{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3GHMKW5Z4G4IRP6P25B57PYHVN","short_pith_number":"pith:3GHMKW5Z","canonical_record":{"source":{"id":"2607.16094","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-17T16:25:03Z","cross_cats_sorted":[],"title_canon_sha256":"402f8b281bc5935f002736ba6543dceff51112c0edecc3812012ed4d070428ef","abstract_canon_sha256":"511788c7572660791565c4a1ae475546f6f30bb4482dea079ab8db16bcd4eede"},"schema_version":"1.0"},"canonical_sha256":"d98ec55bb9e1b888bfcfd743dfbf07ab45bf6d87453bd4d9eb99bd1ed576ed2b","source":{"kind":"arxiv","id":"2607.16094","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.16094","created_at":"2026-07-20T02:19:30Z"},{"alias_kind":"arxiv_version","alias_value":"2607.16094v1","created_at":"2026-07-20T02:19:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16094","created_at":"2026-07-20T02:19:30Z"},{"alias_kind":"pith_short_12","alias_value":"3GHMKW5Z4G4I","created_at":"2026-07-20T02:19:30Z"},{"alias_kind":"pith_short_16","alias_value":"3GHMKW5Z4G4IRP6P","created_at":"2026-07-20T02:19:30Z"},{"alias_kind":"pith_short_8","alias_value":"3GHMKW5Z","created_at":"2026-07-20T02:19:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3GHMKW5Z4G4IRP6P25B57PYHVN","target":"record","payload":{"canonical_record":{"source":{"id":"2607.16094","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-17T16:25:03Z","cross_cats_sorted":[],"title_canon_sha256":"402f8b281bc5935f002736ba6543dceff51112c0edecc3812012ed4d070428ef","abstract_canon_sha256":"511788c7572660791565c4a1ae475546f6f30bb4482dea079ab8db16bcd4eede"},"schema_version":"1.0"},"canonical_sha256":"d98ec55bb9e1b888bfcfd743dfbf07ab45bf6d87453bd4d9eb99bd1ed576ed2b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-20T02:19:30.555593Z","signature_b64":"CbkgbIBApp41o+kS3lYwb5cbfVXBtfrmS0SofS6Mmv1MFYYwCFLQLgrCZm7htmnuKFYJNcZVMErbcylr2flECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d98ec55bb9e1b888bfcfd743dfbf07ab45bf6d87453bd4d9eb99bd1ed576ed2b","last_reissued_at":"2026-07-20T02:19:30.554760Z","signature_status":"signed_v1","first_computed_at":"2026-07-20T02:19:30.554760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.16094","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":"2026-07-20T02:19:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9GtK4+lL+DDjLk0AwHJj3/GCLJrhr+qTGJWfLoxixkoyPCh3WelIfhaNrQxP29yn6TQa7QWF9TO88tcpKFbQCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T13:00:32.262916Z"},"content_sha256":"f3a5cd997dfc68fb51a7097e691d744a15f31a1b95c429c41003ce3a3a314cfe","schema_version":"1.0","event_id":"sha256:f3a5cd997dfc68fb51a7097e691d744a15f31a1b95c429c41003ce3a3a314cfe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3GHMKW5Z4G4IRP6P25B57PYHVN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How Do VLMs Fail? Vision-Operation Misalignment in Compositional VQA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Avinash Anand, Bingjie Xu, Navya Gupta, Timothy Liu, Zhengchen Zhang","submitted_at":"2026-07-17T16:25:03Z","abstract_excerpt":"Compositional visual question answering requires Vision-Language Models (VLMs) to execute multiple reasoning operations like object selection, spatial relation resolution, and attribute verification. Despite strong aggregate performance, the mechanistic basis of VLM failures on this task remains underexplored. To address this gap, we analyze vision-operation misalignment in VLMs by examining how failures relate to specific reasoning operations and the internal computational pathways through which they arise and propagate. We introduce an Operation-centric mechanistic framework that decomposes "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16094","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/2607.16094/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":"2026-07-20T02:19:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YAkAMFinaFTC0rWjyCKPBr6DCIjB2UBacwRGL6MRN+6j5ETi0hBMRWLYAYuNFptZbkU02P9IC2899eGPNSbyCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T13:00:32.263673Z"},"content_sha256":"12fb660184a7530ebde74e157246d2ca8f94db259eb0331992f16f0b223633d7","schema_version":"1.0","event_id":"sha256:12fb660184a7530ebde74e157246d2ca8f94db259eb0331992f16f0b223633d7"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:3GHMKW5Z4G4IRP6P25B57PYHVN","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.18653/v1/D18-1437) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Anna Rohrbach, Lisa Anne Hendricks, Kaylee Burns, Trevor Darrell, and Kate Saenko. 2018. Object Hallucination in Image Captioning. InProceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Ellen Riloff, David","arxiv_id":"2607.16094","detector":"doi_compliance","evidence":{"ref_index":27,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.18653/v1/d18-","reconstructed_doi":"10.18653/v1/D18-1437"},"severity":"advisory","ref_index":27,"audited_at":"2026-08-01T21:30:12.778819Z","event_type":"pith.integrity.v1","detected_doi":"10.18653/v1/D18-1437","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"a46f88dee6aa05ec37c90eddede572859ae9c3654e593844fc33a3fda4079b23","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":16662,"payload_sha256":"99b008986599e5b0d09b0936da8b6fe4395226bb99c8d26e61b7ad960fa73cb9","signature_b64":"Pj6h9TrhA/1Qgn3/vlVWqktp2JbkeTBgqjmKAQzTAYXhNm1hihOCF29yvXvN0Feg8ej+ZYoH1/kmQmHEuZJiBA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-01T21:33:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UsTf34azv8ujUFwd+fdjSyo+Q2E1TJ+qCiLZAFWqG1HXI1DBLzrthD5SKKMBmABe/0PbOo2pAd/L0FbatKiqCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T13:00:32.269070Z"},"content_sha256":"c0b1798fd3fe285ea96eeda7adb0fdb344039d6f0e252e843f637d23b94214dd","schema_version":"1.0","event_id":"sha256:c0b1798fd3fe285ea96eeda7adb0fdb344039d6f0e252e843f637d23b94214dd"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:3GHMKW5Z4G4IRP6P25B57PYHVN","target":"integrity","payload":{"note":"DOI is split by whitespace or line breaks in the printed bibliography. Reconstructed DOI 10.1162/coli_a_00422 resolves to 'Probing Classifiers: Promises, Shortcomings, and Advances'. A reader following the printed text alone cannot reach it.","snippet":"Yonatan Belinkov. 2022. Probing Classifiers: Promises, Shortcomings, and Ad- vances.Computational Linguistics48, 1 (March 2022), 207–219. doi:10.1162/coli_ a_00422","arxiv_id":"2607.16094","detector":"doi_compliance","evidence":{"ref_index":5,"verdict_class":"incontrovertible","resolved_title":"Probing Classifiers: Promises, Shortcomings, and Advances","printed_excerpt":"10.1162/coli_","reconstructed_doi":"10.1162/coli_a_00422"},"severity":"advisory","ref_index":5,"audited_at":"2026-08-01T21:30:12.778819Z","event_type":"pith.integrity.v1","detected_doi":"10.1162/coli_a_00422","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"4d36d1f7963b4faf6bce30c8c062666e6c9a168f6fe666ff63e9a8ead61c0e58","paper_version":1,"verdict_class":"incontrovertible","resolved_title":"Probing Classifiers: Promises, Shortcomings, and Advances","detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":16661,"payload_sha256":"047e099f2ad169028b60748502591ff3471325c3822b3e3d8d2940208a87735f","signature_b64":"IKcz7lx6LjxW2ZRIzvlraQGe/zR0XkvpB669n6KVoragGc4SYwKplMe6wF0quwEQ3FzmnCws/bdP2/SsEOfvBw==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-01T21:33:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W9lxmxl/QvugfUXLmzAVYcoDAbk+OHBFUEmjSrbTffUyv7FMkn3I4b3Sj9USEi5jdk05on4YlV21eOMP1TxfCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T13:00:32.269846Z"},"content_sha256":"d52b90a6bf9ecfdc47c2aa5a85d0ea918252ebd1efd2134e519447b5c779c6ed","schema_version":"1.0","event_id":"sha256:d52b90a6bf9ecfdc47c2aa5a85d0ea918252ebd1efd2134e519447b5c779c6ed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3GHMKW5Z4G4IRP6P25B57PYHVN/bundle.json","state_url":"https://pith.science/pith/3GHMKW5Z4G4IRP6P25B57PYHVN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3GHMKW5Z4G4IRP6P25B57PYHVN/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":"2026-08-10T13:00:32Z","links":{"resolver":"https://pith.science/pith/3GHMKW5Z4G4IRP6P25B57PYHVN","bundle":"https://pith.science/pith/3GHMKW5Z4G4IRP6P25B57PYHVN/bundle.json","state":"https://pith.science/pith/3GHMKW5Z4G4IRP6P25B57PYHVN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3GHMKW5Z4G4IRP6P25B57PYHVN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3GHMKW5Z4G4IRP6P25B57PYHVN","merge_version":"pith-open-graph-merge-v1","event_count":4,"valid_event_count":4,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"511788c7572660791565c4a1ae475546f6f30bb4482dea079ab8db16bcd4eede","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-17T16:25:03Z","title_canon_sha256":"402f8b281bc5935f002736ba6543dceff51112c0edecc3812012ed4d070428ef"},"schema_version":"1.0","source":{"id":"2607.16094","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.16094","created_at":"2026-07-20T02:19:30Z"},{"alias_kind":"arxiv_version","alias_value":"2607.16094v1","created_at":"2026-07-20T02:19:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16094","created_at":"2026-07-20T02:19:30Z"},{"alias_kind":"pith_short_12","alias_value":"3GHMKW5Z4G4I","created_at":"2026-07-20T02:19:30Z"},{"alias_kind":"pith_short_16","alias_value":"3GHMKW5Z4G4IRP6P","created_at":"2026-07-20T02:19:30Z"},{"alias_kind":"pith_short_8","alias_value":"3GHMKW5Z","created_at":"2026-07-20T02:19:30Z"}],"graph_snapshots":[{"event_id":"sha256:12fb660184a7530ebde74e157246d2ca8f94db259eb0331992f16f0b223633d7","target":"graph","created_at":"2026-07-20T02:19:30Z","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/2607.16094/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Compositional visual question answering requires Vision-Language Models (VLMs) to execute multiple reasoning operations like object selection, spatial relation resolution, and attribute verification. Despite strong aggregate performance, the mechanistic basis of VLM failures on this task remains underexplored. To address this gap, we analyze vision-operation misalignment in VLMs by examining how failures relate to specific reasoning operations and the internal computational pathways through which they arise and propagate. We introduce an Operation-centric mechanistic framework that decomposes ","authors_text":"Avinash Anand, Bingjie Xu, Navya Gupta, Timothy Liu, Zhengchen Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-17T16:25:03Z","title":"How Do VLMs Fail? Vision-Operation Misalignment in Compositional VQA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16094","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:f3a5cd997dfc68fb51a7097e691d744a15f31a1b95c429c41003ce3a3a314cfe","target":"record","created_at":"2026-07-20T02:19:30Z","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":"511788c7572660791565c4a1ae475546f6f30bb4482dea079ab8db16bcd4eede","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-17T16:25:03Z","title_canon_sha256":"402f8b281bc5935f002736ba6543dceff51112c0edecc3812012ed4d070428ef"},"schema_version":"1.0","source":{"id":"2607.16094","kind":"arxiv","version":1}},"canonical_sha256":"d98ec55bb9e1b888bfcfd743dfbf07ab45bf6d87453bd4d9eb99bd1ed576ed2b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d98ec55bb9e1b888bfcfd743dfbf07ab45bf6d87453bd4d9eb99bd1ed576ed2b","first_computed_at":"2026-07-20T02:19:30.554760Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-20T02:19:30.554760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CbkgbIBApp41o+kS3lYwb5cbfVXBtfrmS0SofS6Mmv1MFYYwCFLQLgrCZm7htmnuKFYJNcZVMErbcylr2flECg==","signature_status":"signed_v1","signed_at":"2026-07-20T02:19:30.555593Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.16094","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:c0b1798fd3fe285ea96eeda7adb0fdb344039d6f0e252e843f637d23b94214dd","sha256:d52b90a6bf9ecfdc47c2aa5a85d0ea918252ebd1efd2134e519447b5c779c6ed"]}],"invalid_events":[],"applied_event_ids":["sha256:f3a5cd997dfc68fb51a7097e691d744a15f31a1b95c429c41003ce3a3a314cfe","sha256:12fb660184a7530ebde74e157246d2ca8f94db259eb0331992f16f0b223633d7"],"state_sha256":"85d6c1a36dbe998e4a2185cfdbd32c90dea18fac565ed20f63875271fc2491ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0MegTOnF6n+kSzfLflcTD/YJNLxrATdV2EdxdKotDYMDVGCdqA8HwaZoxrRCDeJtjdk2PBw3SDv7r+fU26msBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T13:00:32.273053Z","bundle_sha256":"04b3677b2fd16e9a6a74f9be31c48158153ea628f0073e827e728b5a16dbb6bb"}}