{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OYG6YMBTUV2YGYE4ABSWD6EIQT","short_pith_number":"pith:OYG6YMBT","schema_version":"1.0","canonical_sha256":"760dec3033a57583609c006561f88884c7caeb3e31e1f30266f4ab2d5e8c7924","source":{"kind":"arxiv","id":"2607.12433","version":1},"attestation_state":"computed","paper":{"title":"ARDepth: Auto-regressive Monocular Depth Estimation with Progressive Visual Conditioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guanbin Li, Weikai Chen, Weiming Zhang, Wei Zhang, Xiao Tan, Xiaoxu Li, Zijie Wang","submitted_at":"2026-07-14T07:06:46Z","abstract_excerpt":"Diffusion models have recently become the dominant paradigm for monocular depth estimation (MDE). However, they implicitly assume that depth can be recovered as a globally smooth field through iterative denoising, which does not explicitly reflect the piecewise and scale-dependent organization of scene geometry. In practice, geometric structure emerges progressively across spatial scales, where coarse layout, surfaces, and boundaries are constructed in a hierarchical manner. Motivated by this observation, we introduce ARDepth, which formulates depth estimation as structured auto-regressive gen"},"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":"2607.12433","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-14T07:06:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e34586c2287e0640d5e14270f131ccd4b3be14a66644cdde39fdd9a2f6bb52e4","abstract_canon_sha256":"4cbf9a8ddb8b397b07e0504d3e831d3b02d2f1acf97da2998bb121a88ac5cf96"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-15T01:21:34.685830Z","signature_b64":"qWSJdRFH/BZAiiLlLhEdPAeWvw8Iy1J30+W+XfRQ7NoF2fQ5v0ML3xQRghnAl3XpJ7Cxtr2fyivLLkkpQFLJDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"760dec3033a57583609c006561f88884c7caeb3e31e1f30266f4ab2d5e8c7924","last_reissued_at":"2026-07-15T01:21:34.684952Z","signature_status":"signed_v1","first_computed_at":"2026-07-15T01:21:34.684952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ARDepth: Auto-regressive Monocular Depth Estimation with Progressive Visual Conditioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guanbin Li, Weikai Chen, Weiming Zhang, Wei Zhang, Xiao Tan, Xiaoxu Li, Zijie Wang","submitted_at":"2026-07-14T07:06:46Z","abstract_excerpt":"Diffusion models have recently become the dominant paradigm for monocular depth estimation (MDE). However, they implicitly assume that depth can be recovered as a globally smooth field through iterative denoising, which does not explicitly reflect the piecewise and scale-dependent organization of scene geometry. In practice, geometric structure emerges progressively across spatial scales, where coarse layout, surfaces, and boundaries are constructed in a hierarchical manner. Motivated by this observation, we introduce ARDepth, which formulates depth estimation as structured auto-regressive gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.12433","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/2607.12433/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":"2607.12433","created_at":"2026-07-15T01:21:34.685401+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.12433v1","created_at":"2026-07-15T01:21:34.685401+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.12433","created_at":"2026-07-15T01:21:34.685401+00:00"},{"alias_kind":"pith_short_12","alias_value":"OYG6YMBTUV2Y","created_at":"2026-07-15T01:21:34.685401+00:00"},{"alias_kind":"pith_short_16","alias_value":"OYG6YMBTUV2YGYE4","created_at":"2026-07-15T01:21:34.685401+00:00"},{"alias_kind":"pith_short_8","alias_value":"OYG6YMBT","created_at":"2026-07-15T01:21:34.685401+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/OYG6YMBTUV2YGYE4ABSWD6EIQT","json":"https://pith.science/pith/OYG6YMBTUV2YGYE4ABSWD6EIQT.json","graph_json":"https://pith.science/api/pith-number/OYG6YMBTUV2YGYE4ABSWD6EIQT/graph.json","events_json":"https://pith.science/api/pith-number/OYG6YMBTUV2YGYE4ABSWD6EIQT/events.json","paper":"https://pith.science/paper/OYG6YMBT"},"agent_actions":{"view_html":"https://pith.science/pith/OYG6YMBTUV2YGYE4ABSWD6EIQT","download_json":"https://pith.science/pith/OYG6YMBTUV2YGYE4ABSWD6EIQT.json","view_paper":"https://pith.science/paper/OYG6YMBT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.12433&json=true","fetch_graph":"https://pith.science/api/pith-number/OYG6YMBTUV2YGYE4ABSWD6EIQT/graph.json","fetch_events":"https://pith.science/api/pith-number/OYG6YMBTUV2YGYE4ABSWD6EIQT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OYG6YMBTUV2YGYE4ABSWD6EIQT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OYG6YMBTUV2YGYE4ABSWD6EIQT/action/storage_attestation","attest_author":"https://pith.science/pith/OYG6YMBTUV2YGYE4ABSWD6EIQT/action/author_attestation","sign_citation":"https://pith.science/pith/OYG6YMBTUV2YGYE4ABSWD6EIQT/action/citation_signature","submit_replication":"https://pith.science/pith/OYG6YMBTUV2YGYE4ABSWD6EIQT/action/replication_record"}},"created_at":"2026-07-15T01:21:34.685401+00:00","updated_at":"2026-07-15T01:21:34.685401+00:00"}