{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RKU3JY4YQ73ERIT3X2RZDZLQ4A","short_pith_number":"pith:RKU3JY4Y","canonical_record":{"source":{"id":"2410.18881","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-24T16:17:18Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"457ba0670c3eb3a4cc0afdeb24d205d2f8ea91d8aee1fc31ff981cba8fb187bb","abstract_canon_sha256":"7ccf7f888879734ecc03eec65174e298caecc2b7fff325afd4ab49cf55d217c2"},"schema_version":"1.0"},"canonical_sha256":"8aa9b4e39887f648a27bbea391e570e02476ab0374d18f034844fd0ff57b486f","source":{"kind":"arxiv","id":"2410.18881","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18881","created_at":"2026-07-05T11:16:30Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18881v2","created_at":"2026-07-05T11:16:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18881","created_at":"2026-07-05T11:16:30Z"},{"alias_kind":"pith_short_12","alias_value":"RKU3JY4YQ73E","created_at":"2026-07-05T11:16:30Z"},{"alias_kind":"pith_short_16","alias_value":"RKU3JY4YQ73ERIT3","created_at":"2026-07-05T11:16:30Z"},{"alias_kind":"pith_short_8","alias_value":"RKU3JY4Y","created_at":"2026-07-05T11:16:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RKU3JY4YQ73ERIT3X2RZDZLQ4A","target":"record","payload":{"canonical_record":{"source":{"id":"2410.18881","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-24T16:17:18Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"457ba0670c3eb3a4cc0afdeb24d205d2f8ea91d8aee1fc31ff981cba8fb187bb","abstract_canon_sha256":"7ccf7f888879734ecc03eec65174e298caecc2b7fff325afd4ab49cf55d217c2"},"schema_version":"1.0"},"canonical_sha256":"8aa9b4e39887f648a27bbea391e570e02476ab0374d18f034844fd0ff57b486f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:30.110072Z","signature_b64":"vOtQqAaNKTaquGGe9IE6nYwofWcx8F6L7y9wv60SpVZUIMccwA8ZII23CxolXyO07GpgwJLTPka3qwzlUiOLAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8aa9b4e39887f648a27bbea391e570e02476ab0374d18f034844fd0ff57b486f","last_reissued_at":"2026-07-05T11:16:30.109509Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:30.109509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.18881","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:16:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+VaRwMBVKFUybjWSDrvmWSI062muueoEm0iJ1ShIVEnZ5jA8oC+fLTg36AnBZhfzkvgPM657Lmdy5iK4IXdpAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T14:08:31.047965Z"},"content_sha256":"dae4d8871a48f9750f8e6c50513478e5d3bc24d05ea6d9bff34e8fc654517ec6","schema_version":"1.0","event_id":"sha256:dae4d8871a48f9750f8e6c50513478e5d3bc24d05ea6d9bff34e8fc654517ec6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RKU3JY4YQ73ERIT3X2RZDZLQ4A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diff-Instruct++: Training One-step Text-to-image Generator Model to Align with Human Preferences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Weijian Luo","submitted_at":"2024-10-24T16:17:18Z","abstract_excerpt":"One-step text-to-image generator models offer advantages such as swift inference efficiency, flexible architectures, and state-of-the-art generation performance. In this paper, we study the problem of aligning one-step generator models with human preferences for the first time. Inspired by the success of reinforcement learning using human feedback (RLHF), we formulate the alignment problem as maximizing expected human reward functions while adding an Integral Kullback-Leibler divergence term to prevent the generator from diverging. By overcoming technical challenges, we introduce Diff-Instruct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18881","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.18881/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:16:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sXQxT5zX82hBCmvNpjSFoTEPbn3h+9ZHG7pz7qlIuq+cRUNlhNFKx2AgliSq1Y4Bd1+cNCEJlcpqQBc9TArSAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T14:08:31.048782Z"},"content_sha256":"08078d3c164327c8170b35975076c9f09e6ee8eafb7bc31fb86a45913e043ea7","schema_version":"1.0","event_id":"sha256:08078d3c164327c8170b35975076c9f09e6ee8eafb7bc31fb86a45913e043ea7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RKU3JY4YQ73ERIT3X2RZDZLQ4A/bundle.json","state_url":"https://pith.science/pith/RKU3JY4YQ73ERIT3X2RZDZLQ4A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RKU3JY4YQ73ERIT3X2RZDZLQ4A/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T14:08:31Z","links":{"resolver":"https://pith.science/pith/RKU3JY4YQ73ERIT3X2RZDZLQ4A","bundle":"https://pith.science/pith/RKU3JY4YQ73ERIT3X2RZDZLQ4A/bundle.json","state":"https://pith.science/pith/RKU3JY4YQ73ERIT3X2RZDZLQ4A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RKU3JY4YQ73ERIT3X2RZDZLQ4A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RKU3JY4YQ73ERIT3X2RZDZLQ4A","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":"7ccf7f888879734ecc03eec65174e298caecc2b7fff325afd4ab49cf55d217c2","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-24T16:17:18Z","title_canon_sha256":"457ba0670c3eb3a4cc0afdeb24d205d2f8ea91d8aee1fc31ff981cba8fb187bb"},"schema_version":"1.0","source":{"id":"2410.18881","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18881","created_at":"2026-07-05T11:16:30Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18881v2","created_at":"2026-07-05T11:16:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18881","created_at":"2026-07-05T11:16:30Z"},{"alias_kind":"pith_short_12","alias_value":"RKU3JY4YQ73E","created_at":"2026-07-05T11:16:30Z"},{"alias_kind":"pith_short_16","alias_value":"RKU3JY4YQ73ERIT3","created_at":"2026-07-05T11:16:30Z"},{"alias_kind":"pith_short_8","alias_value":"RKU3JY4Y","created_at":"2026-07-05T11:16:30Z"}],"graph_snapshots":[{"event_id":"sha256:08078d3c164327c8170b35975076c9f09e6ee8eafb7bc31fb86a45913e043ea7","target":"graph","created_at":"2026-07-05T11:16:30Z","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/2410.18881/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One-step text-to-image generator models offer advantages such as swift inference efficiency, flexible architectures, and state-of-the-art generation performance. In this paper, we study the problem of aligning one-step generator models with human preferences for the first time. Inspired by the success of reinforcement learning using human feedback (RLHF), we formulate the alignment problem as maximizing expected human reward functions while adding an Integral Kullback-Leibler divergence term to prevent the generator from diverging. By overcoming technical challenges, we introduce Diff-Instruct","authors_text":"Weijian Luo","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-24T16:17:18Z","title":"Diff-Instruct++: Training One-step Text-to-image Generator Model to Align with Human Preferences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18881","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:dae4d8871a48f9750f8e6c50513478e5d3bc24d05ea6d9bff34e8fc654517ec6","target":"record","created_at":"2026-07-05T11:16:30Z","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":"7ccf7f888879734ecc03eec65174e298caecc2b7fff325afd4ab49cf55d217c2","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-24T16:17:18Z","title_canon_sha256":"457ba0670c3eb3a4cc0afdeb24d205d2f8ea91d8aee1fc31ff981cba8fb187bb"},"schema_version":"1.0","source":{"id":"2410.18881","kind":"arxiv","version":2}},"canonical_sha256":"8aa9b4e39887f648a27bbea391e570e02476ab0374d18f034844fd0ff57b486f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8aa9b4e39887f648a27bbea391e570e02476ab0374d18f034844fd0ff57b486f","first_computed_at":"2026-07-05T11:16:30.109509Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:30.109509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vOtQqAaNKTaquGGe9IE6nYwofWcx8F6L7y9wv60SpVZUIMccwA8ZII23CxolXyO07GpgwJLTPka3qwzlUiOLAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:30.110072Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.18881","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dae4d8871a48f9750f8e6c50513478e5d3bc24d05ea6d9bff34e8fc654517ec6","sha256:08078d3c164327c8170b35975076c9f09e6ee8eafb7bc31fb86a45913e043ea7"],"state_sha256":"6a366e3adcfac360628cbc37ea5f65a68c6e6cbefec98a5c3c7598437e616852"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"btTN7RIfibK/remqe3QGG/KIVJSkpW2aFnr9Mo5vsm5ZG2sLMpKPNSlYj0MrKhbOXbz8BuLxdvBFDWpiL2rlDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T14:08:31.054935Z","bundle_sha256":"63cce2ebfd7e3f879305edf45b068aebece81c3a8dad7d38639c12e60e5c89ab"}}