{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HBJXVXWGHB7XU3RKYG3WTYCAYI","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":"0c5121ba3906d920cf5cef838cbcae8656fdd5d5f971aadd20a325ca322749ad","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-05T06:28:54Z","title_canon_sha256":"2fdd0aaab271c41304d847eadab4db3277636e61eaf66ef354064ee94773df96"},"schema_version":"1.0","source":{"id":"2410.04055","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04055","created_at":"2026-07-05T11:16:29Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04055v3","created_at":"2026-07-05T11:16:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04055","created_at":"2026-07-05T11:16:29Z"},{"alias_kind":"pith_short_12","alias_value":"HBJXVXWGHB7X","created_at":"2026-07-05T11:16:29Z"},{"alias_kind":"pith_short_16","alias_value":"HBJXVXWGHB7XU3RK","created_at":"2026-07-05T11:16:29Z"},{"alias_kind":"pith_short_8","alias_value":"HBJXVXWG","created_at":"2026-07-05T11:16:29Z"}],"graph_snapshots":[{"event_id":"sha256:52a20f141a59557acbddeebe2f912dfc71e84adf01f8698069efb73b69f1159a","target":"graph","created_at":"2026-07-05T11:16:29Z","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/2410.04055/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Vision-Language Models (VLMs) have shown remarkable abilities in visual and language reasoning tasks, they invariably generate flawed responses. Self-correction that instructs models to refine their outputs presents a promising solution to this issue. Previous studies have mainly concentrated on Large Language Models (LLMs), while the self-correction abilities of VLMs, particularly concerning both visual and linguistic information, remain largely unexamined. This study investigates the self-correction capabilities of VLMs during both inference and fine-tuning stages. We introduce a Self-","authors_text":"Hehai Lin, Heng Ji, Jiayi He, Qingyun Wang, Yi Fung","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-05T06:28:54Z","title":"Self-Correction is More than Refinement: A Learning Framework for Visual and Language Reasoning Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04055","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:a6db4999a9667f33ac960070f2be0e839cdb7697995d23986f4853fe5d7a142f","target":"record","created_at":"2026-07-05T11:16:29Z","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":"0c5121ba3906d920cf5cef838cbcae8656fdd5d5f971aadd20a325ca322749ad","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-05T06:28:54Z","title_canon_sha256":"2fdd0aaab271c41304d847eadab4db3277636e61eaf66ef354064ee94773df96"},"schema_version":"1.0","source":{"id":"2410.04055","kind":"arxiv","version":3}},"canonical_sha256":"38537adec6387f7a6e2ac1b769e040c2063b6b77ba5901ecbfb2fcb22ece2f8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"38537adec6387f7a6e2ac1b769e040c2063b6b77ba5901ecbfb2fcb22ece2f8d","first_computed_at":"2026-07-05T11:16:29.799795Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:29.799795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GRbEHAB9lqOSfDnjiVjznCUo4rsMcm/LvXHM1sI7y3+esb0Q/Dz8IkXsq/77EtmGxMz7MdaXYx+iruiWVDwPAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:29.800394Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.04055","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6db4999a9667f33ac960070f2be0e839cdb7697995d23986f4853fe5d7a142f","sha256:52a20f141a59557acbddeebe2f912dfc71e84adf01f8698069efb73b69f1159a"],"state_sha256":"c5bb944e2f52c5afb00e2634f32c6cf1b461464b60facfa9c098c079dad9c1d1"}