{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:66L4HAMM555HACGWGSELLRLSHT","short_pith_number":"pith:66L4HAMM","schema_version":"1.0","canonical_sha256":"f797c3818cef7a7008d63488b5c5723cef1976a65168ff32eb0dbe08be13a172","source":{"kind":"arxiv","id":"2501.13620","version":5},"attestation_state":"computed","paper":{"title":"A Cognitive Paradigm Approach to Probe the Perception-Reasoning Interface in VLMs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Mohit Vaishnav, Tanel Tammet","submitted_at":"2025-01-23T12:42:42Z","abstract_excerpt":"A fundamental challenge in artificial intelligence involves understanding the cognitive mechanisms underlying visual reasoning in sophisticated models like Vision-Language Models (VLMs). How do these models integrate visual perception with abstract thought, especially when reasoning across multiple images or requiring fine-grained compositional understanding? Drawing inspiration from cognitive science, this paper introduces a structured evaluation framework using diverse visual reasoning tasks-Bongard Problems (BPs) and Winoground-to dissect the perception-reasoning interface in VLMs. We propo"},"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":"2501.13620","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-23T12:42:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a95cf10f2a0c1378e7fb42d4456b7011784e199b57170ce1f6690e1221d10e47","abstract_canon_sha256":"e1ec713cf29106f9fe554703f914e868b6d80e1b78ca7df0caa7e6dec85cae05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:05.026101Z","signature_b64":"tlYoJ5ROJjshqDxg8fnhQgEHZB8ylvPTf6q7YSo5VNXJB7ClP8a4SWt7a8MxeNRIDGiUy9CiR0zVwOu9u92BBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f797c3818cef7a7008d63488b5c5723cef1976a65168ff32eb0dbe08be13a172","last_reissued_at":"2026-07-05T10:59:05.025538Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:05.025538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Cognitive Paradigm Approach to Probe the Perception-Reasoning Interface in VLMs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Mohit Vaishnav, Tanel Tammet","submitted_at":"2025-01-23T12:42:42Z","abstract_excerpt":"A fundamental challenge in artificial intelligence involves understanding the cognitive mechanisms underlying visual reasoning in sophisticated models like Vision-Language Models (VLMs). How do these models integrate visual perception with abstract thought, especially when reasoning across multiple images or requiring fine-grained compositional understanding? Drawing inspiration from cognitive science, this paper introduces a structured evaluation framework using diverse visual reasoning tasks-Bongard Problems (BPs) and Winoground-to dissect the perception-reasoning interface in VLMs. We propo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13620","kind":"arxiv","version":5},"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/2501.13620/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":"2501.13620","created_at":"2026-07-05T10:59:05.025598+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.13620v5","created_at":"2026-07-05T10:59:05.025598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13620","created_at":"2026-07-05T10:59:05.025598+00:00"},{"alias_kind":"pith_short_12","alias_value":"66L4HAMM555H","created_at":"2026-07-05T10:59:05.025598+00:00"},{"alias_kind":"pith_short_16","alias_value":"66L4HAMM555HACGW","created_at":"2026-07-05T10:59:05.025598+00:00"},{"alias_kind":"pith_short_8","alias_value":"66L4HAMM","created_at":"2026-07-05T10:59:05.025598+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.07632","citing_title":"Test-Time Matching: Unlocking Compositional Reasoning in Multimodal Models","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/66L4HAMM555HACGWGSELLRLSHT","json":"https://pith.science/pith/66L4HAMM555HACGWGSELLRLSHT.json","graph_json":"https://pith.science/api/pith-number/66L4HAMM555HACGWGSELLRLSHT/graph.json","events_json":"https://pith.science/api/pith-number/66L4HAMM555HACGWGSELLRLSHT/events.json","paper":"https://pith.science/paper/66L4HAMM"},"agent_actions":{"view_html":"https://pith.science/pith/66L4HAMM555HACGWGSELLRLSHT","download_json":"https://pith.science/pith/66L4HAMM555HACGWGSELLRLSHT.json","view_paper":"https://pith.science/paper/66L4HAMM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.13620&json=true","fetch_graph":"https://pith.science/api/pith-number/66L4HAMM555HACGWGSELLRLSHT/graph.json","fetch_events":"https://pith.science/api/pith-number/66L4HAMM555HACGWGSELLRLSHT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/66L4HAMM555HACGWGSELLRLSHT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/66L4HAMM555HACGWGSELLRLSHT/action/storage_attestation","attest_author":"https://pith.science/pith/66L4HAMM555HACGWGSELLRLSHT/action/author_attestation","sign_citation":"https://pith.science/pith/66L4HAMM555HACGWGSELLRLSHT/action/citation_signature","submit_replication":"https://pith.science/pith/66L4HAMM555HACGWGSELLRLSHT/action/replication_record"}},"created_at":"2026-07-05T10:59:05.025598+00:00","updated_at":"2026-07-05T10:59:05.025598+00:00"}