{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WRPSK7TPYYZVALRVHENJAEHVSZ","short_pith_number":"pith:WRPSK7TP","schema_version":"1.0","canonical_sha256":"b45f257e6fc633502e35391a9010f596474c2ed797a6cb7612103444d5dc7f59","source":{"kind":"arxiv","id":"2403.13556","version":2},"attestation_state":"computed","paper":{"title":"Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environments","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Djamahl Etchegaray, Tatsuya Harada, Yadan Luo, Zi Huang","submitted_at":"2024-03-20T12:51:30Z","abstract_excerpt":"In this work, we tackle the limitations of current LiDAR-based 3D object detection systems, which are hindered by a restricted class vocabulary and the high costs associated with annotating new object classes. Our exploration of open-vocabulary (OV) learning in urban environments aims to capture novel instances using pre-trained vision-language models (VLMs) with multi-sensor data. We design and benchmark a set of four potential solutions as baselines, categorizing them into either top-down or bottom-up approaches based on their input data strategies. While effective, these methods exhibit cer"},"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":"2403.13556","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T12:51:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8f898966ea0063c7f93d6b3801f6e998037213bab7b271c2f77f085da6b46ac9","abstract_canon_sha256":"7cac3f6399757d5b4788a5d68bc0e51ea736e6d6c4701278d95ae432b5ec6d95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:09.417534Z","signature_b64":"p9pcRavpQ0YvcHq4FhEY6K0ocf6/BBVGLIQ1kVIkAwQ6ryhO1/WIsM7tK3oLmTcRzJSzaUqjxaFkYZnVCwK+Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b45f257e6fc633502e35391a9010f596474c2ed797a6cb7612103444d5dc7f59","last_reissued_at":"2026-07-05T08:43:09.417059Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:09.417059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environments","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Djamahl Etchegaray, Tatsuya Harada, Yadan Luo, Zi Huang","submitted_at":"2024-03-20T12:51:30Z","abstract_excerpt":"In this work, we tackle the limitations of current LiDAR-based 3D object detection systems, which are hindered by a restricted class vocabulary and the high costs associated with annotating new object classes. Our exploration of open-vocabulary (OV) learning in urban environments aims to capture novel instances using pre-trained vision-language models (VLMs) with multi-sensor data. We design and benchmark a set of four potential solutions as baselines, categorizing them into either top-down or bottom-up approaches based on their input data strategies. While effective, these methods exhibit cer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13556","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/2403.13556/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":"2403.13556","created_at":"2026-07-05T08:43:09.417117+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.13556v2","created_at":"2026-07-05T08:43:09.417117+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13556","created_at":"2026-07-05T08:43:09.417117+00:00"},{"alias_kind":"pith_short_12","alias_value":"WRPSK7TPYYZV","created_at":"2026-07-05T08:43:09.417117+00:00"},{"alias_kind":"pith_short_16","alias_value":"WRPSK7TPYYZVALRV","created_at":"2026-07-05T08:43:09.417117+00:00"},{"alias_kind":"pith_short_8","alias_value":"WRPSK7TP","created_at":"2026-07-05T08:43:09.417117+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.16812","citing_title":"Towards Open-Vocabulary Multimodal 3D Object Detection with Attributes","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WRPSK7TPYYZVALRVHENJAEHVSZ","json":"https://pith.science/pith/WRPSK7TPYYZVALRVHENJAEHVSZ.json","graph_json":"https://pith.science/api/pith-number/WRPSK7TPYYZVALRVHENJAEHVSZ/graph.json","events_json":"https://pith.science/api/pith-number/WRPSK7TPYYZVALRVHENJAEHVSZ/events.json","paper":"https://pith.science/paper/WRPSK7TP"},"agent_actions":{"view_html":"https://pith.science/pith/WRPSK7TPYYZVALRVHENJAEHVSZ","download_json":"https://pith.science/pith/WRPSK7TPYYZVALRVHENJAEHVSZ.json","view_paper":"https://pith.science/paper/WRPSK7TP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.13556&json=true","fetch_graph":"https://pith.science/api/pith-number/WRPSK7TPYYZVALRVHENJAEHVSZ/graph.json","fetch_events":"https://pith.science/api/pith-number/WRPSK7TPYYZVALRVHENJAEHVSZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WRPSK7TPYYZVALRVHENJAEHVSZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WRPSK7TPYYZVALRVHENJAEHVSZ/action/storage_attestation","attest_author":"https://pith.science/pith/WRPSK7TPYYZVALRVHENJAEHVSZ/action/author_attestation","sign_citation":"https://pith.science/pith/WRPSK7TPYYZVALRVHENJAEHVSZ/action/citation_signature","submit_replication":"https://pith.science/pith/WRPSK7TPYYZVALRVHENJAEHVSZ/action/replication_record"}},"created_at":"2026-07-05T08:43:09.417117+00:00","updated_at":"2026-07-05T08:43:09.417117+00:00"}