{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4V2BTG6G6P7VYCEJCWS4FFYAPC","short_pith_number":"pith:4V2BTG6G","schema_version":"1.0","canonical_sha256":"e574199bc6f3ff5c088915a5c2970078ae2dc15cf6c42fe87b59d0eb806e99e9","source":{"kind":"arxiv","id":"2607.08772","version":1},"attestation_state":"computed","paper":{"title":"Wat3R: Underwater 3D Geometry Learning without Annotations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dingkang Liang, Hongkai Lin, Jiangwei Ren, Wei Xu, Xiang Bai, Xingyu Jiang, Zijie Song","submitted_at":"2026-07-09T17:59:58Z","abstract_excerpt":"Estimating 3D geometry in underwater environments presents unique challenges due to light attenuation, scattering, and the absence of large-scale, high-quality 3D annotations. Pioneering methods rely on massive dense annotations that are impractical in underwater settings. In this paper, we propose Wat3R, a cross-domain semi-supervised learning framework designed to adapt feed-forward 3D reconstruction models from air to underwater scenes. Uniquely, our method eliminates the need for any annotated underwater data following a teacher-student architecture, that learns robust geometry representat"},"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":"2607.08772","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-09T17:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"31ff66affdd65e160f12ca06465d68fc551b1c990ad2afcec73212dabfba0396","abstract_canon_sha256":"bc0e162d0bb0069bdcb19f45da8e86cb6fbe6fa4548c829bca8116432b5efd9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T01:19:59.898595Z","signature_b64":"dU5D0hmaw/JYAjZPgeSYsfnXPSiL/bm9ADfZjurS1xYoU0B5PkswmzR1A4htmOfrs8KUrVfbm69EulCrlwMSBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e574199bc6f3ff5c088915a5c2970078ae2dc15cf6c42fe87b59d0eb806e99e9","last_reissued_at":"2026-07-10T01:19:59.898196Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T01:19:59.898196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Wat3R: Underwater 3D Geometry Learning without Annotations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dingkang Liang, Hongkai Lin, Jiangwei Ren, Wei Xu, Xiang Bai, Xingyu Jiang, Zijie Song","submitted_at":"2026-07-09T17:59:58Z","abstract_excerpt":"Estimating 3D geometry in underwater environments presents unique challenges due to light attenuation, scattering, and the absence of large-scale, high-quality 3D annotations. Pioneering methods rely on massive dense annotations that are impractical in underwater settings. In this paper, we propose Wat3R, a cross-domain semi-supervised learning framework designed to adapt feed-forward 3D reconstruction models from air to underwater scenes. Uniquely, our method eliminates the need for any annotated underwater data following a teacher-student architecture, that learns robust geometry representat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08772","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/2607.08772/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":"2607.08772","created_at":"2026-07-10T01:19:59.898250+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.08772v1","created_at":"2026-07-10T01:19:59.898250+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08772","created_at":"2026-07-10T01:19:59.898250+00:00"},{"alias_kind":"pith_short_12","alias_value":"4V2BTG6G6P7V","created_at":"2026-07-10T01:19:59.898250+00:00"},{"alias_kind":"pith_short_16","alias_value":"4V2BTG6G6P7VYCEJ","created_at":"2026-07-10T01:19:59.898250+00:00"},{"alias_kind":"pith_short_8","alias_value":"4V2BTG6G","created_at":"2026-07-10T01:19:59.898250+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/4V2BTG6G6P7VYCEJCWS4FFYAPC","json":"https://pith.science/pith/4V2BTG6G6P7VYCEJCWS4FFYAPC.json","graph_json":"https://pith.science/api/pith-number/4V2BTG6G6P7VYCEJCWS4FFYAPC/graph.json","events_json":"https://pith.science/api/pith-number/4V2BTG6G6P7VYCEJCWS4FFYAPC/events.json","paper":"https://pith.science/paper/4V2BTG6G"},"agent_actions":{"view_html":"https://pith.science/pith/4V2BTG6G6P7VYCEJCWS4FFYAPC","download_json":"https://pith.science/pith/4V2BTG6G6P7VYCEJCWS4FFYAPC.json","view_paper":"https://pith.science/paper/4V2BTG6G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.08772&json=true","fetch_graph":"https://pith.science/api/pith-number/4V2BTG6G6P7VYCEJCWS4FFYAPC/graph.json","fetch_events":"https://pith.science/api/pith-number/4V2BTG6G6P7VYCEJCWS4FFYAPC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4V2BTG6G6P7VYCEJCWS4FFYAPC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4V2BTG6G6P7VYCEJCWS4FFYAPC/action/storage_attestation","attest_author":"https://pith.science/pith/4V2BTG6G6P7VYCEJCWS4FFYAPC/action/author_attestation","sign_citation":"https://pith.science/pith/4V2BTG6G6P7VYCEJCWS4FFYAPC/action/citation_signature","submit_replication":"https://pith.science/pith/4V2BTG6G6P7VYCEJCWS4FFYAPC/action/replication_record"}},"created_at":"2026-07-10T01:19:59.898250+00:00","updated_at":"2026-07-10T01:19:59.898250+00:00"}