{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UZOZ3ZIKVJY7VBHEEXBHRATOSV","short_pith_number":"pith:UZOZ3ZIK","schema_version":"1.0","canonical_sha256":"a65d9de50aaa71fa84e425c278826e95753ddc3081caa4560181f6c457e23461","source":{"kind":"arxiv","id":"2212.06250","version":2},"attestation_state":"computed","paper":{"title":"ScanEnts3D: Exploiting Phrase-to-3D-Object Correspondences for Improved Visio-Linguistic Models in 3D Scenes","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ahmed Abdelreheem, Hsin-Ying Lee, Kyle Olszewski, Panos Achlioptas, Peter Wonka","submitted_at":"2022-12-12T21:25:58Z","abstract_excerpt":"The two popular datasets ScanRefer [16] and ReferIt3D [3] connect natural language to real-world 3D data. In this paper, we curate a large-scale and complementary dataset extending both the aforementioned ones by associating all objects mentioned in a referential sentence to their underlying instances inside a 3D scene. Specifically, our Scan Entities in 3D (ScanEnts3D) dataset provides explicit correspondences between 369k objects across 84k natural referential sentences, covering 705 real-world scenes. Crucially, we show that by incorporating intuitive losses that enable learning from this n"},"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":"2212.06250","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-12T21:25:58Z","cross_cats_sorted":[],"title_canon_sha256":"8dd545610b5f1653e52284042f542dc5a4dd5e617aed9ea10bd31683c8db4756","abstract_canon_sha256":"bc1237d3babf5c399d4e8ea7bb3d6b1507bcda108b16c8c47f0875824380932e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:55.489198Z","signature_b64":"e+S2q1LpA9qWyq6bgsUiWWA0OJy3//Am4cqjHemLwjyUZxZ3tZrmaa5eEgcMlAmsfkRiLuBhb/qdZjwS8DvYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a65d9de50aaa71fa84e425c278826e95753ddc3081caa4560181f6c457e23461","last_reissued_at":"2026-07-05T05:56:55.488760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:55.488760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ScanEnts3D: Exploiting Phrase-to-3D-Object Correspondences for Improved Visio-Linguistic Models in 3D Scenes","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ahmed Abdelreheem, Hsin-Ying Lee, Kyle Olszewski, Panos Achlioptas, Peter Wonka","submitted_at":"2022-12-12T21:25:58Z","abstract_excerpt":"The two popular datasets ScanRefer [16] and ReferIt3D [3] connect natural language to real-world 3D data. In this paper, we curate a large-scale and complementary dataset extending both the aforementioned ones by associating all objects mentioned in a referential sentence to their underlying instances inside a 3D scene. Specifically, our Scan Entities in 3D (ScanEnts3D) dataset provides explicit correspondences between 369k objects across 84k natural referential sentences, covering 705 real-world scenes. Crucially, we show that by incorporating intuitive losses that enable learning from this n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.06250","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/2212.06250/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":"2212.06250","created_at":"2026-07-05T05:56:55.488818+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.06250v2","created_at":"2026-07-05T05:56:55.488818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.06250","created_at":"2026-07-05T05:56:55.488818+00:00"},{"alias_kind":"pith_short_12","alias_value":"UZOZ3ZIKVJY7","created_at":"2026-07-05T05:56:55.488818+00:00"},{"alias_kind":"pith_short_16","alias_value":"UZOZ3ZIKVJY7VBHE","created_at":"2026-07-05T05:56:55.488818+00:00"},{"alias_kind":"pith_short_8","alias_value":"UZOZ3ZIK","created_at":"2026-07-05T05:56:55.488818+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.01366","citing_title":"ViGiL3D: A Linguistically Diverse Dataset for 3D Visual Grounding","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UZOZ3ZIKVJY7VBHEEXBHRATOSV","json":"https://pith.science/pith/UZOZ3ZIKVJY7VBHEEXBHRATOSV.json","graph_json":"https://pith.science/api/pith-number/UZOZ3ZIKVJY7VBHEEXBHRATOSV/graph.json","events_json":"https://pith.science/api/pith-number/UZOZ3ZIKVJY7VBHEEXBHRATOSV/events.json","paper":"https://pith.science/paper/UZOZ3ZIK"},"agent_actions":{"view_html":"https://pith.science/pith/UZOZ3ZIKVJY7VBHEEXBHRATOSV","download_json":"https://pith.science/pith/UZOZ3ZIKVJY7VBHEEXBHRATOSV.json","view_paper":"https://pith.science/paper/UZOZ3ZIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.06250&json=true","fetch_graph":"https://pith.science/api/pith-number/UZOZ3ZIKVJY7VBHEEXBHRATOSV/graph.json","fetch_events":"https://pith.science/api/pith-number/UZOZ3ZIKVJY7VBHEEXBHRATOSV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UZOZ3ZIKVJY7VBHEEXBHRATOSV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UZOZ3ZIKVJY7VBHEEXBHRATOSV/action/storage_attestation","attest_author":"https://pith.science/pith/UZOZ3ZIKVJY7VBHEEXBHRATOSV/action/author_attestation","sign_citation":"https://pith.science/pith/UZOZ3ZIKVJY7VBHEEXBHRATOSV/action/citation_signature","submit_replication":"https://pith.science/pith/UZOZ3ZIKVJY7VBHEEXBHRATOSV/action/replication_record"}},"created_at":"2026-07-05T05:56:55.488818+00:00","updated_at":"2026-07-05T05:56:55.488818+00:00"}