{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AQSGC5YZMMBDG7PUACGGZ6F5CC","short_pith_number":"pith:AQSGC5YZ","schema_version":"1.0","canonical_sha256":"04246177196302337df4008c6cf8bd10981ecb40f454a4bcd59d06d3c0630154","source":{"kind":"arxiv","id":"2501.09898","version":4},"attestation_state":"computed","paper":{"title":"FoundationStereo: Zero-Shot Stereo Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Bowen Wen, Jan Kautz, Joseph Aribido, Matthew Trepte, Orazio Gallo, Stan Birchfield","submitted_at":"2025-01-17T01:01:44Z","abstract_excerpt":"Tremendous progress has been made in deep stereo matching to excel on benchmark datasets through per-domain fine-tuning. However, achieving strong zero-shot generalization - a hallmark of foundation models in other computer vision tasks - remains challenging for stereo matching. We introduce FoundationStereo, a foundation model for stereo depth estimation designed to achieve strong zero-shot generalization. To this end, we first construct a large-scale (1M stereo pairs) synthetic training dataset featuring large diversity and high photorealism, followed by an automatic self-curation pipeline t"},"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":"2501.09898","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-17T01:01:44Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"f280d64023c4c22ff1d941859ab2a3e1c92e8f1b6440ba90a9b3699c5809188e","abstract_canon_sha256":"8843799c53a7a6c06845117f823fb28360c28eadcb271b7e23f1cb579a39ac84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:21.624976Z","signature_b64":"182H4h6nuXxSK6EDmWADvOxQBD6svyJhVvHK5q1P4mltTmfFROvmwgzHyCKiVW5+nKfR03eho2rmiI9ns0WBDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04246177196302337df4008c6cf8bd10981ecb40f454a4bcd59d06d3c0630154","last_reissued_at":"2026-07-05T10:44:21.624492Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:21.624492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FoundationStereo: Zero-Shot Stereo Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Bowen Wen, Jan Kautz, Joseph Aribido, Matthew Trepte, Orazio Gallo, Stan Birchfield","submitted_at":"2025-01-17T01:01:44Z","abstract_excerpt":"Tremendous progress has been made in deep stereo matching to excel on benchmark datasets through per-domain fine-tuning. However, achieving strong zero-shot generalization - a hallmark of foundation models in other computer vision tasks - remains challenging for stereo matching. We introduce FoundationStereo, a foundation model for stereo depth estimation designed to achieve strong zero-shot generalization. To this end, we first construct a large-scale (1M stereo pairs) synthetic training dataset featuring large diversity and high photorealism, followed by an automatic self-curation pipeline t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09898","kind":"arxiv","version":4},"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/2501.09898/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":"2501.09898","created_at":"2026-07-05T10:44:21.624549+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.09898v4","created_at":"2026-07-05T10:44:21.624549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09898","created_at":"2026-07-05T10:44:21.624549+00:00"},{"alias_kind":"pith_short_12","alias_value":"AQSGC5YZMMBD","created_at":"2026-07-05T10:44:21.624549+00:00"},{"alias_kind":"pith_short_16","alias_value":"AQSGC5YZMMBDG7PU","created_at":"2026-07-05T10:44:21.624549+00:00"},{"alias_kind":"pith_short_8","alias_value":"AQSGC5YZ","created_at":"2026-07-05T10:44:21.624549+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24457","citing_title":"Lite Any Stereo V2: Faster and Stronger Efficient Zero-Shot Stereo Matching","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12604","citing_title":"EgoEngine: From Egocentric Human Videos to High-Fidelity Dexterous Robot Demonstrations","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09989","citing_title":"StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31636","citing_title":"LiteMatch: Lightweight Zero-Shot Stereo Matching via Cost Volume Stabilization","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2507.01099","citing_title":"Geometry-aware 4D Video Generation for Robot Manipulation","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2511.00392","citing_title":"SonarSweep: Fusing Sonar and Vision for Robust 3D Reconstruction via Plane Sweeping","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2511.07412","citing_title":"TwinOR: Photorealistic Digital Twins of Dynamic Operating Rooms for Embodied AI Research","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2512.06171","citing_title":"Automated Annotation of Shearographic Measurements Enabling Weakly Supervised Defect Detection","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09989","citing_title":"StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10333","citing_title":"Zero-shot World Models Are Developmentally Efficient Learners","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09352","citing_title":"LuMon: A Comprehensive Benchmark and Development Suite with Novel Datasets for Lunar Monocular Depth Estimation","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AQSGC5YZMMBDG7PUACGGZ6F5CC","json":"https://pith.science/pith/AQSGC5YZMMBDG7PUACGGZ6F5CC.json","graph_json":"https://pith.science/api/pith-number/AQSGC5YZMMBDG7PUACGGZ6F5CC/graph.json","events_json":"https://pith.science/api/pith-number/AQSGC5YZMMBDG7PUACGGZ6F5CC/events.json","paper":"https://pith.science/paper/AQSGC5YZ"},"agent_actions":{"view_html":"https://pith.science/pith/AQSGC5YZMMBDG7PUACGGZ6F5CC","download_json":"https://pith.science/pith/AQSGC5YZMMBDG7PUACGGZ6F5CC.json","view_paper":"https://pith.science/paper/AQSGC5YZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.09898&json=true","fetch_graph":"https://pith.science/api/pith-number/AQSGC5YZMMBDG7PUACGGZ6F5CC/graph.json","fetch_events":"https://pith.science/api/pith-number/AQSGC5YZMMBDG7PUACGGZ6F5CC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AQSGC5YZMMBDG7PUACGGZ6F5CC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AQSGC5YZMMBDG7PUACGGZ6F5CC/action/storage_attestation","attest_author":"https://pith.science/pith/AQSGC5YZMMBDG7PUACGGZ6F5CC/action/author_attestation","sign_citation":"https://pith.science/pith/AQSGC5YZMMBDG7PUACGGZ6F5CC/action/citation_signature","submit_replication":"https://pith.science/pith/AQSGC5YZMMBDG7PUACGGZ6F5CC/action/replication_record"}},"created_at":"2026-07-05T10:44:21.624549+00:00","updated_at":"2026-07-05T10:44:21.624549+00:00"}