{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IWYKFD7TLPXEFEFGSSUJJZKLMC","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":"899ae12c4dfda6d4e4aca496e424d90cbaca8e77a791c1d54abed0ecd5bb34a1","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T19:38:44Z","title_canon_sha256":"62de4fa9b56b21b79685bf35fe99b44400ec8d2a30878a1ca10c53cdce4ebc28"},"schema_version":"1.0","source":{"id":"2402.11690","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11690","created_at":"2026-07-05T07:46:43Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11690v1","created_at":"2026-07-05T07:46:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11690","created_at":"2026-07-05T07:46:43Z"},{"alias_kind":"pith_short_12","alias_value":"IWYKFD7TLPXE","created_at":"2026-07-05T07:46:43Z"},{"alias_kind":"pith_short_16","alias_value":"IWYKFD7TLPXEFEFG","created_at":"2026-07-05T07:46:43Z"},{"alias_kind":"pith_short_8","alias_value":"IWYKFD7T","created_at":"2026-07-05T07:46:43Z"}],"graph_snapshots":[{"event_id":"sha256:6011bc808a579028d72c4db9c2a7f57141e5c4d3b6d0987ce1cfbf0ba33d5afe","target":"graph","created_at":"2026-07-05T07:46:43Z","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/2402.11690/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite vision-language models' (VLMs) remarkable capabilities as versatile visual assistants, two substantial challenges persist within the existing VLM frameworks: (1) lacking task diversity in pretraining and visual instruction tuning, and (2) annotation error and bias in GPT-4 synthesized instruction tuning data. Both challenges lead to issues such as poor generalizability, hallucination, and catastrophic forgetting. To address these challenges, we construct Vision-Flan, the most diverse publicly available visual instruction tuning dataset to date, comprising 187 diverse tasks and 1,664,26","authors_text":"Chao Feng, Di Jin, Lifu Huang, Qifan Wang, Rulin Shao, Trevor Ashby, Ying Shen, Yu Cheng, Zhiyang Xu","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T19:38:44Z","title":"Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11690","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:f04535b87e50448ab8a881079f483f30d202d429a0dd5ea6d0763447ec635656","target":"record","created_at":"2026-07-05T07:46:43Z","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":"899ae12c4dfda6d4e4aca496e424d90cbaca8e77a791c1d54abed0ecd5bb34a1","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T19:38:44Z","title_canon_sha256":"62de4fa9b56b21b79685bf35fe99b44400ec8d2a30878a1ca10c53cdce4ebc28"},"schema_version":"1.0","source":{"id":"2402.11690","kind":"arxiv","version":1}},"canonical_sha256":"45b0a28ff35bee4290a694a894e54b6088661d06e149a2ba5d1c4b99f7919038","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45b0a28ff35bee4290a694a894e54b6088661d06e149a2ba5d1c4b99f7919038","first_computed_at":"2026-07-05T07:46:43.220938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:46:43.220938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j8d1APnf8lsW9sDd/crrBNUI+UARkZ16loKhSEY9zlwagQR0otbaXF4reRYi7tMDmPAy9YxmymIzqVZzCE+FCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:46:43.221384Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.11690","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f04535b87e50448ab8a881079f483f30d202d429a0dd5ea6d0763447ec635656","sha256:6011bc808a579028d72c4db9c2a7f57141e5c4d3b6d0987ce1cfbf0ba33d5afe"],"state_sha256":"82bd253b60311b1c05e722fdc38aaca954786254fe0d6b794d2c6e96a4d71b1b"}