{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KS2KBB76YPUTI6DBIDUGI54AGL","short_pith_number":"pith:KS2KBB76","canonical_record":{"source":{"id":"2410.22029","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T13:20:50Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"cf42df2a7c2605440b49c735276388febfecce0a4fea9686692fb0c3e74468eb","abstract_canon_sha256":"9dbc068bbfba997fa20138a886edd9736848ba52161bff7393b203ff171e7107"},"schema_version":"1.0"},"canonical_sha256":"54b4a087fec3e934786140e864778032c762eb1eee97e15bd31a4b201f1abcdb","source":{"kind":"arxiv","id":"2410.22029","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.22029","created_at":"2026-07-05T09:28:03Z"},{"alias_kind":"arxiv_version","alias_value":"2410.22029v1","created_at":"2026-07-05T09:28:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22029","created_at":"2026-07-05T09:28:03Z"},{"alias_kind":"pith_short_12","alias_value":"KS2KBB76YPUT","created_at":"2026-07-05T09:28:03Z"},{"alias_kind":"pith_short_16","alias_value":"KS2KBB76YPUTI6DB","created_at":"2026-07-05T09:28:03Z"},{"alias_kind":"pith_short_8","alias_value":"KS2KBB76","created_at":"2026-07-05T09:28:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KS2KBB76YPUTI6DBIDUGI54AGL","target":"record","payload":{"canonical_record":{"source":{"id":"2410.22029","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T13:20:50Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"cf42df2a7c2605440b49c735276388febfecce0a4fea9686692fb0c3e74468eb","abstract_canon_sha256":"9dbc068bbfba997fa20138a886edd9736848ba52161bff7393b203ff171e7107"},"schema_version":"1.0"},"canonical_sha256":"54b4a087fec3e934786140e864778032c762eb1eee97e15bd31a4b201f1abcdb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:03.160187Z","signature_b64":"7D3ffwheBMNWvH1FJOXQozLyUohuJJ12JUUyWBXRKMbxRBo1Xzey4782GENZLDeGW2kPFet5VwNd8lz2IZ0IBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54b4a087fec3e934786140e864778032c762eb1eee97e15bd31a4b201f1abcdb","last_reissued_at":"2026-07-05T09:28:03.159721Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:03.159721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.22029","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":"2026-07-05T09:28:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6+4iDRXQV3OcqfJQiXcmC5QYKLQuibzromh0hiZOT23KaBLiywks5+B5aO5Ghe1FcTH7CcZNxSAVQhJaqZ1jCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:07:28.619452Z"},"content_sha256":"74c8a9f9f3b2f95ac0c546728b356029420cb329ef580d0d406e267bfc9ab785","schema_version":"1.0","event_id":"sha256:74c8a9f9f3b2f95ac0c546728b356029420cb329ef580d0d406e267bfc9ab785"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KS2KBB76YPUTI6DBIDUGI54AGL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Are VLMs Really Blind","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Ayush Singh, Mansi Gupta, Shivank Garg","submitted_at":"2024-10-29T13:20:50Z","abstract_excerpt":"Vision Language Models excel in handling a wide range of complex tasks, including Optical Character Recognition (OCR), Visual Question Answering (VQA), and advanced geometric reasoning. However, these models fail to perform well on low-level basic visual tasks which are especially easy for humans. Our goal in this work was to determine if these models are truly \"blind\" to geometric reasoning or if there are ways to enhance their capabilities in this area. Our work presents a novel automatic pipeline designed to extract key information from images in response to specific questions. Instead of j"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22029","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/2410.22029/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":"2026-07-05T09:28:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BDOT5hI7HiX1YbVfuBMTCxpUKWHSUV0uI9dj4Y4azj+36u/eZtgT7Ml7115F+mjOLG74TnTihFF4uJumAhLNBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:07:28.620230Z"},"content_sha256":"ac7e13ddaad6762b110aaa1df77ac2419f9ce2b5170b802b3979bef2c5c72413","schema_version":"1.0","event_id":"sha256:ac7e13ddaad6762b110aaa1df77ac2419f9ce2b5170b802b3979bef2c5c72413"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KS2KBB76YPUTI6DBIDUGI54AGL/bundle.json","state_url":"https://pith.science/pith/KS2KBB76YPUTI6DBIDUGI54AGL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KS2KBB76YPUTI6DBIDUGI54AGL/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":"2026-08-07T18:07:28Z","links":{"resolver":"https://pith.science/pith/KS2KBB76YPUTI6DBIDUGI54AGL","bundle":"https://pith.science/pith/KS2KBB76YPUTI6DBIDUGI54AGL/bundle.json","state":"https://pith.science/pith/KS2KBB76YPUTI6DBIDUGI54AGL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KS2KBB76YPUTI6DBIDUGI54AGL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KS2KBB76YPUTI6DBIDUGI54AGL","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":"9dbc068bbfba997fa20138a886edd9736848ba52161bff7393b203ff171e7107","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T13:20:50Z","title_canon_sha256":"cf42df2a7c2605440b49c735276388febfecce0a4fea9686692fb0c3e74468eb"},"schema_version":"1.0","source":{"id":"2410.22029","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.22029","created_at":"2026-07-05T09:28:03Z"},{"alias_kind":"arxiv_version","alias_value":"2410.22029v1","created_at":"2026-07-05T09:28:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22029","created_at":"2026-07-05T09:28:03Z"},{"alias_kind":"pith_short_12","alias_value":"KS2KBB76YPUT","created_at":"2026-07-05T09:28:03Z"},{"alias_kind":"pith_short_16","alias_value":"KS2KBB76YPUTI6DB","created_at":"2026-07-05T09:28:03Z"},{"alias_kind":"pith_short_8","alias_value":"KS2KBB76","created_at":"2026-07-05T09:28:03Z"}],"graph_snapshots":[{"event_id":"sha256:ac7e13ddaad6762b110aaa1df77ac2419f9ce2b5170b802b3979bef2c5c72413","target":"graph","created_at":"2026-07-05T09:28:03Z","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/2410.22029/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Language Models excel in handling a wide range of complex tasks, including Optical Character Recognition (OCR), Visual Question Answering (VQA), and advanced geometric reasoning. However, these models fail to perform well on low-level basic visual tasks which are especially easy for humans. Our goal in this work was to determine if these models are truly \"blind\" to geometric reasoning or if there are ways to enhance their capabilities in this area. Our work presents a novel automatic pipeline designed to extract key information from images in response to specific questions. Instead of j","authors_text":"Ayush Singh, Mansi Gupta, Shivank Garg","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T13:20:50Z","title":"Are VLMs Really Blind"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22029","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":"sha256:74c8a9f9f3b2f95ac0c546728b356029420cb329ef580d0d406e267bfc9ab785","target":"record","created_at":"2026-07-05T09:28:03Z","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":"9dbc068bbfba997fa20138a886edd9736848ba52161bff7393b203ff171e7107","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T13:20:50Z","title_canon_sha256":"cf42df2a7c2605440b49c735276388febfecce0a4fea9686692fb0c3e74468eb"},"schema_version":"1.0","source":{"id":"2410.22029","kind":"arxiv","version":1}},"canonical_sha256":"54b4a087fec3e934786140e864778032c762eb1eee97e15bd31a4b201f1abcdb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54b4a087fec3e934786140e864778032c762eb1eee97e15bd31a4b201f1abcdb","first_computed_at":"2026-07-05T09:28:03.159721Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:03.159721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7D3ffwheBMNWvH1FJOXQozLyUohuJJ12JUUyWBXRKMbxRBo1Xzey4782GENZLDeGW2kPFet5VwNd8lz2IZ0IBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:03.160187Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.22029","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74c8a9f9f3b2f95ac0c546728b356029420cb329ef580d0d406e267bfc9ab785","sha256:ac7e13ddaad6762b110aaa1df77ac2419f9ce2b5170b802b3979bef2c5c72413"],"state_sha256":"850b43fa4b86bf197edb372c31818e476a41f61e19be713bef5d55863f599b66"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qybTgck8QqgARBMbRPS/Tnu5WQGVndA82VLzoZqTBMew53OsTCaaFJi2plYNX8ktf3tXxb7VlWNbYteoGjJPCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:07:28.628505Z","bundle_sha256":"061d4fb00ea293179f6d56f62d470539fd870dd1ec526f37265b4c9d2086a77d"}}