{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FWJ3RRHEZ2IZQYKDOSYEABKJM5","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":"8ba33b4a28139138d15ae8cb09638d39d14441ce410959cbcd924a857ed6f819","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T17:59:15Z","title_canon_sha256":"b1d84ec33eb6f694625ff24c71e7bf393005cb5ab42dc004d16a0285c5386dcc"},"schema_version":"1.0","source":{"id":"2404.01297","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.01297","created_at":"2026-07-05T08:03:04Z"},{"alias_kind":"arxiv_version","alias_value":"2404.01297v1","created_at":"2026-07-05T08:03:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01297","created_at":"2026-07-05T08:03:04Z"},{"alias_kind":"pith_short_12","alias_value":"FWJ3RRHEZ2IZ","created_at":"2026-07-05T08:03:04Z"},{"alias_kind":"pith_short_16","alias_value":"FWJ3RRHEZ2IZQYKD","created_at":"2026-07-05T08:03:04Z"},{"alias_kind":"pith_short_8","alias_value":"FWJ3RRHE","created_at":"2026-07-05T08:03:04Z"}],"graph_snapshots":[{"event_id":"sha256:69db2b1a85731e4d4e044e837f4569c9b9238b281e089cf4938938320ba1a18d","target":"graph","created_at":"2026-07-05T08:03:04Z","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/2404.01297/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"An ideal model for dense video captioning -- predicting captions localized temporally in a video -- should be able to handle long input videos, predict rich, detailed textual descriptions, and be able to produce outputs before processing the entire video. Current state-of-the-art models, however, process a fixed number of downsampled frames, and make a single full prediction after seeing the whole video. We propose a streaming dense video captioning model that consists of two novel components: First, we propose a new memory module, based on clustering incoming tokens, which can handle arbitrar","authors_text":"Anurag Arnab, Arsha Nagrani, Austin Myers, Cordelia Schmid, Shen Yan, Shyamal Buch, Xingyi Zhou, Xuehan Xiong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T17:59:15Z","title":"Streaming Dense Video Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01297","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:d04346d1715a2292f445f4014a08b73f9d88f8436bb221380afc6ff692ec6321","target":"record","created_at":"2026-07-05T08:03:04Z","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":"8ba33b4a28139138d15ae8cb09638d39d14441ce410959cbcd924a857ed6f819","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T17:59:15Z","title_canon_sha256":"b1d84ec33eb6f694625ff24c71e7bf393005cb5ab42dc004d16a0285c5386dcc"},"schema_version":"1.0","source":{"id":"2404.01297","kind":"arxiv","version":1}},"canonical_sha256":"2d93b8c4e4ce9198614374b0400549677e95441f0542c479b5405b6a472984c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d93b8c4e4ce9198614374b0400549677e95441f0542c479b5405b6a472984c8","first_computed_at":"2026-07-05T08:03:04.247888Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:03:04.247888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ktXS+eI6FEj8l7E/NDAqhrleFjntZPnHpcGi6m1YqkZFxV4DFUuPQCNWBcSIApDMbaAxQf2rIOePaSwPAMtwDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:03:04.248371Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.01297","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d04346d1715a2292f445f4014a08b73f9d88f8436bb221380afc6ff692ec6321","sha256:69db2b1a85731e4d4e044e837f4569c9b9238b281e089cf4938938320ba1a18d"],"state_sha256":"d37804e0d89558c4305d9034d9e2f06de81d0bbd7fd15d44b243077278ea021e"}