{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OPSRKU56PSPGXSVR4AOURF2PE5","short_pith_number":"pith:OPSRKU56","schema_version":"1.0","canonical_sha256":"73e51553be7c9e6bcab1e01d48974f27762edd462078ef692facba39cd7c0c36","source":{"kind":"arxiv","id":"2506.02112","version":2},"attestation_state":"computed","paper":{"title":"SAB3R: Semantic-Augmented Backbone in 3D Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianing Yang, Joyce Chai, Sihan Xu, Tian Xia, Xuweiyi Chen, Zezhou Cheng","submitted_at":"2025-06-02T18:00:04Z","abstract_excerpt":"We introduce a new task, Map and Locate, which unifies the traditionally distinct objectives of open-vocabulary segmentation - detecting and segmenting object instances based on natural language queries - and 3D reconstruction, the process of estimating a scene's 3D structure from visual inputs. Specifically, Map and Locate involves generating a point cloud from an unposed video and segmenting object instances based on open-vocabulary queries. This task serves as a critical step toward real-world embodied AI applications and introduces a practical task that bridges reconstruction, recognition "},"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":"2506.02112","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T18:00:04Z","cross_cats_sorted":[],"title_canon_sha256":"87b08eca9c3d9943750ffe296d26aa77c745819a3d91eac2bbaafc0fad7198e6","abstract_canon_sha256":"f4e995f47e6ceec72ab1df98d24b274a93ce719be737d83078296afc6b46cbb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:21.959497Z","signature_b64":"Hzv1lREZzUftISUNbS+FYdlGTRRsYQBEAPPfnWwEJrLv98/3KybUqysoyYB9J4cRiI06t3CTAlz6uRbWclobAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73e51553be7c9e6bcab1e01d48974f27762edd462078ef692facba39cd7c0c36","last_reissued_at":"2026-07-05T11:15:21.959026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:21.959026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAB3R: Semantic-Augmented Backbone in 3D Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianing Yang, Joyce Chai, Sihan Xu, Tian Xia, Xuweiyi Chen, Zezhou Cheng","submitted_at":"2025-06-02T18:00:04Z","abstract_excerpt":"We introduce a new task, Map and Locate, which unifies the traditionally distinct objectives of open-vocabulary segmentation - detecting and segmenting object instances based on natural language queries - and 3D reconstruction, the process of estimating a scene's 3D structure from visual inputs. Specifically, Map and Locate involves generating a point cloud from an unposed video and segmenting object instances based on open-vocabulary queries. This task serves as a critical step toward real-world embodied AI applications and introduces a practical task that bridges reconstruction, recognition "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02112","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/2506.02112/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":"2506.02112","created_at":"2026-07-05T11:15:21.959085+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02112v2","created_at":"2026-07-05T11:15:21.959085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02112","created_at":"2026-07-05T11:15:21.959085+00:00"},{"alias_kind":"pith_short_12","alias_value":"OPSRKU56PSPG","created_at":"2026-07-05T11:15:21.959085+00:00"},{"alias_kind":"pith_short_16","alias_value":"OPSRKU56PSPGXSVR","created_at":"2026-07-05T11:15:21.959085+00:00"},{"alias_kind":"pith_short_8","alias_value":"OPSRKU56","created_at":"2026-07-05T11:15:21.959085+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.14307","citing_title":"Pano3D: Unified 3D Reconstruction and Panoptic Segmentation","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OPSRKU56PSPGXSVR4AOURF2PE5","json":"https://pith.science/pith/OPSRKU56PSPGXSVR4AOURF2PE5.json","graph_json":"https://pith.science/api/pith-number/OPSRKU56PSPGXSVR4AOURF2PE5/graph.json","events_json":"https://pith.science/api/pith-number/OPSRKU56PSPGXSVR4AOURF2PE5/events.json","paper":"https://pith.science/paper/OPSRKU56"},"agent_actions":{"view_html":"https://pith.science/pith/OPSRKU56PSPGXSVR4AOURF2PE5","download_json":"https://pith.science/pith/OPSRKU56PSPGXSVR4AOURF2PE5.json","view_paper":"https://pith.science/paper/OPSRKU56","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02112&json=true","fetch_graph":"https://pith.science/api/pith-number/OPSRKU56PSPGXSVR4AOURF2PE5/graph.json","fetch_events":"https://pith.science/api/pith-number/OPSRKU56PSPGXSVR4AOURF2PE5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OPSRKU56PSPGXSVR4AOURF2PE5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OPSRKU56PSPGXSVR4AOURF2PE5/action/storage_attestation","attest_author":"https://pith.science/pith/OPSRKU56PSPGXSVR4AOURF2PE5/action/author_attestation","sign_citation":"https://pith.science/pith/OPSRKU56PSPGXSVR4AOURF2PE5/action/citation_signature","submit_replication":"https://pith.science/pith/OPSRKU56PSPGXSVR4AOURF2PE5/action/replication_record"}},"created_at":"2026-07-05T11:15:21.959085+00:00","updated_at":"2026-07-05T11:15:21.959085+00:00"}