{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4LIR5NNB4C3HFZKMSFDSR4YIGQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8faae238dd5a3616041cd75bca85418ec3e92225805adb5b10e5f89c60da726c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-21T11:00:12Z","title_canon_sha256":"0deca4cd98c926280df2395f30b25088064e6880f8e9235ee617241301466271"},"schema_version":"1.0","source":{"id":"2503.17044","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.17044","created_at":"2026-07-05T10:36:56Z"},{"alias_kind":"arxiv_version","alias_value":"2503.17044v1","created_at":"2026-07-05T10:36:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17044","created_at":"2026-07-05T10:36:56Z"},{"alias_kind":"pith_short_12","alias_value":"4LIR5NNB4C3H","created_at":"2026-07-05T10:36:56Z"},{"alias_kind":"pith_short_16","alias_value":"4LIR5NNB4C3HFZKM","created_at":"2026-07-05T10:36:56Z"},{"alias_kind":"pith_short_8","alias_value":"4LIR5NNB","created_at":"2026-07-05T10:36:56Z"}],"graph_snapshots":[{"event_id":"sha256:3b01585029a7c0300c7300ad60b5b9aec020fbb57fdc0671b24fa8e53e97d7d8","target":"graph","created_at":"2026-07-05T10:36:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.17044/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Angela Dai, Chandan Yeshwanth, David Rozenberszki","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-21T11:00:12Z","title":"ExCap3D: Expressive 3D Scene Understanding via Object Captioning with Varying Detail"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17044","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fd5f821c1bba48bc4f11987c49bea9c92733ecac17d20617a084eb3a75a62c61","target":"record","created_at":"2026-07-05T10:36:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8faae238dd5a3616041cd75bca85418ec3e92225805adb5b10e5f89c60da726c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-21T11:00:12Z","title_canon_sha256":"0deca4cd98c926280df2395f30b25088064e6880f8e9235ee617241301466271"},"schema_version":"1.0","source":{"id":"2503.17044","kind":"arxiv","version":1}},"canonical_sha256":"e2d11eb5a1e0b672e54c914728f30834299a2c1ffb99ab4d7b32f14e3fd33306","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2d11eb5a1e0b672e54c914728f30834299a2c1ffb99ab4d7b32f14e3fd33306","first_computed_at":"2026-07-05T10:36:56.068083Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:36:56.068083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4Wtkf/iqUlBfRbnujzu52TM3WSmxNBRd6T7pRToRhfbbs14tJ+d/1EYG3WBDJoZf9HIA/TZR80fP3M4ifS4aDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:36:56.068564Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.17044","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd5f821c1bba48bc4f11987c49bea9c92733ecac17d20617a084eb3a75a62c61","sha256:3b01585029a7c0300c7300ad60b5b9aec020fbb57fdc0671b24fa8e53e97d7d8"],"state_sha256":"0b372ee8134ade8a5fdefb6cb597f6ccd10c4be8c23993c28b00768b211e9f5c"}