{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3RD6RTFNCRLSBQKJO4TQUFXYKM","short_pith_number":"pith:3RD6RTFN","schema_version":"1.0","canonical_sha256":"dc47e8ccad145720c14977270a16f85305d9f1104551b89143b5b4bd5249d091","source":{"kind":"arxiv","id":"2301.05372","version":1},"attestation_state":"computed","paper":{"title":"Text to Point Cloud Localization with Relation-Enhanced Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangzhi Wang, Hehe Fan, Mohan Kankanhalli","submitted_at":"2023-01-13T02:58:49Z","abstract_excerpt":"Automatically localizing a position based on a few natural language instructions is essential for future robots to communicate and collaborate with humans. To approach this goal, we focus on the text-to-point-cloud cross-modal localization problem. Given a textual query, it aims to identify the described location from city-scale point clouds. The task involves two challenges. 1) In city-scale point clouds, similar ambient instances may exist in several locations. Searching each location in a huge point cloud with only instances as guidance may lead to less discriminative signals and incorrect "},"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":"2301.05372","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-13T02:58:49Z","cross_cats_sorted":[],"title_canon_sha256":"1139c18051336a6105a96aca064b8c2b8ffb83275d8669f1fd250aebcb4a4a5c","abstract_canon_sha256":"03d4e95598bde60024966355f354ce02264dbf7bc62e66c2cbcdab776fd0a8c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:32:52.130896Z","signature_b64":"MXGqQXOX5VmcOVcB3hK7Gpl5qC1qrvD8qTcKW37/EKomFKblVkkIIlQ1KwZeRK2Wm2GOm8AOGjkST1sH907kBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc47e8ccad145720c14977270a16f85305d9f1104551b89143b5b4bd5249d091","last_reissued_at":"2026-07-05T05:32:52.130438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:32:52.130438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text to Point Cloud Localization with Relation-Enhanced Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangzhi Wang, Hehe Fan, Mohan Kankanhalli","submitted_at":"2023-01-13T02:58:49Z","abstract_excerpt":"Automatically localizing a position based on a few natural language instructions is essential for future robots to communicate and collaborate with humans. To approach this goal, we focus on the text-to-point-cloud cross-modal localization problem. Given a textual query, it aims to identify the described location from city-scale point clouds. The task involves two challenges. 1) In city-scale point clouds, similar ambient instances may exist in several locations. Searching each location in a huge point cloud with only instances as guidance may lead to less discriminative signals and incorrect "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.05372","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/2301.05372/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":"2301.05372","created_at":"2026-07-05T05:32:52.130493+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.05372v1","created_at":"2026-07-05T05:32:52.130493+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.05372","created_at":"2026-07-05T05:32:52.130493+00:00"},{"alias_kind":"pith_short_12","alias_value":"3RD6RTFNCRLS","created_at":"2026-07-05T05:32:52.130493+00:00"},{"alias_kind":"pith_short_16","alias_value":"3RD6RTFNCRLSBQKJ","created_at":"2026-07-05T05:32:52.130493+00:00"},{"alias_kind":"pith_short_8","alias_value":"3RD6RTFN","created_at":"2026-07-05T05:32:52.130493+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.12079","citing_title":"UniLoc: Towards Universal Place Recognition Using Any Single Modality","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3RD6RTFNCRLSBQKJO4TQUFXYKM","json":"https://pith.science/pith/3RD6RTFNCRLSBQKJO4TQUFXYKM.json","graph_json":"https://pith.science/api/pith-number/3RD6RTFNCRLSBQKJO4TQUFXYKM/graph.json","events_json":"https://pith.science/api/pith-number/3RD6RTFNCRLSBQKJO4TQUFXYKM/events.json","paper":"https://pith.science/paper/3RD6RTFN"},"agent_actions":{"view_html":"https://pith.science/pith/3RD6RTFNCRLSBQKJO4TQUFXYKM","download_json":"https://pith.science/pith/3RD6RTFNCRLSBQKJO4TQUFXYKM.json","view_paper":"https://pith.science/paper/3RD6RTFN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.05372&json=true","fetch_graph":"https://pith.science/api/pith-number/3RD6RTFNCRLSBQKJO4TQUFXYKM/graph.json","fetch_events":"https://pith.science/api/pith-number/3RD6RTFNCRLSBQKJO4TQUFXYKM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3RD6RTFNCRLSBQKJO4TQUFXYKM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3RD6RTFNCRLSBQKJO4TQUFXYKM/action/storage_attestation","attest_author":"https://pith.science/pith/3RD6RTFNCRLSBQKJO4TQUFXYKM/action/author_attestation","sign_citation":"https://pith.science/pith/3RD6RTFNCRLSBQKJO4TQUFXYKM/action/citation_signature","submit_replication":"https://pith.science/pith/3RD6RTFNCRLSBQKJO4TQUFXYKM/action/replication_record"}},"created_at":"2026-07-05T05:32:52.130493+00:00","updated_at":"2026-07-05T05:32:52.130493+00:00"}