collected on the fly during model learning. Specifically, HERO features two ","authors_text":"Ayano Hiranaka, Chieh-Hsin Lai, Dongjun Kim, Naoki Murata, Shang-Fu Chen, Shao-Hua Sun, Takashi Shibuya, Wei-Hsiang Liao, Yuki Mitsufuji","cross_cats":["cs.AI","cs.CV","cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-07T15:12:01Z","title":"HERO: Human-Feedback Efficient Reinforcement Learning for Online Diffusion Model Finetuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05116","kind":"arxiv","version":3},"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:a8036d69dbb0e7966e54fc347fe1a9f86735c8168505b24b5654dc2b493b6402","target":"record","created_at":"2026-07-05T10:30:24Z","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":"d9208bbec68b38fd95da5bb6dc9263892f7b7cf1e0ab9d032384b6feb277cf1e","cross_cats_sorted":["cs.AI","cs.CV","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-07T15:12:01Z","title_canon_sha256":"769ae352ab00c57ee20b135c40a9cc763b575b848dd86323ade73ec7eac3913e"},"schema_version":"1.0","source":{"id":"2410.05116","kind":"arxiv","version":3}},"canonical_sha256":"667e1de662a77c65673b6ec2acfbf62fae610a16e5f55bcc1f3d7a63ad028bb0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"667e1de662a77c65673b6ec2acfbf62fae610a16e5f55bcc1f3d7a63ad028bb0","first_computed_at":"2026-07-05T10:30:24.116860Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:30:24.116860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PMegossCCxTBPaw0KqrcIuA5uLngUC+//ogIMVBs+2siOimD7XUYk+ql43RWmWOvlaQoSz8shBF467kaepn0Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:30:24.117517Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.05116","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8036d69dbb0e7966e54fc347fe1a9f86735c8168505b24b5654dc2b493b6402","sha256:1be4432b4f0e063acd25f7c0eb4b09786ac5fda07b87ecb5ce3870fef5d7cbe9"],"state_sha256":"2317f9eca5de6fc93d207d9805d96af80f0b52eb2b5add9c14cea21f794d0079"}