{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6LJETYVCDBNREFY245737H5AYL","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":"527d809cdffe3c14c8d57996e69328e2b538807de6e07be7071943a7adf5744b","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T08:48:30Z","title_canon_sha256":"15e9421923c0c6f3271207856712f87cd9d32a4837d2199420cc42539845fc2e"},"schema_version":"1.0","source":{"id":"2411.14797","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14797","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14797v1","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14797","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"pith_short_12","alias_value":"6LJETYVCDBNR","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"pith_short_16","alias_value":"6LJETYVCDBNREFY2","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"pith_short_8","alias_value":"6LJETYVC","created_at":"2026-07-05T09:39:12Z"}],"graph_snapshots":[{"event_id":"sha256:8a25072f028b3789bdd52f7ce58e0b9d3b9abf0089d62e155bbc74b7694c660d","target":"graph","created_at":"2026-07-05T09:39:12Z","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/2411.14797/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal RLHF usually happens after supervised finetuning (SFT) stage to continually improve vision-language models' (VLMs) comprehension. Conventional wisdom holds its superiority over continual SFT during this preference alignment stage. In this paper, we observe that the inherent value of multimodal RLHF lies in its negative supervision, the logit of the rejected responses. We thus propose a novel negative supervised finetuning (nSFT) approach that fully excavates these information resided. Our nSFT disentangles this negative supervision in RLHF paradigm, and continually aligns VLMs with ","authors_text":"Gang Zhang, Jiangjiang Liu, Jingdong Wang, Ke Zhu, Qiang Chen, Yanpeng Sun, Yu Wang","cross_cats":["cs.AI","cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T08:48:30Z","title":"Continual SFT Matches Multimodal RLHF with Negative Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14797","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":"sha256:60dfbab80469968333f09b086dd52a48eb20c80515bfced5fb07bd1cc54a7184","target":"record","created_at":"2026-07-05T09:39:12Z","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":"527d809cdffe3c14c8d57996e69328e2b538807de6e07be7071943a7adf5744b","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T08:48:30Z","title_canon_sha256":"15e9421923c0c6f3271207856712f87cd9d32a4837d2199420cc42539845fc2e"},"schema_version":"1.0","source":{"id":"2411.14797","kind":"arxiv","version":1}},"canonical_sha256":"f2d249e2a2185b12171ae77fbf9fa0c2dd7a487e47f43aaea3affa5ab46e61b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2d249e2a2185b12171ae77fbf9fa0c2dd7a487e47f43aaea3affa5ab46e61b7","first_computed_at":"2026-07-05T09:39:12.085417Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:39:12.085417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JwAYqJUNG9Jl927a9aQxP3KYwCmAASUCTgIGllbi57nU8STU58dOxHFEas9SA01z0on2YmqIwp3+33akO4B4Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:39:12.085794Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14797","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60dfbab80469968333f09b086dd52a48eb20c80515bfced5fb07bd1cc54a7184","sha256:8a25072f028b3789bdd52f7ce58e0b9d3b9abf0089d62e155bbc74b7694c660d"],"state_sha256":"c68fecc60e08c7d62ee85687c1a735e2bc3f1197a0af63ba6677ac9dc8bb9ab2"}