{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VVNQO6VNWWMABNTHI7EK3HSKGA","short_pith_number":"pith:VVNQO6VN","canonical_record":{"source":{"id":"2607.26769","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-29T11:10:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5f118899a8873f35681539dc1ada07c28ca6c1abeb2823b0764ccd1eb063f0b8","abstract_canon_sha256":"6762138af9902b8d99e64570b05dfc24d3aaabad77e1873ba4a912c88a414e46"},"schema_version":"1.0"},"canonical_sha256":"ad5b077aadb59800b66747c8ad9e4a3011663ccfc8dc40e662d40d843f8eb9c4","source":{"kind":"arxiv","id":"2607.26769","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26769","created_at":"2026-07-30T01:22:15Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26769v1","created_at":"2026-07-30T01:22:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26769","created_at":"2026-07-30T01:22:15Z"},{"alias_kind":"pith_short_12","alias_value":"VVNQO6VNWWMA","created_at":"2026-07-30T01:22:15Z"},{"alias_kind":"pith_short_16","alias_value":"VVNQO6VNWWMABNTH","created_at":"2026-07-30T01:22:15Z"},{"alias_kind":"pith_short_8","alias_value":"VVNQO6VN","created_at":"2026-07-30T01:22:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VVNQO6VNWWMABNTHI7EK3HSKGA","target":"record","payload":{"canonical_record":{"source":{"id":"2607.26769","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-29T11:10:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5f118899a8873f35681539dc1ada07c28ca6c1abeb2823b0764ccd1eb063f0b8","abstract_canon_sha256":"6762138af9902b8d99e64570b05dfc24d3aaabad77e1873ba4a912c88a414e46"},"schema_version":"1.0"},"canonical_sha256":"ad5b077aadb59800b66747c8ad9e4a3011663ccfc8dc40e662d40d843f8eb9c4","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad5b077aadb59800b66747c8ad9e4a3011663ccfc8dc40e662d40d843f8eb9c4","last_reissued_at":"2026-07-30T01:22:15.289373Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:22:15.289373Z"},"source_kind":"arxiv","source_id":"2607.26769","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-30T01:22:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bbjbaXHljJWHLcEbd1madlbZd2XXbRsulupPOj47E9I4khVPkS8pa/VWw7IJEROzi0r4fK7wwxqpwo9ATz2hBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:43:01.809456Z"},"content_sha256":"ef60806f5836b73072e7d9b267ca82a3fd94650e440069448149203efa755241","schema_version":"1.0","event_id":"sha256:ef60806f5836b73072e7d9b267ca82a3fd94650e440069448149203efa755241"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VVNQO6VNWWMABNTHI7EK3HSKGA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"See2Think: Do Multimodal Models Really Use Intermediate Visual States?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alex Jinpeng Wang, Chenhao Ji, Haiying Xu, Haoze Liu, Jingyu Chen, Panhao Zhou, Shuo Cao, Siyu Yan, Siyu Zhang, Xiwen Gu, Yihao Liu, Yongheng Zhang, Zhuoran Yan","submitted_at":"2026-07-29T11:10:34Z","abstract_excerpt":"Multimodal large language models increasingly use sketches, annotations, tools, and intermediate images during reasoning, but it remains unclear whether they truly rely on these visual states. Existing benchmarks are limited both by task collections with narrow coverage or partially text-solvable samples and by evaluations that emphasize final answers without diagnosing how intermediate visual states are generated, rendered, and used. We introduce See2Think, a unified evaluation framework comprising See2ThinkBench and Visual Action-of-Thought (VAoT). See2ThinkBench contains 1,200 open-ended, v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26769","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.26769/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-30T01:22:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/GPEc2Paj2Jy87MEzK8YisWEOEmJswOYJAs09FfF1XRFoNcA3GUaQv+jxrK6Sauy3ANXpGeDo/jEis8ksWuKAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:43:01.809954Z"},"content_sha256":"1f9529ad117aaf3a8095d1d056a4c7eb1d3fc08b76e83509e395abc5d7ce9f66","schema_version":"1.0","event_id":"sha256:1f9529ad117aaf3a8095d1d056a4c7eb1d3fc08b76e83509e395abc5d7ce9f66"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VVNQO6VNWWMABNTHI7EK3HSKGA/bundle.json","state_url":"https://pith.science/pith/VVNQO6VNWWMABNTHI7EK3HSKGA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VVNQO6VNWWMABNTHI7EK3HSKGA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T19:43:01Z","links":{"resolver":"https://pith.science/pith/VVNQO6VNWWMABNTHI7EK3HSKGA","bundle":"https://pith.science/pith/VVNQO6VNWWMABNTHI7EK3HSKGA/bundle.json","state":"https://pith.science/pith/VVNQO6VNWWMABNTHI7EK3HSKGA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VVNQO6VNWWMABNTHI7EK3HSKGA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VVNQO6VNWWMABNTHI7EK3HSKGA","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":"6762138af9902b8d99e64570b05dfc24d3aaabad77e1873ba4a912c88a414e46","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-29T11:10:34Z","title_canon_sha256":"5f118899a8873f35681539dc1ada07c28ca6c1abeb2823b0764ccd1eb063f0b8"},"schema_version":"1.0","source":{"id":"2607.26769","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26769","created_at":"2026-07-30T01:22:15Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26769v1","created_at":"2026-07-30T01:22:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26769","created_at":"2026-07-30T01:22:15Z"},{"alias_kind":"pith_short_12","alias_value":"VVNQO6VNWWMA","created_at":"2026-07-30T01:22:15Z"},{"alias_kind":"pith_short_16","alias_value":"VVNQO6VNWWMABNTH","created_at":"2026-07-30T01:22:15Z"},{"alias_kind":"pith_short_8","alias_value":"VVNQO6VN","created_at":"2026-07-30T01:22:15Z"}],"graph_snapshots":[{"event_id":"sha256:1f9529ad117aaf3a8095d1d056a4c7eb1d3fc08b76e83509e395abc5d7ce9f66","target":"graph","created_at":"2026-07-30T01:22:15Z","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/2607.26769/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models increasingly use sketches, annotations, tools, and intermediate images during reasoning, but it remains unclear whether they truly rely on these visual states. Existing benchmarks are limited both by task collections with narrow coverage or partially text-solvable samples and by evaluations that emphasize final answers without diagnosing how intermediate visual states are generated, rendered, and used. We introduce See2Think, a unified evaluation framework comprising See2ThinkBench and Visual Action-of-Thought (VAoT). See2ThinkBench contains 1,200 open-ended, v","authors_text":"Alex Jinpeng Wang, Chenhao Ji, Haiying Xu, Haoze Liu, Jingyu Chen, Panhao Zhou, Shuo Cao, Siyu Yan, Siyu Zhang, Xiwen Gu, Yihao Liu, Yongheng Zhang, Zhuoran Yan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-29T11:10:34Z","title":"See2Think: Do Multimodal Models Really Use Intermediate Visual States?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26769","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:ef60806f5836b73072e7d9b267ca82a3fd94650e440069448149203efa755241","target":"record","created_at":"2026-07-30T01:22:15Z","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":"6762138af9902b8d99e64570b05dfc24d3aaabad77e1873ba4a912c88a414e46","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-29T11:10:34Z","title_canon_sha256":"5f118899a8873f35681539dc1ada07c28ca6c1abeb2823b0764ccd1eb063f0b8"},"schema_version":"1.0","source":{"id":"2607.26769","kind":"arxiv","version":1}},"canonical_sha256":"ad5b077aadb59800b66747c8ad9e4a3011663ccfc8dc40e662d40d843f8eb9c4","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad5b077aadb59800b66747c8ad9e4a3011663ccfc8dc40e662d40d843f8eb9c4","first_computed_at":"2026-07-30T01:22:15.289373Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:22:15.289373Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.26769","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef60806f5836b73072e7d9b267ca82a3fd94650e440069448149203efa755241","sha256:1f9529ad117aaf3a8095d1d056a4c7eb1d3fc08b76e83509e395abc5d7ce9f66"],"state_sha256":"3abdef4b9c5c182d2c07404ff20ee0e2872767319ecf5a02bb85d223863f05ca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z8Y63cxfZWProhOMOKER6cSrTW4ztITvwjifvWcuwDLeRBBBZeEnxicvaHSO7pJtp8i5NxPRXBTXhJwdUvqIBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:43:01.814810Z","bundle_sha256":"78c11d0ca1bb79f89cb26b663b3bc4d9f09c0ccac9da6e413b9f6a47e0acfc6d"}}