{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4LIR5NNB4C3HFZKMSFDSR4YIGQ","short_pith_number":"pith:4LIR5NNB","schema_version":"1.0","canonical_sha256":"e2d11eb5a1e0b672e54c914728f30834299a2c1ffb99ab4d7b32f14e3fd33306","source":{"kind":"arxiv","id":"2503.17044","version":1},"attestation_state":"computed","paper":{"title":"ExCap3D: Expressive 3D Scene Understanding via Object Captioning with Varying Detail","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angela Dai, Chandan Yeshwanth, David Rozenberszki","submitted_at":"2025-03-21T11:00:12Z","abstract_excerpt":"Generating text descriptions of objects in 3D indoor scenes is an important building block of embodied understanding. Existing methods do this by describing objects at a single level of detail, which often does not capture fine-grained details such as varying textures, materials, and shapes of the parts of objects. We propose the task of expressive 3D captioning: given an input 3D scene, describe objects at multiple levels of detail: a high-level object description, and a low-level description of the properties of its parts. To produce such captions, we present ExCap3D, an expressive 3D captio"},"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":"2503.17044","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-21T11:00:12Z","cross_cats_sorted":[],"title_canon_sha256":"0deca4cd98c926280df2395f30b25088064e6880f8e9235ee617241301466271","abstract_canon_sha256":"8faae238dd5a3616041cd75bca85418ec3e92225805adb5b10e5f89c60da726c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:56.068564Z","signature_b64":"4Wtkf/iqUlBfRbnujzu52TM3WSmxNBRd6T7pRToRhfbbs14tJ+d/1EYG3WBDJoZf9HIA/TZR80fP3M4ifS4aDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2d11eb5a1e0b672e54c914728f30834299a2c1ffb99ab4d7b32f14e3fd33306","last_reissued_at":"2026-07-05T10:36:56.068083Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:56.068083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ExCap3D: Expressive 3D Scene Understanding via Object Captioning with Varying Detail","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angela Dai, Chandan Yeshwanth, David Rozenberszki","submitted_at":"2025-03-21T11:00:12Z","abstract_excerpt":"Generating text descriptions of objects in 3D indoor scenes is an important building block of embodied understanding. Existing methods do this by describing objects at a single level of detail, which often does not capture fine-grained details such as varying textures, materials, and shapes of the parts of objects. We propose the task of expressive 3D captioning: given an input 3D scene, describe objects at multiple levels of detail: a high-level object description, and a low-level description of the properties of its parts. To produce such captions, we present ExCap3D, an expressive 3D captio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17044","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/2503.17044/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":"2503.17044","created_at":"2026-07-05T10:36:56.068137+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.17044v1","created_at":"2026-07-05T10:36:56.068137+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17044","created_at":"2026-07-05T10:36:56.068137+00:00"},{"alias_kind":"pith_short_12","alias_value":"4LIR5NNB4C3H","created_at":"2026-07-05T10:36:56.068137+00:00"},{"alias_kind":"pith_short_16","alias_value":"4LIR5NNB4C3HFZKM","created_at":"2026-07-05T10:36:56.068137+00:00"},{"alias_kind":"pith_short_8","alias_value":"4LIR5NNB","created_at":"2026-07-05T10:36:56.068137+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.07781","citing_title":"SURPRISE3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4LIR5NNB4C3HFZKMSFDSR4YIGQ","json":"https://pith.science/pith/4LIR5NNB4C3HFZKMSFDSR4YIGQ.json","graph_json":"https://pith.science/api/pith-number/4LIR5NNB4C3HFZKMSFDSR4YIGQ/graph.json","events_json":"https://pith.science/api/pith-number/4LIR5NNB4C3HFZKMSFDSR4YIGQ/events.json","paper":"https://pith.science/paper/4LIR5NNB"},"agent_actions":{"view_html":"https://pith.science/pith/4LIR5NNB4C3HFZKMSFDSR4YIGQ","download_json":"https://pith.science/pith/4LIR5NNB4C3HFZKMSFDSR4YIGQ.json","view_paper":"https://pith.science/paper/4LIR5NNB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.17044&json=true","fetch_graph":"https://pith.science/api/pith-number/4LIR5NNB4C3HFZKMSFDSR4YIGQ/graph.json","fetch_events":"https://pith.science/api/pith-number/4LIR5NNB4C3HFZKMSFDSR4YIGQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4LIR5NNB4C3HFZKMSFDSR4YIGQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4LIR5NNB4C3HFZKMSFDSR4YIGQ/action/storage_attestation","attest_author":"https://pith.science/pith/4LIR5NNB4C3HFZKMSFDSR4YIGQ/action/author_attestation","sign_citation":"https://pith.science/pith/4LIR5NNB4C3HFZKMSFDSR4YIGQ/action/citation_signature","submit_replication":"https://pith.science/pith/4LIR5NNB4C3HFZKMSFDSR4YIGQ/action/replication_record"}},"created_at":"2026-07-05T10:36:56.068137+00:00","updated_at":"2026-07-05T10:36:56.068137+00:00"}