{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XBL6S4L4LTVFDD63R55K5F6B2C","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":"be9da03324afa0fc9f98d76c0fe01c3cf3cd7d02e74f841ec3de7d8d162b7b64","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-22T13:07:37Z","title_canon_sha256":"21146a96b7445da0e4dfc85394b08a340f2da9f7fab520672d127f9319111310"},"schema_version":"1.0","source":{"id":"2204.10688","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.10688","created_at":"2026-07-05T04:17:00Z"},{"alias_kind":"arxiv_version","alias_value":"2204.10688v1","created_at":"2026-07-05T04:17:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.10688","created_at":"2026-07-05T04:17:00Z"},{"alias_kind":"pith_short_12","alias_value":"XBL6S4L4LTVF","created_at":"2026-07-05T04:17:00Z"},{"alias_kind":"pith_short_16","alias_value":"XBL6S4L4LTVFDD63","created_at":"2026-07-05T04:17:00Z"},{"alias_kind":"pith_short_8","alias_value":"XBL6S4L4","created_at":"2026-07-05T04:17:00Z"}],"graph_snapshots":[{"event_id":"sha256:32d5947024051906bca8b3f4ba36612f45eda027ffd5c8b299c8433f22117d0f","target":"graph","created_at":"2026-07-05T04:17:00Z","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/2204.10688/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dense captioning in 3D point clouds is an emerging vision-and-language task involving object-level 3D scene understanding. Apart from coarse semantic class prediction and bounding box regression as in traditional 3D object detection, 3D dense captioning aims at producing a further and finer instance-level label of natural language description on visual appearance and spatial relations for each scene object of interest. To detect and describe objects in a scene, following the spirit of neural machine translation, we propose a transformer-based encoder-decoder architecture, namely SpaCap3D, to t","authors_text":"Chaoyi Zhang, Heng Wang, Jianhui Yu, Weidong Cai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-22T13:07:37Z","title":"Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.10688","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:da10806b66f059533e538e5c28dbd71031f714f5a5f43ffdd1daef8a9d7e5e53","target":"record","created_at":"2026-07-05T04:17:00Z","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":"be9da03324afa0fc9f98d76c0fe01c3cf3cd7d02e74f841ec3de7d8d162b7b64","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-22T13:07:37Z","title_canon_sha256":"21146a96b7445da0e4dfc85394b08a340f2da9f7fab520672d127f9319111310"},"schema_version":"1.0","source":{"id":"2204.10688","kind":"arxiv","version":1}},"canonical_sha256":"b857e9717c5cea518fdb8f7aae97c1d0a66421fd8a5f0af1dbf796907e24f560","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b857e9717c5cea518fdb8f7aae97c1d0a66421fd8a5f0af1dbf796907e24f560","first_computed_at":"2026-07-05T04:17:00.044724Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:17:00.044724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S6a4mNDsqrbLbwwk0SREQitRw+IvOXiSDyvlef+D970PlL7W5XgXe9jBvbjeGklFn5nB9jxRN1Xr4QQuDiO4CA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:17:00.045196Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.10688","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da10806b66f059533e538e5c28dbd71031f714f5a5f43ffdd1daef8a9d7e5e53","sha256:32d5947024051906bca8b3f4ba36612f45eda027ffd5c8b299c8433f22117d0f"],"state_sha256":"ed5f6cb4a8a9bb587e092471ae36e2eda4ebf0897749e72c3f968fbd6f330b1e"}