{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NUPJRV7LUDRNQ5FRV3L5AEIUJV","short_pith_number":"pith:NUPJRV7L","schema_version":"1.0","canonical_sha256":"6d1e98d7eba0e2d874b1aed7d011144d7a801d96306612e527ec0067731d9406","source":{"kind":"arxiv","id":"2601.22054","version":2},"attestation_state":"computed","paper":{"title":"MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Baorui Ma, Donglin Di, Hao Li, Jiahui Yang, Jianxun Cui, Wei Chen, Xuancheng Zhang, Yan Xie","submitted_at":"2026-01-29T17:52:41Z","abstract_excerpt":"Scaling has powered recent advances in vision foundation models, yet extending this paradigm to metric depth estimation remains challenging due to heterogeneous sensor noise, camera-dependent biases, and metric ambiguity in noisy cross-source 3D data. We introduce Metric Anything, a simple and scalable pretraining framework that learns metric depth from noisy, diverse 3D sources without manually engineered prompts, camera-specific modeling, or task-specific architectures. Central to our approach is the Sparse Metric Prompt, created by randomly masking depth maps, which serves as a universal in"},"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":"2601.22054","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-29T17:52:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"406d01f57326811cf52ec1fd868139276afdc5b52e0c916718461ecf93f3cc76","abstract_canon_sha256":"6297532d40b4d021959a5e43a918fbb33b6e8424d4a9ab72de2e197b707852b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T01:16:05.014629Z","signature_b64":"mlG/p+P81nrnXzZKjyFWkecnQjxs74rlgLZT4SwUIE6kfuhIXO/gVJHVDjoW3KrC6zAo8anf/WvcsM1faaVQCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d1e98d7eba0e2d874b1aed7d011144d7a801d96306612e527ec0067731d9406","last_reissued_at":"2026-07-07T01:16:05.013821Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T01:16:05.013821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Baorui Ma, Donglin Di, Hao Li, Jiahui Yang, Jianxun Cui, Wei Chen, Xuancheng Zhang, Yan Xie","submitted_at":"2026-01-29T17:52:41Z","abstract_excerpt":"Scaling has powered recent advances in vision foundation models, yet extending this paradigm to metric depth estimation remains challenging due to heterogeneous sensor noise, camera-dependent biases, and metric ambiguity in noisy cross-source 3D data. We introduce Metric Anything, a simple and scalable pretraining framework that learns metric depth from noisy, diverse 3D sources without manually engineered prompts, camera-specific modeling, or task-specific architectures. Central to our approach is the Sparse Metric Prompt, created by randomly masking depth maps, which serves as a universal in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.22054","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/2601.22054/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":"2601.22054","created_at":"2026-07-07T01:16:05.013913+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.22054v2","created_at":"2026-07-07T01:16:05.013913+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.22054","created_at":"2026-07-07T01:16:05.013913+00:00"},{"alias_kind":"pith_short_12","alias_value":"NUPJRV7LUDRN","created_at":"2026-07-07T01:16:05.013913+00:00"},{"alias_kind":"pith_short_16","alias_value":"NUPJRV7LUDRNQ5FR","created_at":"2026-07-07T01:16:05.013913+00:00"},{"alias_kind":"pith_short_8","alias_value":"NUPJRV7L","created_at":"2026-07-07T01:16:05.013913+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.31488","citing_title":"DrivingDepth: Sparse-Prompted Pixel-wise Scale Correction for Driving Depth Estimation","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NUPJRV7LUDRNQ5FRV3L5AEIUJV","json":"https://pith.science/pith/NUPJRV7LUDRNQ5FRV3L5AEIUJV.json","graph_json":"https://pith.science/api/pith-number/NUPJRV7LUDRNQ5FRV3L5AEIUJV/graph.json","events_json":"https://pith.science/api/pith-number/NUPJRV7LUDRNQ5FRV3L5AEIUJV/events.json","paper":"https://pith.science/paper/NUPJRV7L"},"agent_actions":{"view_html":"https://pith.science/pith/NUPJRV7LUDRNQ5FRV3L5AEIUJV","download_json":"https://pith.science/pith/NUPJRV7LUDRNQ5FRV3L5AEIUJV.json","view_paper":"https://pith.science/paper/NUPJRV7L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.22054&json=true","fetch_graph":"https://pith.science/api/pith-number/NUPJRV7LUDRNQ5FRV3L5AEIUJV/graph.json","fetch_events":"https://pith.science/api/pith-number/NUPJRV7LUDRNQ5FRV3L5AEIUJV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NUPJRV7LUDRNQ5FRV3L5AEIUJV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NUPJRV7LUDRNQ5FRV3L5AEIUJV/action/storage_attestation","attest_author":"https://pith.science/pith/NUPJRV7LUDRNQ5FRV3L5AEIUJV/action/author_attestation","sign_citation":"https://pith.science/pith/NUPJRV7LUDRNQ5FRV3L5AEIUJV/action/citation_signature","submit_replication":"https://pith.science/pith/NUPJRV7LUDRNQ5FRV3L5AEIUJV/action/replication_record"}},"created_at":"2026-07-07T01:16:05.013913+00:00","updated_at":"2026-07-07T01:16:05.013913+00:00"}