{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OOVH4AJHSWCGLG6YRLOS5RDRUL","short_pith_number":"pith:OOVH4AJH","schema_version":"1.0","canonical_sha256":"73aa7e01279584659bd88add2ec471a2f3149b5856572657f4eab6dea363437d","source":{"kind":"arxiv","id":"2605.15876","version":2},"attestation_state":"computed","paper":{"title":"Unlocking Dense Metric Depth Estimation in VLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanxun Yu, Jianke Zhu, Lei Ke, Xuan Qu, Yuxin Wang","submitted_at":"2026-05-15T11:54:17Z","abstract_excerpt":"Vision-Language Models (VLMs) excel at 2D tasks such as grounding and captioning, yet remain limited in 3D understanding. A key limitation is their text-only supervision paradigm, which under-constrains fine-grained visual perception and prevents the recovery of dense geometry. Prior methods either distill geometry from external vision models, introducing error accumulation, or enable direct prediction with inefficient per-pixel query or coarse token-level outputs. In this paper, we propose DepthVLM, a simple yet effective framework that transforms a single VLM into a native dense geometry pre"},"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":"2605.15876","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T11:54:17Z","cross_cats_sorted":[],"title_canon_sha256":"a3cce3419fb9a86749b27a6c43e5dcf137d51828e22972aa4bc0bbd8ae1fd568","abstract_canon_sha256":"8680f7a399f5d4d6cc24ddffad4cda0bfe5f9c1a4d26147e5b3bf8a6596c20c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:38.623960Z","signature_b64":"HgJSz4x8XG2Unvu6bLCRlPURmX2VpSjPsZXGlG/zv7mcwDXSCPKLINCokLB6Jd2Y/ikLgKbtHXbOSiJgOHm8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73aa7e01279584659bd88add2ec471a2f3149b5856572657f4eab6dea363437d","last_reissued_at":"2026-05-20T00:04:38.622967Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:38.622967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unlocking Dense Metric Depth Estimation in VLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanxun Yu, Jianke Zhu, Lei Ke, Xuan Qu, Yuxin Wang","submitted_at":"2026-05-15T11:54:17Z","abstract_excerpt":"Vision-Language Models (VLMs) excel at 2D tasks such as grounding and captioning, yet remain limited in 3D understanding. A key limitation is their text-only supervision paradigm, which under-constrains fine-grained visual perception and prevents the recovery of dense geometry. Prior methods either distill geometry from external vision models, introducing error accumulation, or enable direct prediction with inefficient per-pixel query or coarse token-level outputs. In this paper, we propose DepthVLM, a simple yet effective framework that transforms a single VLM into a native dense geometry pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15876","kind":"arxiv","version":2},"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/2605.15876/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":"2605.15876","created_at":"2026-05-20T00:04:38.623117+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15876v2","created_at":"2026-05-20T00:04:38.623117+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15876","created_at":"2026-05-20T00:04:38.623117+00:00"},{"alias_kind":"pith_short_12","alias_value":"OOVH4AJHSWCG","created_at":"2026-05-20T00:04:38.623117+00:00"},{"alias_kind":"pith_short_16","alias_value":"OOVH4AJHSWCGLG6Y","created_at":"2026-05-20T00:04:38.623117+00:00"},{"alias_kind":"pith_short_8","alias_value":"OOVH4AJH","created_at":"2026-05-20T00:04:38.623117+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/OOVH4AJHSWCGLG6YRLOS5RDRUL","json":"https://pith.science/pith/OOVH4AJHSWCGLG6YRLOS5RDRUL.json","graph_json":"https://pith.science/api/pith-number/OOVH4AJHSWCGLG6YRLOS5RDRUL/graph.json","events_json":"https://pith.science/api/pith-number/OOVH4AJHSWCGLG6YRLOS5RDRUL/events.json","paper":"https://pith.science/paper/OOVH4AJH"},"agent_actions":{"view_html":"https://pith.science/pith/OOVH4AJHSWCGLG6YRLOS5RDRUL","download_json":"https://pith.science/pith/OOVH4AJHSWCGLG6YRLOS5RDRUL.json","view_paper":"https://pith.science/paper/OOVH4AJH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15876&json=true","fetch_graph":"https://pith.science/api/pith-number/OOVH4AJHSWCGLG6YRLOS5RDRUL/graph.json","fetch_events":"https://pith.science/api/pith-number/OOVH4AJHSWCGLG6YRLOS5RDRUL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OOVH4AJHSWCGLG6YRLOS5RDRUL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OOVH4AJHSWCGLG6YRLOS5RDRUL/action/storage_attestation","attest_author":"https://pith.science/pith/OOVH4AJHSWCGLG6YRLOS5RDRUL/action/author_attestation","sign_citation":"https://pith.science/pith/OOVH4AJHSWCGLG6YRLOS5RDRUL/action/citation_signature","submit_replication":"https://pith.science/pith/OOVH4AJHSWCGLG6YRLOS5RDRUL/action/replication_record"}},"created_at":"2026-05-20T00:04:38.623117+00:00","updated_at":"2026-05-20T00:04:38.623117+00:00"}