{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PO5E5JHDNLRF5RF5SXQL3TLW2E","short_pith_number":"pith:PO5E5JHD","schema_version":"1.0","canonical_sha256":"7bba4ea4e36ae25ec4bd95e0bdcd76d139fe91783e3fdf0dfdf5e4f9a14c46bb","source":{"kind":"arxiv","id":"2606.25066","version":1},"attestation_state":"computed","paper":{"title":"Do vision-language models search like humans? Reasoning tokens as a reaction-time analog in classic visual-search paradigms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Farahnaz Wick","submitted_at":"2026-06-23T18:19:16Z","abstract_excerpt":"Visual search has been one of the most productive paradigms in the study of visual attention: the way reaction time scales with the number of items distinguishes parallel, \"pop-out\" search from serial, attention-demanding search. I ask whether vision-language models (VLMs) exhibit the same behavioral signatures. I adapt four classic paradigms: feature versus conjunction search, spatial-configuration (T-vs-L) search, enumeration, and the tilted/vertical search asymmetry; and present them to current frontier and mid-tier models. Because a single model call has no reaction time, I use the number "},"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":"2606.25066","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T18:19:16Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e9cb51bb30f156537f6574aea4e61946f15e11d4b1a80ce8e8265c4b1a73feb3","abstract_canon_sha256":"92df1fe907cca62991b143b0c7e837619dcc839d37f6010500bd71ee960b9a63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T00:18:16.815538Z","signature_b64":"bexfCVkUt7yZJQAR4V/Acr5TsrspIbzJH7zEn/peFJVayNdWBi5r8fBgXKTBC/qmiUeJTx2PPdw3cduR3u1EAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bba4ea4e36ae25ec4bd95e0bdcd76d139fe91783e3fdf0dfdf5e4f9a14c46bb","last_reissued_at":"2026-06-25T00:18:16.815054Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T00:18:16.815054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do vision-language models search like humans? Reasoning tokens as a reaction-time analog in classic visual-search paradigms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Farahnaz Wick","submitted_at":"2026-06-23T18:19:16Z","abstract_excerpt":"Visual search has been one of the most productive paradigms in the study of visual attention: the way reaction time scales with the number of items distinguishes parallel, \"pop-out\" search from serial, attention-demanding search. I ask whether vision-language models (VLMs) exhibit the same behavioral signatures. I adapt four classic paradigms: feature versus conjunction search, spatial-configuration (T-vs-L) search, enumeration, and the tilted/vertical search asymmetry; and present them to current frontier and mid-tier models. Because a single model call has no reaction time, I use the number "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25066","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/2606.25066/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":"2606.25066","created_at":"2026-06-25T00:18:16.815110+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.25066v1","created_at":"2026-06-25T00:18:16.815110+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25066","created_at":"2026-06-25T00:18:16.815110+00:00"},{"alias_kind":"pith_short_12","alias_value":"PO5E5JHDNLRF","created_at":"2026-06-25T00:18:16.815110+00:00"},{"alias_kind":"pith_short_16","alias_value":"PO5E5JHDNLRF5RF5","created_at":"2026-06-25T00:18:16.815110+00:00"},{"alias_kind":"pith_short_8","alias_value":"PO5E5JHD","created_at":"2026-06-25T00:18:16.815110+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PO5E5JHDNLRF5RF5SXQL3TLW2E","json":"https://pith.science/pith/PO5E5JHDNLRF5RF5SXQL3TLW2E.json","graph_json":"https://pith.science/api/pith-number/PO5E5JHDNLRF5RF5SXQL3TLW2E/graph.json","events_json":"https://pith.science/api/pith-number/PO5E5JHDNLRF5RF5SXQL3TLW2E/events.json","paper":"https://pith.science/paper/PO5E5JHD"},"agent_actions":{"view_html":"https://pith.science/pith/PO5E5JHDNLRF5RF5SXQL3TLW2E","download_json":"https://pith.science/pith/PO5E5JHDNLRF5RF5SXQL3TLW2E.json","view_paper":"https://pith.science/paper/PO5E5JHD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.25066&json=true","fetch_graph":"https://pith.science/api/pith-number/PO5E5JHDNLRF5RF5SXQL3TLW2E/graph.json","fetch_events":"https://pith.science/api/pith-number/PO5E5JHDNLRF5RF5SXQL3TLW2E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PO5E5JHDNLRF5RF5SXQL3TLW2E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PO5E5JHDNLRF5RF5SXQL3TLW2E/action/storage_attestation","attest_author":"https://pith.science/pith/PO5E5JHDNLRF5RF5SXQL3TLW2E/action/author_attestation","sign_citation":"https://pith.science/pith/PO5E5JHDNLRF5RF5SXQL3TLW2E/action/citation_signature","submit_replication":"https://pith.science/pith/PO5E5JHDNLRF5RF5SXQL3TLW2E/action/replication_record"}},"created_at":"2026-06-25T00:18:16.815110+00:00","updated_at":"2026-06-25T00:18:16.815110+00:00"}