{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2FICLQ2UWOJMPPA3PN2IYNOYVZ","short_pith_number":"pith:2FICLQ2U","schema_version":"1.0","canonical_sha256":"d15025c354b392c7bc1b7b748c35d8ae6647c39ec02381bc4910d78a9fe92852","source":{"kind":"arxiv","id":"2401.10891","version":2},"attestation_state":"computed","paper":{"title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingyi Kang, Hengshuang Zhao, Jiashi Feng, Lihe Yang, Xiaogang Xu, Zilong Huang","submitted_at":"2024-01-19T18:59:52Z","abstract_excerpt":"This work presents Depth Anything, a highly practical solution for robust monocular depth estimation. Without pursuing novel technical modules, we aim to build a simple yet powerful foundation model dealing with any images under any circumstances. To this end, we scale up the dataset by designing a data engine to collect and automatically annotate large-scale unlabeled data (~62M), which significantly enlarges the data coverage and thus is able to reduce the generalization error. We investigate two simple yet effective strategies that make data scaling-up promising. First, a more challenging o"},"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":"2401.10891","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-19T18:59:52Z","cross_cats_sorted":[],"title_canon_sha256":"1119eda998cdde83511f54cae9c2fc0dfbd6b2b2cf66870126de7b1ef22e00b7","abstract_canon_sha256":"31bdcd575d4b79d49a4b71369de421ec52cadb1eee37ba4a1a25f6ed1cdc6970"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:09.503539Z","signature_b64":"mJelh0QEenM9y2GtxcJMTW7f/9Sjbnzuy/4Qr37mrZV9otw0On4nPkH+rUKJY/xxfm6yxC0UOt7Hu6A1IdwKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d15025c354b392c7bc1b7b748c35d8ae6647c39ec02381bc4910d78a9fe92852","last_reissued_at":"2026-07-05T08:05:09.503073Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:09.503073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingyi Kang, Hengshuang Zhao, Jiashi Feng, Lihe Yang, Xiaogang Xu, Zilong Huang","submitted_at":"2024-01-19T18:59:52Z","abstract_excerpt":"This work presents Depth Anything, a highly practical solution for robust monocular depth estimation. Without pursuing novel technical modules, we aim to build a simple yet powerful foundation model dealing with any images under any circumstances. To this end, we scale up the dataset by designing a data engine to collect and automatically annotate large-scale unlabeled data (~62M), which significantly enlarges the data coverage and thus is able to reduce the generalization error. We investigate two simple yet effective strategies that make data scaling-up promising. First, a more challenging o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.10891","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/2401.10891/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":"2401.10891","created_at":"2026-07-05T08:05:09.503130+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.10891v2","created_at":"2026-07-05T08:05:09.503130+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.10891","created_at":"2026-07-05T08:05:09.503130+00:00"},{"alias_kind":"pith_short_12","alias_value":"2FICLQ2UWOJM","created_at":"2026-07-05T08:05:09.503130+00:00"},{"alias_kind":"pith_short_16","alias_value":"2FICLQ2UWOJMPPA3","created_at":"2026-07-05T08:05:09.503130+00:00"},{"alias_kind":"pith_short_8","alias_value":"2FICLQ2U","created_at":"2026-07-05T08:05:09.503130+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.06871","citing_title":"Geometric Collapse: When Vision Models Fail to Verify Physical Causality","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2607.05392","citing_title":"SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion","ref_index":64,"is_internal_anchor":true},{"citing_arxiv_id":"2606.18426","citing_title":"VEGA: Learning Navigation VLAs from In-the-Wild Egocentric Video with Geometric Trajectory Supervision","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26456","citing_title":"Sparse-LiDAR Prompting of Monocular Geometry Foundations: An Empirical Study Toward Long-Range Driving Depth","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2411.14295","citing_title":"DissolveStereo: Coarse Depth Injection for Zero-Shot Stereo Video Generation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22190","citing_title":"No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12239","citing_title":"Physics-Grounded Monocular Vehicle Distance Estimation Using Standardized License Plate Typography","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2512.11988","citing_title":"CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interaction","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2406.06978","citing_title":"Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12239","citing_title":"Physics-Grounded Monocular Vehicle Distance Estimation Using Standardized License Plate Typography","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13294","citing_title":"PAT-VCM: Plug-and-Play Auxiliary Tokens for Video Coding for Machines","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20393","citing_title":"MLG-Stereo: ViT Based Stereo Matching with Multi-Stage Local-Global Enhancement","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2FICLQ2UWOJMPPA3PN2IYNOYVZ","json":"https://pith.science/pith/2FICLQ2UWOJMPPA3PN2IYNOYVZ.json","graph_json":"https://pith.science/api/pith-number/2FICLQ2UWOJMPPA3PN2IYNOYVZ/graph.json","events_json":"https://pith.science/api/pith-number/2FICLQ2UWOJMPPA3PN2IYNOYVZ/events.json","paper":"https://pith.science/paper/2FICLQ2U"},"agent_actions":{"view_html":"https://pith.science/pith/2FICLQ2UWOJMPPA3PN2IYNOYVZ","download_json":"https://pith.science/pith/2FICLQ2UWOJMPPA3PN2IYNOYVZ.json","view_paper":"https://pith.science/paper/2FICLQ2U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.10891&json=true","fetch_graph":"https://pith.science/api/pith-number/2FICLQ2UWOJMPPA3PN2IYNOYVZ/graph.json","fetch_events":"https://pith.science/api/pith-number/2FICLQ2UWOJMPPA3PN2IYNOYVZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2FICLQ2UWOJMPPA3PN2IYNOYVZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2FICLQ2UWOJMPPA3PN2IYNOYVZ/action/storage_attestation","attest_author":"https://pith.science/pith/2FICLQ2UWOJMPPA3PN2IYNOYVZ/action/author_attestation","sign_citation":"https://pith.science/pith/2FICLQ2UWOJMPPA3PN2IYNOYVZ/action/citation_signature","submit_replication":"https://pith.science/pith/2FICLQ2UWOJMPPA3PN2IYNOYVZ/action/replication_record"}},"created_at":"2026-07-05T08:05:09.503130+00:00","updated_at":"2026-07-05T08:05:09.503130+00:00"}