{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CFFTP3JLKH274ACSTL6P763Q46","short_pith_number":"pith:CFFTP3JL","schema_version":"1.0","canonical_sha256":"114b37ed2b51f5fe00529afcfffb70e79c59c2492133b1f9c586494e382fd1da","source":{"kind":"arxiv","id":"2607.17099","version":1},"attestation_state":"computed","paper":{"title":"DepthART: Scaling Foundation Monocular Depth to Tiny Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Anlong Ming, Dianqiao Lei, Feng Xue, Guofeng Zhong, Haiyang Zhang, Haozhe Wang, Mingshuai Zhao, Nicu Sebe, Wu Chen, Zhaowen Lin","submitted_at":"2026-07-19T06:54:52Z","abstract_excerpt":"Recent geometric foundation models (e.g., Metric3D, Depth Anything and UniDepth) have substantially improved monocular depth estimation (MDE) in both cross-scene generalization and metric-scale prediction, yet these gains have not translated to tiny models. We bridge this gap with DepthART (Depth Anything Rethought for Tiny Models), which is a compact MDE model for on-device deployment across diverse scenes. We first identify two capacity-driven bottlenecks in tiny models: (i) overfitting to dataset-specific distribution bias and (ii) unstable metric adaptation under camera shift, where full f"},"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":"2607.17099","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-19T06:54:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b8f56a3879cbf623b629d9c8f46fc4bb915b28d846ae0572aa51e5861b08379f","abstract_canon_sha256":"d2bb4cd20ec49c0b7be7c9d98fc6ab97f2db32649114772b5ead00bd98eeaf20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:21:15.769883Z","signature_b64":"yW0uqdauKzcuKEhvRDy0z4A2K9tWnO9j/tjrOuS5ETBi8jSs3uoFvkxgWUsdPsaOuIoXqJS2M7jipS9xPaDgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"114b37ed2b51f5fe00529afcfffb70e79c59c2492133b1f9c586494e382fd1da","last_reissued_at":"2026-07-21T01:21:15.768971Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:21:15.768971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DepthART: Scaling Foundation Monocular Depth to Tiny Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Anlong Ming, Dianqiao Lei, Feng Xue, Guofeng Zhong, Haiyang Zhang, Haozhe Wang, Mingshuai Zhao, Nicu Sebe, Wu Chen, Zhaowen Lin","submitted_at":"2026-07-19T06:54:52Z","abstract_excerpt":"Recent geometric foundation models (e.g., Metric3D, Depth Anything and UniDepth) have substantially improved monocular depth estimation (MDE) in both cross-scene generalization and metric-scale prediction, yet these gains have not translated to tiny models. We bridge this gap with DepthART (Depth Anything Rethought for Tiny Models), which is a compact MDE model for on-device deployment across diverse scenes. We first identify two capacity-driven bottlenecks in tiny models: (i) overfitting to dataset-specific distribution bias and (ii) unstable metric adaptation under camera shift, where full f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17099","kind":"arxiv","version":1},"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/2607.17099/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":"2607.17099","created_at":"2026-07-21T01:21:15.769456+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.17099v1","created_at":"2026-07-21T01:21:15.769456+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17099","created_at":"2026-07-21T01:21:15.769456+00:00"},{"alias_kind":"pith_short_12","alias_value":"CFFTP3JLKH27","created_at":"2026-07-21T01:21:15.769456+00:00"},{"alias_kind":"pith_short_16","alias_value":"CFFTP3JLKH274ACS","created_at":"2026-07-21T01:21:15.769456+00:00"},{"alias_kind":"pith_short_8","alias_value":"CFFTP3JL","created_at":"2026-07-21T01:21:15.769456+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/CFFTP3JLKH274ACSTL6P763Q46","json":"https://pith.science/pith/CFFTP3JLKH274ACSTL6P763Q46.json","graph_json":"https://pith.science/api/pith-number/CFFTP3JLKH274ACSTL6P763Q46/graph.json","events_json":"https://pith.science/api/pith-number/CFFTP3JLKH274ACSTL6P763Q46/events.json","paper":"https://pith.science/paper/CFFTP3JL"},"agent_actions":{"view_html":"https://pith.science/pith/CFFTP3JLKH274ACSTL6P763Q46","download_json":"https://pith.science/pith/CFFTP3JLKH274ACSTL6P763Q46.json","view_paper":"https://pith.science/paper/CFFTP3JL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.17099&json=true","fetch_graph":"https://pith.science/api/pith-number/CFFTP3JLKH274ACSTL6P763Q46/graph.json","fetch_events":"https://pith.science/api/pith-number/CFFTP3JLKH274ACSTL6P763Q46/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CFFTP3JLKH274ACSTL6P763Q46/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CFFTP3JLKH274ACSTL6P763Q46/action/storage_attestation","attest_author":"https://pith.science/pith/CFFTP3JLKH274ACSTL6P763Q46/action/author_attestation","sign_citation":"https://pith.science/pith/CFFTP3JLKH274ACSTL6P763Q46/action/citation_signature","submit_replication":"https://pith.science/pith/CFFTP3JLKH274ACSTL6P763Q46/action/replication_record"}},"created_at":"2026-07-21T01:21:15.769456+00:00","updated_at":"2026-07-21T01:21:15.769456+00:00"}