{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:C4SN4L753SDLBUVACKGF7RRFTO","short_pith_number":"pith:C4SN4L75","schema_version":"1.0","canonical_sha256":"1724de2ffddc86b0d2a0128c5fc6259b8b192d53098f6c6997eeb4b89bae251b","source":{"kind":"arxiv","id":"2407.16772","version":2},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2407.16772","created_at":"2026-07-05T10:03:44.384953+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.16772v2","created_at":"2026-07-05T10:03:44.384953+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16772","created_at":"2026-07-05T10:03:44.384953+00:00"},{"alias_kind":"pith_short_12","alias_value":"C4SN4L753SDL","created_at":"2026-07-05T10:03:44.384953+00:00"},{"alias_kind":"pith_short_16","alias_value":"C4SN4L753SDLBUVA","created_at":"2026-07-05T10:03:44.384953+00:00"},{"alias_kind":"pith_short_8","alias_value":"C4SN4L75","created_at":"2026-07-05T10:03:44.384953+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28615","citing_title":"Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimization","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C4SN4L753SDLBUVACKGF7RRFTO","json":"https://pith.science/pith/C4SN4L753SDLBUVACKGF7RRFTO.json","graph_json":"https://pith.science/api/pith-number/C4SN4L753SDLBUVACKGF7RRFTO/graph.json","events_json":"https://pith.science/api/pith-number/C4SN4L753SDLBUVACKGF7RRFTO/events.json","paper":"https://pith.science/paper/C4SN4L75"},"agent_actions":{"view_html":"https://pith.science/pith/C4SN4L753SDLBUVACKGF7RRFTO","download_json":"https://pith.science/pith/C4SN4L753SDLBUVACKGF7RRFTO.json","view_paper":"https://pith.science/paper/C4SN4L75","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.16772&json=true","fetch_graph":"https://pith.science/api/pith-number/C4SN4L753SDLBUVACKGF7RRFTO/graph.json","fetch_events":"https://pith.science/api/pith-number/C4SN4L753SDLBUVACKGF7RRFTO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C4SN4L753SDLBUVACKGF7RRFTO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C4SN4L753SDLBUVACKGF7RRFTO/action/storage_attestation","attest_author":"https://pith.science/pith/C4SN4L753SDLBUVACKGF7RRFTO/action/author_attestation","sign_citation":"https://pith.science/pith/C4SN4L753SDLBUVACKGF7RRFTO/action/citation_signature","submit_replication":"https://pith.science/pith/C4SN4L753SDLBUVACKGF7RRFTO/action/replication_record"}},"created_at":"2026-07-05T10:03:44.384953+00:00","updated_at":"2026-07-05T10:03:44.384953+00:00"}