{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OUKH3PDYMNWWSHM3FETXNFBB6I","short_pith_number":"pith:OUKH3PDY","schema_version":"1.0","canonical_sha256":"75147dbc78636d691d9b2927769421f23145a6a0bf66cc5f3bcf15758bf1d798","source":{"kind":"arxiv","id":"2607.01503","version":1},"attestation_state":"computed","paper":{"title":"Disentangling Pictorial Cue Understanding from Language Bias in VLMs via Depth Ordering Task","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Iuliia Kotseruba, John K. Tsotsos, Yiqian Liu","submitted_at":"2026-07-01T22:02:30Z","abstract_excerpt":"In this paper, we study depth perception of vision-language models (VLMs) to isolate the effects of pictorial depth cues and disentangle vision and language influences on model performance. To this end, we combine depth-ordering and odd-one-out psychophysical tasks: the VLMs are presented with images where one object is at different depth relative to other, otherwise identical, objects, and must determine whether the odd-one-out target is closer or farther to the observer. To create stimuli, we generate 2D views from simulated and real 3D scenes while controlling the presence of individual pic"},"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":"2607.01503","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-01T22:02:30Z","cross_cats_sorted":[],"title_canon_sha256":"839fa44185eeda264a1e0acd64bc4cbde892c90a6cb487594d74e9f2416657f0","abstract_canon_sha256":"8f1b504ef6c2faf2cddcb891a64b482e29a2cc2cce78dec66374c2726ce36157"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T00:17:02.535796Z","signature_b64":"D1ujJZCj8R5ESAQY2rvy8DpY+Cx2zoZPc8ReUa2rP1DxCuQW4se5ruiL95ompFYgp8c36E8fxtZpHU5AkkP9Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75147dbc78636d691d9b2927769421f23145a6a0bf66cc5f3bcf15758bf1d798","last_reissued_at":"2026-07-03T00:17:02.535355Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T00:17:02.535355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disentangling Pictorial Cue Understanding from Language Bias in VLMs via Depth Ordering Task","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Iuliia Kotseruba, John K. Tsotsos, Yiqian Liu","submitted_at":"2026-07-01T22:02:30Z","abstract_excerpt":"In this paper, we study depth perception of vision-language models (VLMs) to isolate the effects of pictorial depth cues and disentangle vision and language influences on model performance. To this end, we combine depth-ordering and odd-one-out psychophysical tasks: the VLMs are presented with images where one object is at different depth relative to other, otherwise identical, objects, and must determine whether the odd-one-out target is closer or farther to the observer. To create stimuli, we generate 2D views from simulated and real 3D scenes while controlling the presence of individual pic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01503","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/2607.01503/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":"2607.01503","created_at":"2026-07-03T00:17:02.535413+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01503v1","created_at":"2026-07-03T00:17:02.535413+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01503","created_at":"2026-07-03T00:17:02.535413+00:00"},{"alias_kind":"pith_short_12","alias_value":"OUKH3PDYMNWW","created_at":"2026-07-03T00:17:02.535413+00:00"},{"alias_kind":"pith_short_16","alias_value":"OUKH3PDYMNWWSHM3","created_at":"2026-07-03T00:17:02.535413+00:00"},{"alias_kind":"pith_short_8","alias_value":"OUKH3PDY","created_at":"2026-07-03T00:17:02.535413+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/OUKH3PDYMNWWSHM3FETXNFBB6I","json":"https://pith.science/pith/OUKH3PDYMNWWSHM3FETXNFBB6I.json","graph_json":"https://pith.science/api/pith-number/OUKH3PDYMNWWSHM3FETXNFBB6I/graph.json","events_json":"https://pith.science/api/pith-number/OUKH3PDYMNWWSHM3FETXNFBB6I/events.json","paper":"https://pith.science/paper/OUKH3PDY"},"agent_actions":{"view_html":"https://pith.science/pith/OUKH3PDYMNWWSHM3FETXNFBB6I","download_json":"https://pith.science/pith/OUKH3PDYMNWWSHM3FETXNFBB6I.json","view_paper":"https://pith.science/paper/OUKH3PDY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01503&json=true","fetch_graph":"https://pith.science/api/pith-number/OUKH3PDYMNWWSHM3FETXNFBB6I/graph.json","fetch_events":"https://pith.science/api/pith-number/OUKH3PDYMNWWSHM3FETXNFBB6I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OUKH3PDYMNWWSHM3FETXNFBB6I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OUKH3PDYMNWWSHM3FETXNFBB6I/action/storage_attestation","attest_author":"https://pith.science/pith/OUKH3PDYMNWWSHM3FETXNFBB6I/action/author_attestation","sign_citation":"https://pith.science/pith/OUKH3PDYMNWWSHM3FETXNFBB6I/action/citation_signature","submit_replication":"https://pith.science/pith/OUKH3PDYMNWWSHM3FETXNFBB6I/action/replication_record"}},"created_at":"2026-07-03T00:17:02.535413+00:00","updated_at":"2026-07-03T00:17:02.535413+00:00"}