{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OD4FY62L6D63QBLRUQBMYZWOPZ","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":"a4c01c1b87f2f2d3c69c31e3d17cdf1524044ea1b4a35d4a71a257c175462dad","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-12T09:10:51Z","title_canon_sha256":"d84d8f19e92803daa1bf5984fca4d97168685e52161ad86550b23328ccf422e9"},"schema_version":"1.0","source":{"id":"2311.06783","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.06783","created_at":"2026-07-05T07:12:03Z"},{"alias_kind":"arxiv_version","alias_value":"2311.06783v1","created_at":"2026-07-05T07:12:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06783","created_at":"2026-07-05T07:12:03Z"},{"alias_kind":"pith_short_12","alias_value":"OD4FY62L6D63","created_at":"2026-07-05T07:12:03Z"},{"alias_kind":"pith_short_16","alias_value":"OD4FY62L6D63QBLR","created_at":"2026-07-05T07:12:03Z"},{"alias_kind":"pith_short_8","alias_value":"OD4FY62L","created_at":"2026-07-05T07:12:03Z"}],"graph_snapshots":[{"event_id":"sha256:022e6ae73c47a76cec7df378fb61c66b3aba7722d6568046f13a8d7f0e8da4ce","target":"graph","created_at":"2026-07-05T07:12:03Z","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/2311.06783/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modality foundation models, as represented by GPT-4V, have brought a new paradigm for low-level visual perception and understanding tasks, that can respond to a broad range of natural human instructions in a model. While existing foundation models have shown exciting potentials on low-level visual tasks, their related abilities are still preliminary and need to be improved. In order to enhance these models, we conduct a large-scale subjective experiment collecting a vast number of real human feedbacks on low-level vision. Each feedback follows a pathway that starts with a detailed descri","authors_text":"Annan Wang, Chaofeng Chen, Chunyi Li, Erli Zhang, Geng Xue, Guangtao Zhai, Haoning Wu, Jingwen Hou, Kaixin Xu, Liang Liao, Qiong Yan, Weisi Lin, Wenxiu Sun, Zicheng Zhang","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-12T09:10:51Z","title":"Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.06783","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:e2a0013d17312159f4b5b7f975af3142a25e4af135a8523ba6efd730b6c6bb0a","target":"record","created_at":"2026-07-05T07:12:03Z","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":"a4c01c1b87f2f2d3c69c31e3d17cdf1524044ea1b4a35d4a71a257c175462dad","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-12T09:10:51Z","title_canon_sha256":"d84d8f19e92803daa1bf5984fca4d97168685e52161ad86550b23328ccf422e9"},"schema_version":"1.0","source":{"id":"2311.06783","kind":"arxiv","version":1}},"canonical_sha256":"70f85c7b4bf0fdb80571a402cc66ce7e406e2bb9d0d14b28e2aea9a5e019940f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70f85c7b4bf0fdb80571a402cc66ce7e406e2bb9d0d14b28e2aea9a5e019940f","first_computed_at":"2026-07-05T07:12:03.616795Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:12:03.616795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ftZ6+rOAtapc6LQlDVUFicU+b8V6txX3VskpfI57T44+AmPhzvJ4jd4Zw9mOdfcX75CjCeUaEqr2FkLpFa0wBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:12:03.617288Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.06783","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2a0013d17312159f4b5b7f975af3142a25e4af135a8523ba6efd730b6c6bb0a","sha256:022e6ae73c47a76cec7df378fb61c66b3aba7722d6568046f13a8d7f0e8da4ce"],"state_sha256":"7efaa9ab2c5337b60f904b5f01276d53b531b051a914dd47c231aefada65c6b9"}