{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HZ3PAL3F2XGCYAIINVJBNCWEJ7","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":"36995ec1ecd3e70f92ed5a692eb0a4b5659cac0edad71a96af5047042156b768","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-12T17:59:03Z","title_canon_sha256":"f670d75e3bce2ba7414ff62e8b332c4c8e3d6dc97a674ae51cc617cce3d67f27"},"schema_version":"1.0","source":{"id":"2306.07279","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07279","created_at":"2026-07-05T06:21:17Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07279v2","created_at":"2026-07-05T06:21:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07279","created_at":"2026-07-05T06:21:17Z"},{"alias_kind":"pith_short_12","alias_value":"HZ3PAL3F2XGC","created_at":"2026-07-05T06:21:17Z"},{"alias_kind":"pith_short_16","alias_value":"HZ3PAL3F2XGCYAII","created_at":"2026-07-05T06:21:17Z"},{"alias_kind":"pith_short_8","alias_value":"HZ3PAL3F","created_at":"2026-07-05T06:21:17Z"}],"graph_snapshots":[{"event_id":"sha256:74f7fe6cdaa0436c8eca1b29354b3c16899be3ee3356bc260ad2a44c161ea8e0","target":"graph","created_at":"2026-07-05T06:21:17Z","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/2306.07279/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Cap3D, an automatic approach for generating descriptive text for 3D objects. This approach utilizes pretrained models from image captioning, image-text alignment, and LLM to consolidate captions from multiple views of a 3D asset, completely side-stepping the time-consuming and costly process of manual annotation. We apply Cap3D to the recently introduced large-scale 3D dataset, Objaverse, resulting in 660k 3D-text pairs. Our evaluation, conducted using 41k human annotations from the same dataset, demonstrates that Cap3D surpasses human-authored descriptions in terms of quality, co","authors_text":"Chris Rockwell, Honglak Lee, Justin Johnson, Tiange Luo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-12T17:59:03Z","title":"Scalable 3D Captioning with Pretrained Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07279","kind":"arxiv","version":2},"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:f804eff4cc5238eb96bac60d7bd430f5b62015f52665d73d5676cc4a79c4e6a7","target":"record","created_at":"2026-07-05T06:21:17Z","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":"36995ec1ecd3e70f92ed5a692eb0a4b5659cac0edad71a96af5047042156b768","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-12T17:59:03Z","title_canon_sha256":"f670d75e3bce2ba7414ff62e8b332c4c8e3d6dc97a674ae51cc617cce3d67f27"},"schema_version":"1.0","source":{"id":"2306.07279","kind":"arxiv","version":2}},"canonical_sha256":"3e76f02f65d5cc2c01086d52168ac44fc232b4855c225814583616fdfd2f84dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e76f02f65d5cc2c01086d52168ac44fc232b4855c225814583616fdfd2f84dd","first_computed_at":"2026-07-05T06:21:17.952293Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:21:17.952293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rmrx93dMfd9k5LktBW6YILM4vH0kteN2W4cSOlcyMOD0y6RLYlTkgSrczV/s4qQRb3DZxrzXHs9xMUf54eFuCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:21:17.952790Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.07279","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f804eff4cc5238eb96bac60d7bd430f5b62015f52665d73d5676cc4a79c4e6a7","sha256:74f7fe6cdaa0436c8eca1b29354b3c16899be3ee3356bc260ad2a44c161ea8e0"],"state_sha256":"974985859bcf2acc73722637f4d5ee7b2a42ddd025a896bd839c6fe9fba6f40d"}