{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:C4SN4L753SDLBUVACKGF7RRFTO","short_pith_number":"pith:C4SN4L75","canonical_record":{"source":{"id":"2407.16772","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-23T18:10:43Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"723295c68a2c50489e45164fbca8e6a7f2b2f34d8d80426538a8642c2611c297","abstract_canon_sha256":"5065317e7b5399668dbfb0c3b709e591824683ce8cf1a08a45b162944b17675a"},"schema_version":"1.0"},"canonical_sha256":"1724de2ffddc86b0d2a0128c5fc6259b8b192d53098f6c6997eeb4b89bae251b","source":{"kind":"arxiv","id":"2407.16772","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.16772","created_at":"2026-07-05T10:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"2407.16772v2","created_at":"2026-07-05T10:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16772","created_at":"2026-07-05T10:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"C4SN4L753SDL","created_at":"2026-07-05T10:03:44Z"},{"alias_kind":"pith_short_16","alias_value":"C4SN4L753SDLBUVA","created_at":"2026-07-05T10:03:44Z"},{"alias_kind":"pith_short_8","alias_value":"C4SN4L75","created_at":"2026-07-05T10:03:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:C4SN4L753SDLBUVACKGF7RRFTO","target":"record","payload":{"canonical_record":{"source":{"id":"2407.16772","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-23T18:10:43Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"723295c68a2c50489e45164fbca8e6a7f2b2f34d8d80426538a8642c2611c297","abstract_canon_sha256":"5065317e7b5399668dbfb0c3b709e591824683ce8cf1a08a45b162944b17675a"},"schema_version":"1.0"},"canonical_sha256":"1724de2ffddc86b0d2a0128c5fc6259b8b192d53098f6c6997eeb4b89bae251b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:44.385349Z","signature_b64":"zewCyHJZniqlEJ+1yN+T1DyIsw+0Zg7YHKROREz8PpvrdsE0SpW5bI7MRVFJVtapbU3dvwrfJ/OagIB3Vy8WDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1724de2ffddc86b0d2a0128c5fc6259b8b192d53098f6c6997eeb4b89bae251b","last_reissued_at":"2026-07-05T10:03:44.384888Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:44.384888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.16772","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:03:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i4v43UB6ZxmJIVLSQHMxvGYRKvqXN4/kfp9SIODK1NE5Bmaf4ytFb/VSmylqEnNYktmePQ2rpZd19cFBynhADw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T20:21:00.112324Z"},"content_sha256":"582d8979340b38e4b9dff17c463f075da4bf5b9f758565da51a5c6ce7cc94090","schema_version":"1.0","event_id":"sha256:582d8979340b38e4b9dff17c463f075da4bf5b9f758565da51a5c6ce7cc94090"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:C4SN4L753SDLBUVACKGF7RRFTO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VisMin: Visual Minimal-Change Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aishwarya Agrawal, Le Zhang, Rabiul Awal, Saba Ahmadi","submitted_at":"2024-07-23T18:10:43Z","abstract_excerpt":"Fine-grained understanding of objects, attributes, and relationships between objects is crucial for visual-language models (VLMs). Existing benchmarks primarily focus on evaluating VLMs' capability to distinguish between two very similar captions given an image. In this paper, we introduce a new, challenging benchmark termed Visual Minimal-Change Understanding (VisMin), which requires models to predict the correct image-caption match given two images and two captions. The image pair and caption pair contain minimal changes, i.e., only one aspect changes at a time from among the following: obje"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16772","kind":"arxiv","version":2},"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/2407.16772/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":"2026-07-05T10:03:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G5179u/BjLAVTsa9ejK8OIMyKnZ6/Mw6MVja9TfxwqrCfbHHbffr06YZIf+JKJTtg3yXmdQYeX9PkM/YvkdWCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T20:21:00.112824Z"},"content_sha256":"d90db1ea903247510c1f76fe93ba67bc3aadf1a225b0b8373f34c58e5949d416","schema_version":"1.0","event_id":"sha256:d90db1ea903247510c1f76fe93ba67bc3aadf1a225b0b8373f34c58e5949d416"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C4SN4L753SDLBUVACKGF7RRFTO/bundle.json","state_url":"https://pith.science/pith/C4SN4L753SDLBUVACKGF7RRFTO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C4SN4L753SDLBUVACKGF7RRFTO/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":"2026-08-06T20:21:00Z","links":{"resolver":"https://pith.science/pith/C4SN4L753SDLBUVACKGF7RRFTO","bundle":"https://pith.science/pith/C4SN4L753SDLBUVACKGF7RRFTO/bundle.json","state":"https://pith.science/pith/C4SN4L753SDLBUVACKGF7RRFTO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C4SN4L753SDLBUVACKGF7RRFTO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:C4SN4L753SDLBUVACKGF7RRFTO","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":"5065317e7b5399668dbfb0c3b709e591824683ce8cf1a08a45b162944b17675a","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-23T18:10:43Z","title_canon_sha256":"723295c68a2c50489e45164fbca8e6a7f2b2f34d8d80426538a8642c2611c297"},"schema_version":"1.0","source":{"id":"2407.16772","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.16772","created_at":"2026-07-05T10:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"2407.16772v2","created_at":"2026-07-05T10:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16772","created_at":"2026-07-05T10:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"C4SN4L753SDL","created_at":"2026-07-05T10:03:44Z"},{"alias_kind":"pith_short_16","alias_value":"C4SN4L753SDLBUVA","created_at":"2026-07-05T10:03:44Z"},{"alias_kind":"pith_short_8","alias_value":"C4SN4L75","created_at":"2026-07-05T10:03:44Z"}],"graph_snapshots":[{"event_id":"sha256:d90db1ea903247510c1f76fe93ba67bc3aadf1a225b0b8373f34c58e5949d416","target":"graph","created_at":"2026-07-05T10:03:44Z","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/2407.16772/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-grained understanding of objects, attributes, and relationships between objects is crucial for visual-language models (VLMs). Existing benchmarks primarily focus on evaluating VLMs' capability to distinguish between two very similar captions given an image. In this paper, we introduce a new, challenging benchmark termed Visual Minimal-Change Understanding (VisMin), which requires models to predict the correct image-caption match given two images and two captions. The image pair and caption pair contain minimal changes, i.e., only one aspect changes at a time from among the following: obje","authors_text":"Aishwarya Agrawal, Le Zhang, Rabiul Awal, Saba Ahmadi","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-23T18:10:43Z","title":"VisMin: Visual Minimal-Change Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16772","kind":"arxiv","version":2},"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":"sha256:582d8979340b38e4b9dff17c463f075da4bf5b9f758565da51a5c6ce7cc94090","target":"record","created_at":"2026-07-05T10:03:44Z","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":"5065317e7b5399668dbfb0c3b709e591824683ce8cf1a08a45b162944b17675a","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-23T18:10:43Z","title_canon_sha256":"723295c68a2c50489e45164fbca8e6a7f2b2f34d8d80426538a8642c2611c297"},"schema_version":"1.0","source":{"id":"2407.16772","kind":"arxiv","version":2}},"canonical_sha256":"1724de2ffddc86b0d2a0128c5fc6259b8b192d53098f6c6997eeb4b89bae251b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1724de2ffddc86b0d2a0128c5fc6259b8b192d53098f6c6997eeb4b89bae251b","first_computed_at":"2026-07-05T10:03:44.384888Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:03:44.384888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zewCyHJZniqlEJ+1yN+T1DyIsw+0Zg7YHKROREz8PpvrdsE0SpW5bI7MRVFJVtapbU3dvwrfJ/OagIB3Vy8WDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:03:44.385349Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.16772","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:582d8979340b38e4b9dff17c463f075da4bf5b9f758565da51a5c6ce7cc94090","sha256:d90db1ea903247510c1f76fe93ba67bc3aadf1a225b0b8373f34c58e5949d416"],"state_sha256":"8086cf8cba30e3113005f215bea6555baa40738bae07aaa3ebddcc0309da3827"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xhQQFCgyOEYgMD2iQW4Ib6w23eRVylATwfI08fi+nbbJLoE0tizYbKr8STnCH3ZYkcEajvHZUUHuAy7cPckiAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T20:21:00.118120Z","bundle_sha256":"372a6e1abf3b01461d1eb0d4cc89693438595b2ce9896f513aac0f0674844966"}}