{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:E4MSYXASM7YS2WK34J6ILWPCJM","short_pith_number":"pith:E4MSYXAS","canonical_record":{"source":{"id":"2506.16082","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-19T07:07:42Z","cross_cats_sorted":[],"title_canon_sha256":"7399c439312670fcefe12b832687f709a33c4c73bf1ee06074454effb7831f1b","abstract_canon_sha256":"9359dbfc219499f7f4d577433ec57dd21b44a01806c55d75ea12e1c58800a7d5"},"schema_version":"1.0"},"canonical_sha256":"27192c5c1267f12d595be27c85d9e24b23e4df5072393ac21df31523c33bb74a","source":{"kind":"arxiv","id":"2506.16082","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16082","created_at":"2026-07-05T11:24:30Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16082v1","created_at":"2026-07-05T11:24:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16082","created_at":"2026-07-05T11:24:30Z"},{"alias_kind":"pith_short_12","alias_value":"E4MSYXASM7YS","created_at":"2026-07-05T11:24:30Z"},{"alias_kind":"pith_short_16","alias_value":"E4MSYXASM7YS2WK3","created_at":"2026-07-05T11:24:30Z"},{"alias_kind":"pith_short_8","alias_value":"E4MSYXAS","created_at":"2026-07-05T11:24:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:E4MSYXASM7YS2WK34J6ILWPCJM","target":"record","payload":{"canonical_record":{"source":{"id":"2506.16082","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-19T07:07:42Z","cross_cats_sorted":[],"title_canon_sha256":"7399c439312670fcefe12b832687f709a33c4c73bf1ee06074454effb7831f1b","abstract_canon_sha256":"9359dbfc219499f7f4d577433ec57dd21b44a01806c55d75ea12e1c58800a7d5"},"schema_version":"1.0"},"canonical_sha256":"27192c5c1267f12d595be27c85d9e24b23e4df5072393ac21df31523c33bb74a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:30.139029Z","signature_b64":"iPIrZjvWkmPuGyKP51/9TkEmGuqVuVWOQhR1YJJYyQxvZ2ipC7oLoNH7Mg1RQhmoRpgV/qT6/Fgc7bRNpjg6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27192c5c1267f12d595be27c85d9e24b23e4df5072393ac21df31523c33bb74a","last_reissued_at":"2026-07-05T11:24:30.138466Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:30.138466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.16082","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":"2026-07-05T11:24:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c6SpZPbXnlU4Vko9jivzxtCu7GYxAgPYwdGIe5sadPCXIQ/r+yXRyG0YfRvIZ0WKkSF9B2lPh1NsFmVTJKqeBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:44:53.876460Z"},"content_sha256":"62c2f7179029ee1d11e669a13c1a1d03e48d5014c91abf5c9f3569ef1cacc070","schema_version":"1.0","event_id":"sha256:62c2f7179029ee1d11e669a13c1a1d03e48d5014c91abf5c9f3569ef1cacc070"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:E4MSYXASM7YS2WK34J6ILWPCJM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PR-DETR: Injecting Position and Relation Prior for Dense Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Le Wang, Sanping Zhou, Yizhe Li, Zheng Qin","submitted_at":"2025-06-19T07:07:42Z","abstract_excerpt":"Dense video captioning is a challenging task that aims to localize and caption multiple events in an untrimmed video. Recent studies mainly follow the transformer-based architecture to jointly perform the two sub-tasks, i.e., event localization and caption generation, in an end-to-end manner. Based on the general philosophy of detection transformer, these methods implicitly learn the event locations and event semantics, which requires a large amount of training data and limits the model's performance in practice. In this paper, we propose a novel dense video captioning framework, named PR-DETR"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16082","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/2506.16082/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":"2026-07-05T11:24:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tS179W5zFZT4d/Z5LJBASbOw3JTfnOJi6BGQHSeWbZ6OWRueQReCp8hoIISDVQNBXewiP+sRf5OyEPPFUdlOAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:44:53.876869Z"},"content_sha256":"0072d7c0bded11b71ef05d47a275559e886356d47d800a39cb8b281c2a48c7b1","schema_version":"1.0","event_id":"sha256:0072d7c0bded11b71ef05d47a275559e886356d47d800a39cb8b281c2a48c7b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E4MSYXASM7YS2WK34J6ILWPCJM/bundle.json","state_url":"https://pith.science/pith/E4MSYXASM7YS2WK34J6ILWPCJM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E4MSYXASM7YS2WK34J6ILWPCJM/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":"2026-07-06T15:44:53Z","links":{"resolver":"https://pith.science/pith/E4MSYXASM7YS2WK34J6ILWPCJM","bundle":"https://pith.science/pith/E4MSYXASM7YS2WK34J6ILWPCJM/bundle.json","state":"https://pith.science/pith/E4MSYXASM7YS2WK34J6ILWPCJM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E4MSYXASM7YS2WK34J6ILWPCJM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:E4MSYXASM7YS2WK34J6ILWPCJM","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":"9359dbfc219499f7f4d577433ec57dd21b44a01806c55d75ea12e1c58800a7d5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-19T07:07:42Z","title_canon_sha256":"7399c439312670fcefe12b832687f709a33c4c73bf1ee06074454effb7831f1b"},"schema_version":"1.0","source":{"id":"2506.16082","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16082","created_at":"2026-07-05T11:24:30Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16082v1","created_at":"2026-07-05T11:24:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16082","created_at":"2026-07-05T11:24:30Z"},{"alias_kind":"pith_short_12","alias_value":"E4MSYXASM7YS","created_at":"2026-07-05T11:24:30Z"},{"alias_kind":"pith_short_16","alias_value":"E4MSYXASM7YS2WK3","created_at":"2026-07-05T11:24:30Z"},{"alias_kind":"pith_short_8","alias_value":"E4MSYXAS","created_at":"2026-07-05T11:24:30Z"}],"graph_snapshots":[{"event_id":"sha256:0072d7c0bded11b71ef05d47a275559e886356d47d800a39cb8b281c2a48c7b1","target":"graph","created_at":"2026-07-05T11:24:30Z","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/2506.16082/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dense video captioning is a challenging task that aims to localize and caption multiple events in an untrimmed video. Recent studies mainly follow the transformer-based architecture to jointly perform the two sub-tasks, i.e., event localization and caption generation, in an end-to-end manner. Based on the general philosophy of detection transformer, these methods implicitly learn the event locations and event semantics, which requires a large amount of training data and limits the model's performance in practice. In this paper, we propose a novel dense video captioning framework, named PR-DETR","authors_text":"Le Wang, Sanping Zhou, Yizhe Li, Zheng Qin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-19T07:07:42Z","title":"PR-DETR: Injecting Position and Relation Prior for Dense Video Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16082","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":"sha256:62c2f7179029ee1d11e669a13c1a1d03e48d5014c91abf5c9f3569ef1cacc070","target":"record","created_at":"2026-07-05T11:24:30Z","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":"9359dbfc219499f7f4d577433ec57dd21b44a01806c55d75ea12e1c58800a7d5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-19T07:07:42Z","title_canon_sha256":"7399c439312670fcefe12b832687f709a33c4c73bf1ee06074454effb7831f1b"},"schema_version":"1.0","source":{"id":"2506.16082","kind":"arxiv","version":1}},"canonical_sha256":"27192c5c1267f12d595be27c85d9e24b23e4df5072393ac21df31523c33bb74a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27192c5c1267f12d595be27c85d9e24b23e4df5072393ac21df31523c33bb74a","first_computed_at":"2026-07-05T11:24:30.138466Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:24:30.138466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iPIrZjvWkmPuGyKP51/9TkEmGuqVuVWOQhR1YJJYyQxvZ2ipC7oLoNH7Mg1RQhmoRpgV/qT6/Fgc7bRNpjg6Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:24:30.139029Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.16082","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62c2f7179029ee1d11e669a13c1a1d03e48d5014c91abf5c9f3569ef1cacc070","sha256:0072d7c0bded11b71ef05d47a275559e886356d47d800a39cb8b281c2a48c7b1"],"state_sha256":"276d022d17e8610bf9baf92dafa2474b6853cfefcd04fc761a652e4a0843a073"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YByJ+IJHDHa6u5dgpDMC2ZGWlvF+/Ysz7e+Y68Hc9hBB2zy1EXzDWxNsyEQJmT16dYGwOvgjWcJnLjAXHTh7DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T15:44:53.879405Z","bundle_sha256":"44b63d0fb4362847b68e578a4fcf6b47aa03caaeed6fb3f65d4ab84bb05de6d8"}}