{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PQ3O2MLLLKE2TNPG6VLFDWYYC5","short_pith_number":"pith:PQ3O2MLL","canonical_record":{"source":{"id":"2411.14688","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T02:46:44Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"8993abceb179d8d8b29c09ad0696474a018f2b56f2e52d8b30ddeea5b580dc46","abstract_canon_sha256":"e2f565ee23d81b7af531de507200fa5c404495eff56de2bde1efff7a20c25f6b"},"schema_version":"1.0"},"canonical_sha256":"7c36ed316b5a89a9b5e6f55651db1817595f9c25ee65d678f339a348da5ebd74","source":{"kind":"arxiv","id":"2411.14688","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14688","created_at":"2026-07-05T09:38:55Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14688v1","created_at":"2026-07-05T09:38:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14688","created_at":"2026-07-05T09:38:55Z"},{"alias_kind":"pith_short_12","alias_value":"PQ3O2MLLLKE2","created_at":"2026-07-05T09:38:55Z"},{"alias_kind":"pith_short_16","alias_value":"PQ3O2MLLLKE2TNPG","created_at":"2026-07-05T09:38:55Z"},{"alias_kind":"pith_short_8","alias_value":"PQ3O2MLL","created_at":"2026-07-05T09:38:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PQ3O2MLLLKE2TNPG6VLFDWYYC5","target":"record","payload":{"canonical_record":{"source":{"id":"2411.14688","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T02:46:44Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"8993abceb179d8d8b29c09ad0696474a018f2b56f2e52d8b30ddeea5b580dc46","abstract_canon_sha256":"e2f565ee23d81b7af531de507200fa5c404495eff56de2bde1efff7a20c25f6b"},"schema_version":"1.0"},"canonical_sha256":"7c36ed316b5a89a9b5e6f55651db1817595f9c25ee65d678f339a348da5ebd74","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:55.590632Z","signature_b64":"l28bN52SbIOUlBBPOOZfss4fckvuhuUgnvN6rpj0gCtnHzuetSsPkfk19MDG5st0BCVUA4qcBabv/v+wYoMeDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c36ed316b5a89a9b5e6f55651db1817595f9c25ee65d678f339a348da5ebd74","last_reissued_at":"2026-07-05T09:38:55.590209Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:55.590209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.14688","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":"2026-07-05T09:38:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5XVAXguCs3s7WqC5BMCS1liDqViK4Yq14xQHx4oVMVISQrUb18gr9R4SznNoF9ySHzxl3wBDwkQIWGpI4AG5Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:31:31.514221Z"},"content_sha256":"1c025cf2dab633bc604b77ee85b5b8241e7481fd9b28509fbde5e6328ddb8cd2","schema_version":"1.0","event_id":"sha256:1c025cf2dab633bc604b77ee85b5b8241e7481fd9b28509fbde5e6328ddb8cd2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PQ3O2MLLLKE2TNPG6VLFDWYYC5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Whats in a Video: Factorized Autoregressive Decoding for Online Dense Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"AJ Piergiovanni, Anelia Angelova, Dahun Kim, Isaac Noble, Michael S. Ryoo","submitted_at":"2024-11-22T02:46:44Z","abstract_excerpt":"Generating automatic dense captions for videos that accurately describe their contents remains a challenging area of research. Most current models require processing the entire video at once. Instead, we propose an efficient, online approach which outputs frequent, detailed and temporally aligned captions, without access to future frames. Our model uses a novel autoregressive factorized decoding architecture, which models the sequence of visual features for each time segment, outputting localized descriptions and efficiently leverages the context from the previous video segments. This allows t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14688","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/2411.14688/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":"2026-07-05T09:38:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m2paaGvCsgIRFw+MGiZRgZYTRtAOBQhjQJGqOcTGeJEELpcowjhMmMXyD3FRavlUVDaZi6rIp5buuJKIqwnhAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:31:31.514743Z"},"content_sha256":"1563b61329dde5bdd44bf26ce7a64c44a7d4e9837d140c5009f2224bad01a7a7","schema_version":"1.0","event_id":"sha256:1563b61329dde5bdd44bf26ce7a64c44a7d4e9837d140c5009f2224bad01a7a7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PQ3O2MLLLKE2TNPG6VLFDWYYC5/bundle.json","state_url":"https://pith.science/pith/PQ3O2MLLLKE2TNPG6VLFDWYYC5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PQ3O2MLLLKE2TNPG6VLFDWYYC5/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":"2026-08-13T04:31:31Z","links":{"resolver":"https://pith.science/pith/PQ3O2MLLLKE2TNPG6VLFDWYYC5","bundle":"https://pith.science/pith/PQ3O2MLLLKE2TNPG6VLFDWYYC5/bundle.json","state":"https://pith.science/pith/PQ3O2MLLLKE2TNPG6VLFDWYYC5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PQ3O2MLLLKE2TNPG6VLFDWYYC5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PQ3O2MLLLKE2TNPG6VLFDWYYC5","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":"e2f565ee23d81b7af531de507200fa5c404495eff56de2bde1efff7a20c25f6b","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T02:46:44Z","title_canon_sha256":"8993abceb179d8d8b29c09ad0696474a018f2b56f2e52d8b30ddeea5b580dc46"},"schema_version":"1.0","source":{"id":"2411.14688","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14688","created_at":"2026-07-05T09:38:55Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14688v1","created_at":"2026-07-05T09:38:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14688","created_at":"2026-07-05T09:38:55Z"},{"alias_kind":"pith_short_12","alias_value":"PQ3O2MLLLKE2","created_at":"2026-07-05T09:38:55Z"},{"alias_kind":"pith_short_16","alias_value":"PQ3O2MLLLKE2TNPG","created_at":"2026-07-05T09:38:55Z"},{"alias_kind":"pith_short_8","alias_value":"PQ3O2MLL","created_at":"2026-07-05T09:38:55Z"}],"graph_snapshots":[{"event_id":"sha256:1563b61329dde5bdd44bf26ce7a64c44a7d4e9837d140c5009f2224bad01a7a7","target":"graph","created_at":"2026-07-05T09:38:55Z","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/2411.14688/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating automatic dense captions for videos that accurately describe their contents remains a challenging area of research. Most current models require processing the entire video at once. Instead, we propose an efficient, online approach which outputs frequent, detailed and temporally aligned captions, without access to future frames. Our model uses a novel autoregressive factorized decoding architecture, which models the sequence of visual features for each time segment, outputting localized descriptions and efficiently leverages the context from the previous video segments. This allows t","authors_text":"AJ Piergiovanni, Anelia Angelova, Dahun Kim, Isaac Noble, Michael S. Ryoo","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T02:46:44Z","title":"Whats in a Video: Factorized Autoregressive Decoding for Online Dense Video Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14688","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":"sha256:1c025cf2dab633bc604b77ee85b5b8241e7481fd9b28509fbde5e6328ddb8cd2","target":"record","created_at":"2026-07-05T09:38:55Z","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":"e2f565ee23d81b7af531de507200fa5c404495eff56de2bde1efff7a20c25f6b","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T02:46:44Z","title_canon_sha256":"8993abceb179d8d8b29c09ad0696474a018f2b56f2e52d8b30ddeea5b580dc46"},"schema_version":"1.0","source":{"id":"2411.14688","kind":"arxiv","version":1}},"canonical_sha256":"7c36ed316b5a89a9b5e6f55651db1817595f9c25ee65d678f339a348da5ebd74","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c36ed316b5a89a9b5e6f55651db1817595f9c25ee65d678f339a348da5ebd74","first_computed_at":"2026-07-05T09:38:55.590209Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:55.590209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l28bN52SbIOUlBBPOOZfss4fckvuhuUgnvN6rpj0gCtnHzuetSsPkfk19MDG5st0BCVUA4qcBabv/v+wYoMeDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:55.590632Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14688","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c025cf2dab633bc604b77ee85b5b8241e7481fd9b28509fbde5e6328ddb8cd2","sha256:1563b61329dde5bdd44bf26ce7a64c44a7d4e9837d140c5009f2224bad01a7a7"],"state_sha256":"f72501eb034ae9014e543fa13fee386b27c23e3af6aae94717b42bd7457b5d7f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1STkSl+2cbAK75ieBfdbzEPCFMlslKYLhTcrSCFuPBt22u1Faf/s1yXNhgTzdULXrKnmsw1M1AIXQ6qX42fiBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T04:31:31.522912Z","bundle_sha256":"f95946d9d43fd08c176206c1c74745f37b2fc607eebf945b4949365106978a75"}}