{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OOVH4AJHSWCGLG6YRLOS5RDRUL","short_pith_number":"pith:OOVH4AJH","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"},"canonical_sha256":"73aa7e01279584659bd88add2ec471a2f3149b5856572657f4eab6dea363437d","source":{"kind":"arxiv","id":"2605.15876","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OOVH4AJHSWCGLG6YRLOS5RDRUL","target":"record","payload":{"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"},"canonical_sha256":"73aa7e01279584659bd88add2ec471a2f3149b5856572657f4eab6dea363437d","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"},"source_kind":"arxiv","source_id":"2605.15876","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:04:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7qzODmSbRztjhYM5anmFRFUCXQUo5UZNH0hPaW/zJXTXabGyyqC4rZVv+H5sDap6JK8A0hfQJEA50DBRtB6RAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T07:28:13.526782Z"},"content_sha256":"b4ce9ae07285353a3fe37515a1b3a6fbc75ea4d7e7daf4466503e0731db90b35","schema_version":"1.0","event_id":"sha256:b4ce9ae07285353a3fe37515a1b3a6fbc75ea4d7e7daf4466503e0731db90b35"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OOVH4AJHSWCGLG6YRLOS5RDRUL","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:04:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3DQc233cYnUtUHon9lTDdTGDqfPTYPXwIVEhOY0ezYpNwL5mzpVQWiMSUtrn+xLii9iZSBsFzbE5I5NxjghkCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T07:28:13.527473Z"},"content_sha256":"793722621b2ccee3899c0f1b5fdc260df48bf83c01dcb2ddf45acbe753a56ae2","schema_version":"1.0","event_id":"sha256:793722621b2ccee3899c0f1b5fdc260df48bf83c01dcb2ddf45acbe753a56ae2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OOVH4AJHSWCGLG6YRLOS5RDRUL/bundle.json","state_url":"https://pith.science/pith/OOVH4AJHSWCGLG6YRLOS5RDRUL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OOVH4AJHSWCGLG6YRLOS5RDRUL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-22T07:28:13Z","links":{"resolver":"https://pith.science/pith/OOVH4AJHSWCGLG6YRLOS5RDRUL","bundle":"https://pith.science/pith/OOVH4AJHSWCGLG6YRLOS5RDRUL/bundle.json","state":"https://pith.science/pith/OOVH4AJHSWCGLG6YRLOS5RDRUL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OOVH4AJHSWCGLG6YRLOS5RDRUL/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oVUocGt9gAxSNLw9A8JTalhnG8SbjSiJ56sV9OJTWz3a2ioh9abY94EpItjkncMqogDZbS5R9gNqlTqDv/EMBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T07:28:13.530982Z","bundle_sha256":"1326f1a39e7eaf09289363ab5cd11a8d8944f7de70d9057cd70be20ffe11f3b4"}}