{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2WZDRTNNTXRZTBC6VRLVPQXEVH","short_pith_number":"pith:2WZDRTNN","schema_version":"1.0","canonical_sha256":"d5b238cdad9de399845eac5757c2e4a9efae3642dbcc5c6b2869a290b2b93d09","source":{"kind":"arxiv","id":"2401.09413","version":1},"attestation_state":"computed","paper":{"title":"POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrei Bursuc, Antonin Vobecky, David Hurych, Josef Sivic, Oriane Sim\\'eoni, Patrick P\\'erez, Spyros Gidaris","submitted_at":"2024-01-17T18:51:53Z","abstract_excerpt":"We describe an approach to predict open-vocabulary 3D semantic voxel occupancy map from input 2D images with the objective of enabling 3D grounding, segmentation and retrieval of free-form language queries. This is a challenging problem because of the 2D-3D ambiguity and the open-vocabulary nature of the target tasks, where obtaining annotated training data in 3D is difficult. The contributions of this work are three-fold. First, we design a new model architecture for open-vocabulary 3D semantic occupancy prediction. The architecture consists of a 2D-3D encoder together with occupancy predicti"},"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":"2401.09413","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-17T18:51:53Z","cross_cats_sorted":[],"title_canon_sha256":"24eaaea33fe6773b61af88dea61a2e228ecbe7d8778ba7bf0300756707f20bf3","abstract_canon_sha256":"6a97c935b9b0632b3789183563ba7758df35c90aeeaa720cde40a789e6c91238"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:34:43.543660Z","signature_b64":"PfCmA7O0C4RKQwHbkU0yG0grAPe34J9hudpcTaKWeIFx4/U6Dn2AHjamQlI/QO5QATd4wKI+GCh/v5nAVkWTDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5b238cdad9de399845eac5757c2e4a9efae3642dbcc5c6b2869a290b2b93d09","last_reissued_at":"2026-07-05T07:34:43.543243Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:34:43.543243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrei Bursuc, Antonin Vobecky, David Hurych, Josef Sivic, Oriane Sim\\'eoni, Patrick P\\'erez, Spyros Gidaris","submitted_at":"2024-01-17T18:51:53Z","abstract_excerpt":"We describe an approach to predict open-vocabulary 3D semantic voxel occupancy map from input 2D images with the objective of enabling 3D grounding, segmentation and retrieval of free-form language queries. This is a challenging problem because of the 2D-3D ambiguity and the open-vocabulary nature of the target tasks, where obtaining annotated training data in 3D is difficult. The contributions of this work are three-fold. First, we design a new model architecture for open-vocabulary 3D semantic occupancy prediction. The architecture consists of a 2D-3D encoder together with occupancy predicti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.09413","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/2401.09413/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":"2401.09413","created_at":"2026-07-05T07:34:43.543297+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.09413v1","created_at":"2026-07-05T07:34:43.543297+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09413","created_at":"2026-07-05T07:34:43.543297+00:00"},{"alias_kind":"pith_short_12","alias_value":"2WZDRTNNTXRZ","created_at":"2026-07-05T07:34:43.543297+00:00"},{"alias_kind":"pith_short_16","alias_value":"2WZDRTNNTXRZTBC6","created_at":"2026-07-05T07:34:43.543297+00:00"},{"alias_kind":"pith_short_8","alias_value":"2WZDRTNN","created_at":"2026-07-05T07:34:43.543297+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13460","citing_title":"VISA: VLM-Guided Instance Semantic Auditing for 3D Occupancy World Models","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2WZDRTNNTXRZTBC6VRLVPQXEVH","json":"https://pith.science/pith/2WZDRTNNTXRZTBC6VRLVPQXEVH.json","graph_json":"https://pith.science/api/pith-number/2WZDRTNNTXRZTBC6VRLVPQXEVH/graph.json","events_json":"https://pith.science/api/pith-number/2WZDRTNNTXRZTBC6VRLVPQXEVH/events.json","paper":"https://pith.science/paper/2WZDRTNN"},"agent_actions":{"view_html":"https://pith.science/pith/2WZDRTNNTXRZTBC6VRLVPQXEVH","download_json":"https://pith.science/pith/2WZDRTNNTXRZTBC6VRLVPQXEVH.json","view_paper":"https://pith.science/paper/2WZDRTNN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.09413&json=true","fetch_graph":"https://pith.science/api/pith-number/2WZDRTNNTXRZTBC6VRLVPQXEVH/graph.json","fetch_events":"https://pith.science/api/pith-number/2WZDRTNNTXRZTBC6VRLVPQXEVH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2WZDRTNNTXRZTBC6VRLVPQXEVH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2WZDRTNNTXRZTBC6VRLVPQXEVH/action/storage_attestation","attest_author":"https://pith.science/pith/2WZDRTNNTXRZTBC6VRLVPQXEVH/action/author_attestation","sign_citation":"https://pith.science/pith/2WZDRTNNTXRZTBC6VRLVPQXEVH/action/citation_signature","submit_replication":"https://pith.science/pith/2WZDRTNNTXRZTBC6VRLVPQXEVH/action/replication_record"}},"created_at":"2026-07-05T07:34:43.543297+00:00","updated_at":"2026-07-05T07:34:43.543297+00:00"}