{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:I4MSTWBEGB4WJ3AXRJGTP4QLLQ","merge_version":"pith-open-graph-merge-v1","event_count":38,"valid_event_count":38,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6ffb7764428421f4404d65d13380ac09569d5121b2a27b24c2aef129bd26a362","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-08T17:49:49Z","title_canon_sha256":"407bd76373e281dca11540e76bc3f3380b52a35ed9918d92196109f640762f6b"},"schema_version":"1.0","source":{"id":"2607.07693","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.07693","created_at":"2026-07-09T01:20:39Z"},{"alias_kind":"arxiv_version","alias_value":"2607.07693v1","created_at":"2026-07-09T01:20:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07693","created_at":"2026-07-09T01:20:39Z"},{"alias_kind":"pith_short_12","alias_value":"I4MSTWBEGB4W","created_at":"2026-07-09T01:20:39Z"},{"alias_kind":"pith_short_16","alias_value":"I4MSTWBEGB4WJ3AX","created_at":"2026-07-09T01:20:39Z"},{"alias_kind":"pith_short_8","alias_value":"I4MSTWBE","created_at":"2026-07-09T01:20:39Z"}],"graph_snapshots":[{"event_id":"sha256:276f8865bd1579eb94bcdcb538b33964dc71a921dc5a05bc991a414d249ba5b2","target":"graph","created_at":"2026-07-09T01:20:39Z","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/2607.07693/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning from human feedback (RLHF) has emerged as a powerful paradigm for aligning generative models with human preferences. However, applying RLHF to diffusion models remains highly feedback inefficient, as existing approaches typically require large amounts of human or reward model evaluations. This limitation reduces the practicality of diffusion RLHF in realworld settings where feedback is the primary bottleneck. In this paper, we propose two complementary strategies that substantially improve the feedback efficiency of diffusion RLHF while preserving generalization to unsee","authors_text":"Abhinav Shrivastava, Eric Zhu, Soumik Mukhopadhyay","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-08T17:49:49Z","title":"Selective Timestep Weighting and Advantage-Based Replay for Sample-Efficient Diffusion RLHF"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07693","kind":"arxiv","version":1},"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:ea6b143628ea8d5666d57f25654d9f5ec7f49bd22d44e0a926f8163149110ecd","target":"record","created_at":"2026-07-09T01:20:39Z","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":"6ffb7764428421f4404d65d13380ac09569d5121b2a27b24c2aef129bd26a362","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-08T17:49:49Z","title_canon_sha256":"407bd76373e281dca11540e76bc3f3380b52a35ed9918d92196109f640762f6b"},"schema_version":"1.0","source":{"id":"2607.07693","kind":"arxiv","version":1}},"canonical_sha256":"471929d824307964ec178a4d37f20b5c36a2c5a58f30c0fc4cabbe3819774530","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"471929d824307964ec178a4d37f20b5c36a2c5a58f30c0fc4cabbe3819774530","first_computed_at":"2026-07-09T01:20:39.330000Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-09T01:20:39.330000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tka0zcG3EKqORKGrANNo01lVp/W3lxqlWkwJTY8llKjjMZT+V18t9ebPgEjIKftLb4gbBPPRdj0ZuphZLIThBA==","signature_status":"signed_v1","signed_at":"2026-07-09T01:20:39.330447Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.07693","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:0ad2650666092c8b5429aaa494b8f0c7472f749f0ec783a35b8ddf27cbf7ae66","sha256:0b8f0926152da1637c66e223cbbb1ee3d55dcf84dffdf355e50e81446faf93af","sha256:185a028f13ba18bb999e8a5e046e79302c27526a575acd864a787b1b0de17c0f","sha256:1bb22785ca1023575bf7accb3dc404a70f71cafc83d8b086ad931c14ff35049d","sha256:222b71c4bcff1e9a0be9e5970423b87a298c33aa7c03e0350727ae78f09ccb94","sha256:4620565ffe8745638b069cbafdfb180fdf94ba94b01cbb6b6b2e7f9d0dc9ce89","sha256:46e805f3c1ec9365203098097f848f2c30bd0d2983d86f81efe96704f750dfe0","sha256:48a6f71ff28e6cc040e75102bc3468bf2dd7068cc6ef220146b0f9eb3746ef44","sha256:51844fc66a2fe8baab705145d87347f5b813bd944b99397e38288dff1dd9ae77","sha256:5a85ab7ef000f35f8e8600d9963a86f44fefe415ecf2cbb3cbdd65ff02256d88","sha256:6129bf74114e872340508e847a12d3d14ba0fc25673ec9821932948e0f77197e","sha256:674a50cbd7d3a8f2e1a41014bce007e3ab318ece0bd7d79826be995f5bc2c382","sha256:68546a7263c39c7c1a2fa5dff9def26726b3989eee699a1516143779100b5957","sha256:69cb28c1e6ef1b78153f4f2a72dc474bbead3e1f9bf4c9047cf56dff1f633a72","sha256:6c900535bb8d371750ecb7b27b9dd5765693e509ed85d60b6d66cfc615b8a7bc","sha256:7c831b7b9c808c8a5b442b69e0f586fb5de6ebfadf5b9b83678b00d640e2652c","sha256:7f58308d15582fcb91946342225877b30392d33109574c39f6c9d4b2ba11d4e0","sha256:81d25c2f7e68c034489d3de613b8125db0635bafba18d614585962e8b93e2dff","sha256:85f96025436b47bc9185df95e7480828b51438c969313ad559e6d4ea4edcee34","sha256:8dbb1c76093e4b9128cbe9a8bec796c331fc39fe39b4fcd05550926606c17db6","sha256:9668d330f43785902d6ad2b1d3b92841c1f4445df173103ae4391e7c1952e5a3","sha256:9bd4fb5e9be95cfcd8694ac79de75849030b3245c1eb49ef89840df6b43e065f","sha256:a3bcadb25b02b5b249db0a9814e9f1fc7cb5e8464105dc0f6eb0e4ff43204181","sha256:a46d2393f0b5c4d0f1656426dfec653d38f99638226e451105bb605ba046455a","sha256:bb84eec67bf505eeeb1586da7bd61be3a9187c1ecb1664698ef71351cb98f887","sha256:c270b6b410dc7fce181887f2eacb729807ec8c37cc12def5f4582dbf5d672855","sha256:c61b0a2e061100bc19c02b208336b3d3febe53feeb48785d970b1fe556f5975e","sha256:cd29d5c465bfa7dfa33fb3fe139174d457dbc261eaa4b623ee82930bae2ec160","sha256:d13b31efc919306d6fec11e64426473f86d8e1e10538b2107f3fafc653483ca1","sha256:d14f2732a56a638bbe38d6ac1e5605b835fb2870675a31d153a844ede2d19bc9","sha256:d59b0fdc9c80bf7551b0040c3c75a3d2a35b070acbcda702f7cce45254eeb691","sha256:d737b050bbb8c2bfb2db3d5d23fb7f46315ff7afad88a7e328659bee250e8821","sha256:d8c6d98caa5fa260281a680fde26ce3a76253116d953cc7cd4f2280ce486a310","sha256:e07c7074408c9eea67967d2002526030fad626e8e3947e29405e455cb832039c","sha256:e6d7ac26997bfda4202ab9a7b4116e7e0b3b5d90639085952fda278b715be117","sha256:f355c994bbc202c7080eceb5b3c398fcb2ab8dde0e39e3d77acd23a5af8bbbbd"]}],"invalid_events":[],"applied_event_ids":["sha256:ea6b143628ea8d5666d57f25654d9f5ec7f49bd22d44e0a926f8163149110ecd","sha256:276f8865bd1579eb94bcdcb538b33964dc71a921dc5a05bc991a414d249ba5b2"],"state_sha256":"aede47cb1e46fbee6182264c3337f95d1f90aeeeca5e3b48ca6309fcbfad8b32"}