{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KTLSUUNBYIXF7J4CR6OU3II7JS","short_pith_number":"pith:KTLSUUNB","schema_version":"1.0","canonical_sha256":"54d72a51a1c22e5fa7828f9d4da11f4c9ba209deafcf576ba8355338efde7f2d","source":{"kind":"arxiv","id":"2606.29600","version":1},"attestation_state":"computed","paper":{"title":"One Scene, Two Depths: Probing Geometric Ambiguity in Monocular Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Feng Xue, Haowei Li, Matthew Johnson-Roberson, Shusheng Yang, Tianyi Zhang, Xiang Li, Xiaohao Xu, Xiaonan Huang","submitted_at":"2026-06-28T20:54:18Z","abstract_excerpt":"A faithful 3D world representation should account for layered geometry, where a single camera ray may contain multiple visible and geometrically valid surfaces. Monocular depth estimation, however, reduces this structure to one scalar depth per pixel. Transparent scenes make this ambiguity measurable: the same ray can pass through foreground glass and observe the background, turning the supervised target into a convention of annotation, data, and training rather than a scene-intrinsic truth. A learned predictor exposes this convention as its depth-layer preference. We introduce MultiDepth-3k ("},"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":"2606.29600","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-28T20:54:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3fa9f30fb8c20a4d3b0c98f0d12ca8f9802d7645de6be4d85a7b1191271a850f","abstract_canon_sha256":"5d0e7743a017577e4bdf9868d31755f6eee4b0bd3be6bb8147581cb0aa7548d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:18:13.764060Z","signature_b64":"jgowvdwhxpjwx7rQMa70DQgNN+q8m77E0Ow8SvnbCCHFktQP8RDN96/OlpiL9+DcdOlSwUNOFYQ04ZsuBAN0CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54d72a51a1c22e5fa7828f9d4da11f4c9ba209deafcf576ba8355338efde7f2d","last_reissued_at":"2026-06-30T01:18:13.763562Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:18:13.763562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One Scene, Two Depths: Probing Geometric Ambiguity in Monocular Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Feng Xue, Haowei Li, Matthew Johnson-Roberson, Shusheng Yang, Tianyi Zhang, Xiang Li, Xiaohao Xu, Xiaonan Huang","submitted_at":"2026-06-28T20:54:18Z","abstract_excerpt":"A faithful 3D world representation should account for layered geometry, where a single camera ray may contain multiple visible and geometrically valid surfaces. Monocular depth estimation, however, reduces this structure to one scalar depth per pixel. Transparent scenes make this ambiguity measurable: the same ray can pass through foreground glass and observe the background, turning the supervised target into a convention of annotation, data, and training rather than a scene-intrinsic truth. A learned predictor exposes this convention as its depth-layer preference. We introduce MultiDepth-3k ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29600","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/2606.29600/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":"2606.29600","created_at":"2026-06-30T01:18:13.763631+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29600v1","created_at":"2026-06-30T01:18:13.763631+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29600","created_at":"2026-06-30T01:18:13.763631+00:00"},{"alias_kind":"pith_short_12","alias_value":"KTLSUUNBYIXF","created_at":"2026-06-30T01:18:13.763631+00:00"},{"alias_kind":"pith_short_16","alias_value":"KTLSUUNBYIXF7J4C","created_at":"2026-06-30T01:18:13.763631+00:00"},{"alias_kind":"pith_short_8","alias_value":"KTLSUUNB","created_at":"2026-06-30T01:18:13.763631+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/KTLSUUNBYIXF7J4CR6OU3II7JS","json":"https://pith.science/pith/KTLSUUNBYIXF7J4CR6OU3II7JS.json","graph_json":"https://pith.science/api/pith-number/KTLSUUNBYIXF7J4CR6OU3II7JS/graph.json","events_json":"https://pith.science/api/pith-number/KTLSUUNBYIXF7J4CR6OU3II7JS/events.json","paper":"https://pith.science/paper/KTLSUUNB"},"agent_actions":{"view_html":"https://pith.science/pith/KTLSUUNBYIXF7J4CR6OU3II7JS","download_json":"https://pith.science/pith/KTLSUUNBYIXF7J4CR6OU3II7JS.json","view_paper":"https://pith.science/paper/KTLSUUNB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29600&json=true","fetch_graph":"https://pith.science/api/pith-number/KTLSUUNBYIXF7J4CR6OU3II7JS/graph.json","fetch_events":"https://pith.science/api/pith-number/KTLSUUNBYIXF7J4CR6OU3II7JS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KTLSUUNBYIXF7J4CR6OU3II7JS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KTLSUUNBYIXF7J4CR6OU3II7JS/action/storage_attestation","attest_author":"https://pith.science/pith/KTLSUUNBYIXF7J4CR6OU3II7JS/action/author_attestation","sign_citation":"https://pith.science/pith/KTLSUUNBYIXF7J4CR6OU3II7JS/action/citation_signature","submit_replication":"https://pith.science/pith/KTLSUUNBYIXF7J4CR6OU3II7JS/action/replication_record"}},"created_at":"2026-06-30T01:18:13.763631+00:00","updated_at":"2026-06-30T01:18:13.763631+00:00"}