{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WJS2SRAK5BUORIYRQHJF7IRRM6","short_pith_number":"pith:WJS2SRAK","schema_version":"1.0","canonical_sha256":"b265a9440ae868e8a31181d25fa23167988c55b6be12a131b6ae75cbf2d697dc","source":{"kind":"arxiv","id":"2504.15485","version":2},"attestation_state":"computed","paper":{"title":"CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Atin Pothiraj, Elias Stengel-Eskin, Jaemin Cho, Mohit Bansal","submitted_at":"2025-04-21T23:38:43Z","abstract_excerpt":"Recognizing and reasoning about occluded (partially or fully hidden) objects is vital to understanding visual scenes, as occlusions frequently occur in real-world environments and act as obstacles for spatial comprehension. To test models' ability to reason about multiple occluded objects, we introduce a novel task, Counting Amodally for Patterns Through Unseen REgions (CAPTURe), which requires a model to count objects arranged in a pattern by inferring how the pattern continues behind an occluder (an object which blocks parts of the scene). CAPTURe requires both recognizing visual patterns an"},"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":"2504.15485","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-21T23:38:43Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c1aaca27853fdacc0543e18b474901db09f80053b5a21ef2b6d7ac5d13a8710a","abstract_canon_sha256":"20184c691249549afd90451e4d4e288a54a1577e5b35506975b0b9b75c29304e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:27.660960Z","signature_b64":"aL1Bu63d1UdZIL/QsSAewsh/MemxPILNgjWBNuS+g5SheOGcfENo+Gad6wtNbiGKjTXRmgB576ErygxYLFPRCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b265a9440ae868e8a31181d25fa23167988c55b6be12a131b6ae75cbf2d697dc","last_reissued_at":"2026-07-05T11:53:27.660442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:27.660442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Atin Pothiraj, Elias Stengel-Eskin, Jaemin Cho, Mohit Bansal","submitted_at":"2025-04-21T23:38:43Z","abstract_excerpt":"Recognizing and reasoning about occluded (partially or fully hidden) objects is vital to understanding visual scenes, as occlusions frequently occur in real-world environments and act as obstacles for spatial comprehension. To test models' ability to reason about multiple occluded objects, we introduce a novel task, Counting Amodally for Patterns Through Unseen REgions (CAPTURe), which requires a model to count objects arranged in a pattern by inferring how the pattern continues behind an occluder (an object which blocks parts of the scene). CAPTURe requires both recognizing visual patterns an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15485","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/2504.15485/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":"2504.15485","created_at":"2026-07-05T11:53:27.660503+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.15485v2","created_at":"2026-07-05T11:53:27.660503+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15485","created_at":"2026-07-05T11:53:27.660503+00:00"},{"alias_kind":"pith_short_12","alias_value":"WJS2SRAK5BUO","created_at":"2026-07-05T11:53:27.660503+00:00"},{"alias_kind":"pith_short_16","alias_value":"WJS2SRAK5BUORIYR","created_at":"2026-07-05T11:53:27.660503+00:00"},{"alias_kind":"pith_short_8","alias_value":"WJS2SRAK","created_at":"2026-07-05T11:53:27.660503+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23176","citing_title":"DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23176","citing_title":"DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving","ref_index":73,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WJS2SRAK5BUORIYRQHJF7IRRM6","json":"https://pith.science/pith/WJS2SRAK5BUORIYRQHJF7IRRM6.json","graph_json":"https://pith.science/api/pith-number/WJS2SRAK5BUORIYRQHJF7IRRM6/graph.json","events_json":"https://pith.science/api/pith-number/WJS2SRAK5BUORIYRQHJF7IRRM6/events.json","paper":"https://pith.science/paper/WJS2SRAK"},"agent_actions":{"view_html":"https://pith.science/pith/WJS2SRAK5BUORIYRQHJF7IRRM6","download_json":"https://pith.science/pith/WJS2SRAK5BUORIYRQHJF7IRRM6.json","view_paper":"https://pith.science/paper/WJS2SRAK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.15485&json=true","fetch_graph":"https://pith.science/api/pith-number/WJS2SRAK5BUORIYRQHJF7IRRM6/graph.json","fetch_events":"https://pith.science/api/pith-number/WJS2SRAK5BUORIYRQHJF7IRRM6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WJS2SRAK5BUORIYRQHJF7IRRM6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WJS2SRAK5BUORIYRQHJF7IRRM6/action/storage_attestation","attest_author":"https://pith.science/pith/WJS2SRAK5BUORIYRQHJF7IRRM6/action/author_attestation","sign_citation":"https://pith.science/pith/WJS2SRAK5BUORIYRQHJF7IRRM6/action/citation_signature","submit_replication":"https://pith.science/pith/WJS2SRAK5BUORIYRQHJF7IRRM6/action/replication_record"}},"created_at":"2026-07-05T11:53:27.660503+00:00","updated_at":"2026-07-05T11:53:27.660503+00:00"}