{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OOVH4AJHSWCGLG6YRLOS5RDRUL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8680f7a399f5d4d6cc24ddffad4cda0bfe5f9c1a4d26147e5b3bf8a6596c20c3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T11:54:17Z","title_canon_sha256":"a3cce3419fb9a86749b27a6c43e5dcf137d51828e22972aa4bc0bbd8ae1fd568"},"schema_version":"1.0","source":{"id":"2605.15876","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15876","created_at":"2026-05-20T00:04:38Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15876v2","created_at":"2026-05-20T00:04:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15876","created_at":"2026-05-20T00:04:38Z"},{"alias_kind":"pith_short_12","alias_value":"OOVH4AJHSWCG","created_at":"2026-05-20T00:04:38Z"},{"alias_kind":"pith_short_16","alias_value":"OOVH4AJHSWCGLG6Y","created_at":"2026-05-20T00:04:38Z"},{"alias_kind":"pith_short_8","alias_value":"OOVH4AJH","created_at":"2026-05-20T00:04:38Z"}],"graph_snapshots":[{"event_id":"sha256:793722621b2ccee3899c0f1b5fdc260df48bf83c01dcb2ddf45acbe753a56ae2","target":"graph","created_at":"2026-05-20T00:04:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.15876/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hanxun Yu, Jianke Zhu, Lei Ke, Xuan Qu, Yuxin Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T11:54:17Z","title":"Unlocking Dense Metric Depth Estimation in VLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15876","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b4ce9ae07285353a3fe37515a1b3a6fbc75ea4d7e7daf4466503e0731db90b35","target":"record","created_at":"2026-05-20T00:04:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8680f7a399f5d4d6cc24ddffad4cda0bfe5f9c1a4d26147e5b3bf8a6596c20c3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T11:54:17Z","title_canon_sha256":"a3cce3419fb9a86749b27a6c43e5dcf137d51828e22972aa4bc0bbd8ae1fd568"},"schema_version":"1.0","source":{"id":"2605.15876","kind":"arxiv","version":2}},"canonical_sha256":"73aa7e01279584659bd88add2ec471a2f3149b5856572657f4eab6dea363437d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73aa7e01279584659bd88add2ec471a2f3149b5856572657f4eab6dea363437d","first_computed_at":"2026-05-20T00:04:38.622967Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:38.622967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HgJSz4x8XG2Unvu6bLCRlPURmX2VpSjPsZXGlG/zv7mcwDXSCPKLINCokLB6Jd2Y/ikLgKbtHXbOSiJgOHm8DQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:38.623960Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15876","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4ce9ae07285353a3fe37515a1b3a6fbc75ea4d7e7daf4466503e0731db90b35","sha256:793722621b2ccee3899c0f1b5fdc260df48bf83c01dcb2ddf45acbe753a56ae2"],"state_sha256":"7cabcff508057661caebd2ec7d02f948388a698844de24357e3878a14690b5b1"}