{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EUSZVBPIXAKGOLTT5GZ7TYFNK3","short_pith_number":"pith:EUSZVBPI","schema_version":"1.0","canonical_sha256":"25259a85e8b814672e73e9b3f9e0ad56c239d9bdac3da80c4d81ca6ccf36ac20","source":{"kind":"arxiv","id":"2303.13483","version":1},"attestation_state":"computed","paper":{"title":"NS3D: Neuro-Symbolic Grounding of 3D Objects and Relations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiajun Wu, Jiayuan Mao, Joy Hsu","submitted_at":"2023-03-23T17:50:40Z","abstract_excerpt":"Grounding object properties and relations in 3D scenes is a prerequisite for a wide range of artificial intelligence tasks, such as visually grounded dialogues and embodied manipulation. However, the variability of the 3D domain induces two fundamental challenges: 1) the expense of labeling and 2) the complexity of 3D grounded language. Hence, essential desiderata for models are to be data-efficient, generalize to different data distributions and tasks with unseen semantic forms, as well as ground complex language semantics (e.g., view-point anchoring and multi-object reference). To address th"},"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":"2303.13483","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-23T17:50:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2085fc3ac482f6fcb8d090cde21702a88ed3e291c2eb86b169543c466ad42361","abstract_canon_sha256":"8283306a8ad5112848ae5cb0fbc91deb88745a131540daecd17d23832dc8baba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:02.826605Z","signature_b64":"k/dSV+YBNCAW3BZaFyeAGB0FodTO8d4KAMkH2yyOjjgPP2xO1oqQHNCncbjmOdAuRMm3cgeBuZF4mSMbt7HPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25259a85e8b814672e73e9b3f9e0ad56c239d9bdac3da80c4d81ca6ccf36ac20","last_reissued_at":"2026-07-05T05:54:02.826148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:02.826148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NS3D: Neuro-Symbolic Grounding of 3D Objects and Relations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiajun Wu, Jiayuan Mao, Joy Hsu","submitted_at":"2023-03-23T17:50:40Z","abstract_excerpt":"Grounding object properties and relations in 3D scenes is a prerequisite for a wide range of artificial intelligence tasks, such as visually grounded dialogues and embodied manipulation. However, the variability of the 3D domain induces two fundamental challenges: 1) the expense of labeling and 2) the complexity of 3D grounded language. Hence, essential desiderata for models are to be data-efficient, generalize to different data distributions and tasks with unseen semantic forms, as well as ground complex language semantics (e.g., view-point anchoring and multi-object reference). To address th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.13483","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/2303.13483/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":"2303.13483","created_at":"2026-07-05T05:54:02.826213+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.13483v1","created_at":"2026-07-05T05:54:02.826213+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.13483","created_at":"2026-07-05T05:54:02.826213+00:00"},{"alias_kind":"pith_short_12","alias_value":"EUSZVBPIXAKG","created_at":"2026-07-05T05:54:02.826213+00:00"},{"alias_kind":"pith_short_16","alias_value":"EUSZVBPIXAKGOLTT","created_at":"2026-07-05T05:54:02.826213+00:00"},{"alias_kind":"pith_short_8","alias_value":"EUSZVBPI","created_at":"2026-07-05T05:54:02.826213+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31144","citing_title":"A Modular Vision-Language-Action Robotics Framework for Indoor Environments","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EUSZVBPIXAKGOLTT5GZ7TYFNK3","json":"https://pith.science/pith/EUSZVBPIXAKGOLTT5GZ7TYFNK3.json","graph_json":"https://pith.science/api/pith-number/EUSZVBPIXAKGOLTT5GZ7TYFNK3/graph.json","events_json":"https://pith.science/api/pith-number/EUSZVBPIXAKGOLTT5GZ7TYFNK3/events.json","paper":"https://pith.science/paper/EUSZVBPI"},"agent_actions":{"view_html":"https://pith.science/pith/EUSZVBPIXAKGOLTT5GZ7TYFNK3","download_json":"https://pith.science/pith/EUSZVBPIXAKGOLTT5GZ7TYFNK3.json","view_paper":"https://pith.science/paper/EUSZVBPI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.13483&json=true","fetch_graph":"https://pith.science/api/pith-number/EUSZVBPIXAKGOLTT5GZ7TYFNK3/graph.json","fetch_events":"https://pith.science/api/pith-number/EUSZVBPIXAKGOLTT5GZ7TYFNK3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EUSZVBPIXAKGOLTT5GZ7TYFNK3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EUSZVBPIXAKGOLTT5GZ7TYFNK3/action/storage_attestation","attest_author":"https://pith.science/pith/EUSZVBPIXAKGOLTT5GZ7TYFNK3/action/author_attestation","sign_citation":"https://pith.science/pith/EUSZVBPIXAKGOLTT5GZ7TYFNK3/action/citation_signature","submit_replication":"https://pith.science/pith/EUSZVBPIXAKGOLTT5GZ7TYFNK3/action/replication_record"}},"created_at":"2026-07-05T05:54:02.826213+00:00","updated_at":"2026-07-05T05:54:02.826213+00:00"}