{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:R4HYQE7MJUNDQ3S3UENOQXEKFW","short_pith_number":"pith:R4HYQE7M","canonical_record":{"source":{"id":"2309.02999","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-06T13:43:27Z","cross_cats_sorted":[],"title_canon_sha256":"604a014c1a8cea5cac8a4c7c20c7ac9b4c7049764934455e7f43957be2a90c4e","abstract_canon_sha256":"eafb24f5b58026e48ffe4198cfa1513b21233f131b4500d7e166fe1c268b2c34"},"schema_version":"1.0"},"canonical_sha256":"8f0f8813ec4d1a386e5ba11ae85c8a2dbc5012ac4d5b688d1335b83b1fb5aae1","source":{"kind":"arxiv","id":"2309.02999","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.02999","created_at":"2026-07-05T06:48:19Z"},{"alias_kind":"arxiv_version","alias_value":"2309.02999v1","created_at":"2026-07-05T06:48:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.02999","created_at":"2026-07-05T06:48:19Z"},{"alias_kind":"pith_short_12","alias_value":"R4HYQE7MJUND","created_at":"2026-07-05T06:48:19Z"},{"alias_kind":"pith_short_16","alias_value":"R4HYQE7MJUNDQ3S3","created_at":"2026-07-05T06:48:19Z"},{"alias_kind":"pith_short_8","alias_value":"R4HYQE7M","created_at":"2026-07-05T06:48:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:R4HYQE7MJUNDQ3S3UENOQXEKFW","target":"record","payload":{"canonical_record":{"source":{"id":"2309.02999","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-06T13:43:27Z","cross_cats_sorted":[],"title_canon_sha256":"604a014c1a8cea5cac8a4c7c20c7ac9b4c7049764934455e7f43957be2a90c4e","abstract_canon_sha256":"eafb24f5b58026e48ffe4198cfa1513b21233f131b4500d7e166fe1c268b2c34"},"schema_version":"1.0"},"canonical_sha256":"8f0f8813ec4d1a386e5ba11ae85c8a2dbc5012ac4d5b688d1335b83b1fb5aae1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:48:19.805617Z","signature_b64":"8ww8AM1BWHxbRFVIW8rrD0ajm1vtDFBIy077GVYxkrPaMs+bxDuh2AleWuYEZXQ/LkWSTTfGk5fNbNwpk3lKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f0f8813ec4d1a386e5ba11ae85c8a2dbc5012ac4d5b688d1335b83b1fb5aae1","last_reissued_at":"2026-07-05T06:48:19.805119Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:48:19.805119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.02999","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:48:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/2i0ecyKfSBHYMsek2qcCv/IUBz3IzLzUWh0Qx8C+zyaaS92gLATzE8f6qSiob7ad2Fdn9gsewKaIS53usY3Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T17:50:14.966119Z"},"content_sha256":"2ee8413c2a55bf4b4e18a6ac72ec12a1c2d69cda73722430c879d16d0b745cd3","schema_version":"1.0","event_id":"sha256:2ee8413c2a55bf4b4e18a6ac72ec12a1c2d69cda73722430c879d16d0b745cd3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:R4HYQE7MJUNDQ3S3UENOQXEKFW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gang Yu, Hongyuan Zhu, Mingsheng Li, Peng Guo, Sijin Chen, Taihao Li, Tao Chen, Xin Chen, Yinjie Lei","submitted_at":"2023-09-06T13:43:27Z","abstract_excerpt":"3D dense captioning requires a model to translate its understanding of an input 3D scene into several captions associated with different object regions. Existing methods adopt a sophisticated \"detect-then-describe\" pipeline, which builds explicit relation modules upon a 3D detector with numerous hand-crafted components. While these methods have achieved initial success, the cascade pipeline tends to accumulate errors because of duplicated and inaccurate box estimations and messy 3D scenes. In this paper, we first propose Vote2Cap-DETR, a simple-yet-effective transformer framework that decouple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.02999","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/2309.02999/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:48:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d8IUnA5YaCMNcdObN5rCk2veQOFmqnrHqbLjReTH0wnepI8kpD/8AJWWa7lNSPX/T4YMhnnisk/E99J0RiXWAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T17:50:14.966729Z"},"content_sha256":"d7832bba2262fb34fd666cd337d7778ca2cd0add94bbbf5dd77b8de57bd45d62","schema_version":"1.0","event_id":"sha256:d7832bba2262fb34fd666cd337d7778ca2cd0add94bbbf5dd77b8de57bd45d62"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R4HYQE7MJUNDQ3S3UENOQXEKFW/bundle.json","state_url":"https://pith.science/pith/R4HYQE7MJUNDQ3S3UENOQXEKFW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R4HYQE7MJUNDQ3S3UENOQXEKFW/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-20T17:50:14Z","links":{"resolver":"https://pith.science/pith/R4HYQE7MJUNDQ3S3UENOQXEKFW","bundle":"https://pith.science/pith/R4HYQE7MJUNDQ3S3UENOQXEKFW/bundle.json","state":"https://pith.science/pith/R4HYQE7MJUNDQ3S3UENOQXEKFW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R4HYQE7MJUNDQ3S3UENOQXEKFW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:R4HYQE7MJUNDQ3S3UENOQXEKFW","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":"eafb24f5b58026e48ffe4198cfa1513b21233f131b4500d7e166fe1c268b2c34","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-06T13:43:27Z","title_canon_sha256":"604a014c1a8cea5cac8a4c7c20c7ac9b4c7049764934455e7f43957be2a90c4e"},"schema_version":"1.0","source":{"id":"2309.02999","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.02999","created_at":"2026-07-05T06:48:19Z"},{"alias_kind":"arxiv_version","alias_value":"2309.02999v1","created_at":"2026-07-05T06:48:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.02999","created_at":"2026-07-05T06:48:19Z"},{"alias_kind":"pith_short_12","alias_value":"R4HYQE7MJUND","created_at":"2026-07-05T06:48:19Z"},{"alias_kind":"pith_short_16","alias_value":"R4HYQE7MJUNDQ3S3","created_at":"2026-07-05T06:48:19Z"},{"alias_kind":"pith_short_8","alias_value":"R4HYQE7M","created_at":"2026-07-05T06:48:19Z"}],"graph_snapshots":[{"event_id":"sha256:d7832bba2262fb34fd666cd337d7778ca2cd0add94bbbf5dd77b8de57bd45d62","target":"graph","created_at":"2026-07-05T06:48:19Z","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/2309.02999/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"3D dense captioning requires a model to translate its understanding of an input 3D scene into several captions associated with different object regions. Existing methods adopt a sophisticated \"detect-then-describe\" pipeline, which builds explicit relation modules upon a 3D detector with numerous hand-crafted components. While these methods have achieved initial success, the cascade pipeline tends to accumulate errors because of duplicated and inaccurate box estimations and messy 3D scenes. In this paper, we first propose Vote2Cap-DETR, a simple-yet-effective transformer framework that decouple","authors_text":"Gang Yu, Hongyuan Zhu, Mingsheng Li, Peng Guo, Sijin Chen, Taihao Li, Tao Chen, Xin Chen, Yinjie Lei","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-06T13:43:27Z","title":"Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.02999","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":"sha256:2ee8413c2a55bf4b4e18a6ac72ec12a1c2d69cda73722430c879d16d0b745cd3","target":"record","created_at":"2026-07-05T06:48:19Z","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":"eafb24f5b58026e48ffe4198cfa1513b21233f131b4500d7e166fe1c268b2c34","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-06T13:43:27Z","title_canon_sha256":"604a014c1a8cea5cac8a4c7c20c7ac9b4c7049764934455e7f43957be2a90c4e"},"schema_version":"1.0","source":{"id":"2309.02999","kind":"arxiv","version":1}},"canonical_sha256":"8f0f8813ec4d1a386e5ba11ae85c8a2dbc5012ac4d5b688d1335b83b1fb5aae1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f0f8813ec4d1a386e5ba11ae85c8a2dbc5012ac4d5b688d1335b83b1fb5aae1","first_computed_at":"2026-07-05T06:48:19.805119Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:48:19.805119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8ww8AM1BWHxbRFVIW8rrD0ajm1vtDFBIy077GVYxkrPaMs+bxDuh2AleWuYEZXQ/LkWSTTfGk5fNbNwpk3lKBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:48:19.805617Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.02999","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ee8413c2a55bf4b4e18a6ac72ec12a1c2d69cda73722430c879d16d0b745cd3","sha256:d7832bba2262fb34fd666cd337d7778ca2cd0add94bbbf5dd77b8de57bd45d62"],"state_sha256":"460e7717448732dcc8f762e73403b89b282c6c69cf55d07492a267ee0c23912b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LBchaksmzk/6SKNoJZ5viUhUkcgrdNkMWGXhb0LxKMUFxr4DH+Ug1ExoLQ2s2DyNpVJuyt6BXvdwmJySd7MlAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T17:50:14.970110Z","bundle_sha256":"54d194479c4e5a455d5006d96e3995dbdb42996b619ef38f488adedafc870040"}}