{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LFTWL7OJQV3Z5H6RGCN6HTNBKJ","short_pith_number":"pith:LFTWL7OJ","schema_version":"1.0","canonical_sha256":"596765fdc985779e9fd1309be3cda1525e274c15c9ee8de349e82323692992f1","source":{"kind":"arxiv","id":"2506.01933","version":3},"attestation_state":"computed","paper":{"title":"E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boris Ivanovic, Chen Chen, Marco Pavone, Wenyan Cong, Yancheng Zhang, Yan Wang, Yiqing Liang, Zhangyang Wang, Zhiwen Fan, Ziyi Yang","submitted_at":"2025-06-02T17:53:09Z","abstract_excerpt":"Spatial intelligence, encompassing 3D reconstruction, perception, and reasoning, is fundamental to applications such as robotics, aerial imaging, and extended reality. A key enabler is the real-time, accurate estimation of core 3D attributes (camera parameters, point clouds, depth maps, and 3D point tracks) from unstructured or streaming imagery. Inspired by the success of large foundation models in language and 2D vision, a new class of end-to-end 3D geometric foundation models (GFMs) has emerged, directly predicting dense 3D representations in a single feed-forward pass, eliminating the need"},"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":"2506.01933","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T17:53:09Z","cross_cats_sorted":[],"title_canon_sha256":"6b2844dcecbf05bbbeaa2c0580ad8a26340c66914ff9138263017876f7f7d212","abstract_canon_sha256":"8666e04d8170e6002cd13bb48d127f6cd432329763ad686f418c467bb28eb638"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:51.840701Z","signature_b64":"+8ud4eJ9IHGmiWQUo1Op0kQtgw6U1Cz1FzS36G2jZFO1x7yEo9i67FJxaQczNwcn1YObmpMF/D5vaGgYAtLwCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"596765fdc985779e9fd1309be3cda1525e274c15c9ee8de349e82323692992f1","last_reissued_at":"2026-07-05T11:34:51.840200Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:51.840200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boris Ivanovic, Chen Chen, Marco Pavone, Wenyan Cong, Yancheng Zhang, Yan Wang, Yiqing Liang, Zhangyang Wang, Zhiwen Fan, Ziyi Yang","submitted_at":"2025-06-02T17:53:09Z","abstract_excerpt":"Spatial intelligence, encompassing 3D reconstruction, perception, and reasoning, is fundamental to applications such as robotics, aerial imaging, and extended reality. A key enabler is the real-time, accurate estimation of core 3D attributes (camera parameters, point clouds, depth maps, and 3D point tracks) from unstructured or streaming imagery. Inspired by the success of large foundation models in language and 2D vision, a new class of end-to-end 3D geometric foundation models (GFMs) has emerged, directly predicting dense 3D representations in a single feed-forward pass, eliminating the need"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01933","kind":"arxiv","version":3},"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/2506.01933/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":"2506.01933","created_at":"2026-07-05T11:34:51.840259+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01933v3","created_at":"2026-07-05T11:34:51.840259+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01933","created_at":"2026-07-05T11:34:51.840259+00:00"},{"alias_kind":"pith_short_12","alias_value":"LFTWL7OJQV3Z","created_at":"2026-07-05T11:34:51.840259+00:00"},{"alias_kind":"pith_short_16","alias_value":"LFTWL7OJQV3Z5H6R","created_at":"2026-07-05T11:34:51.840259+00:00"},{"alias_kind":"pith_short_8","alias_value":"LFTWL7OJ","created_at":"2026-07-05T11:34:51.840259+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27367","citing_title":"SpatialBench: Is Your Spatial Foundation Model an All-Round Player?","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2508.10934","citing_title":"ViPE: Video Pose Engine for 3D Geometric Perception","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LFTWL7OJQV3Z5H6RGCN6HTNBKJ","json":"https://pith.science/pith/LFTWL7OJQV3Z5H6RGCN6HTNBKJ.json","graph_json":"https://pith.science/api/pith-number/LFTWL7OJQV3Z5H6RGCN6HTNBKJ/graph.json","events_json":"https://pith.science/api/pith-number/LFTWL7OJQV3Z5H6RGCN6HTNBKJ/events.json","paper":"https://pith.science/paper/LFTWL7OJ"},"agent_actions":{"view_html":"https://pith.science/pith/LFTWL7OJQV3Z5H6RGCN6HTNBKJ","download_json":"https://pith.science/pith/LFTWL7OJQV3Z5H6RGCN6HTNBKJ.json","view_paper":"https://pith.science/paper/LFTWL7OJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01933&json=true","fetch_graph":"https://pith.science/api/pith-number/LFTWL7OJQV3Z5H6RGCN6HTNBKJ/graph.json","fetch_events":"https://pith.science/api/pith-number/LFTWL7OJQV3Z5H6RGCN6HTNBKJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LFTWL7OJQV3Z5H6RGCN6HTNBKJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LFTWL7OJQV3Z5H6RGCN6HTNBKJ/action/storage_attestation","attest_author":"https://pith.science/pith/LFTWL7OJQV3Z5H6RGCN6HTNBKJ/action/author_attestation","sign_citation":"https://pith.science/pith/LFTWL7OJQV3Z5H6RGCN6HTNBKJ/action/citation_signature","submit_replication":"https://pith.science/pith/LFTWL7OJQV3Z5H6RGCN6HTNBKJ/action/replication_record"}},"created_at":"2026-07-05T11:34:51.840259+00:00","updated_at":"2026-07-05T11:34:51.840259+00:00"}