{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TE3PQ7FXEB6MH2TVHVMHOB6M5H","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":"e41d5510d0653b1887d6dd13b32a3fbb585d810a07c7ba58803a3f7f0eb09c1c","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-06T16:27:52Z","title_canon_sha256":"d40e7812a683057421acc66303cdfb9c7148519d698af625f4c12504db839ebc"},"schema_version":"1.0","source":{"id":"2409.04388","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.04388","created_at":"2026-07-05T11:03:51Z"},{"alias_kind":"arxiv_version","alias_value":"2409.04388v5","created_at":"2026-07-05T11:03:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04388","created_at":"2026-07-05T11:03:51Z"},{"alias_kind":"pith_short_12","alias_value":"TE3PQ7FXEB6M","created_at":"2026-07-05T11:03:51Z"},{"alias_kind":"pith_short_16","alias_value":"TE3PQ7FXEB6MH2TV","created_at":"2026-07-05T11:03:51Z"},{"alias_kind":"pith_short_8","alias_value":"TE3PQ7FX","created_at":"2026-07-05T11:03:51Z"}],"graph_snapshots":[{"event_id":"sha256:401fb487e0d9288a4072fec943b17ca8aa606ed8532e5d0a19b9981e74c94282","target":"graph","created_at":"2026-07-05T11:03:51Z","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/2409.04388/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents question-answering on dense video events, a novel task that answers and grounds dense-event questions in long videos, thus challenging MLLMs to faithfully comprehend and reason about multiple events over extended periods of time. To facilitate the study, we construct DeVE-QA -- a dataset featuring 78K questions about 26K events on 10.6K long videos. Our benchmarking shows that state-of-the-art MLLMs struggle on DeVE-QA. For improvement, we propose DeVi, a novel training-free MLLM approach that highlights a hierarchical captioning module, a temporal event memory module, and ","authors_text":"Angela Yao, Hangyu Qin, Junbin Xiao","cross_cats":["cs.AI","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-06T16:27:52Z","title":"Question-Answering Dense Video Events"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04388","kind":"arxiv","version":5},"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":"sha256:90d66cfc544b35739d7090d5c987ef07788be1f77bc43ae2d4e7cc6159a7abb7","target":"record","created_at":"2026-07-05T11:03:51Z","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":"e41d5510d0653b1887d6dd13b32a3fbb585d810a07c7ba58803a3f7f0eb09c1c","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-06T16:27:52Z","title_canon_sha256":"d40e7812a683057421acc66303cdfb9c7148519d698af625f4c12504db839ebc"},"schema_version":"1.0","source":{"id":"2409.04388","kind":"arxiv","version":5}},"canonical_sha256":"9936f87cb7207cc3ea753d587707cce9dfb2576c2c35f89a077fb2022a1517ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9936f87cb7207cc3ea753d587707cce9dfb2576c2c35f89a077fb2022a1517ed","first_computed_at":"2026-07-05T11:03:51.817753Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:03:51.817753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"80hGTNOUVxspS5k/zxoj4tZYZkQlkKx2QWRtdRzxCttGirkxnHXHBFm/ibJfMtJty9dsknizvBjV/YWBPP1jDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:03:51.818409Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.04388","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90d66cfc544b35739d7090d5c987ef07788be1f77bc43ae2d4e7cc6159a7abb7","sha256:401fb487e0d9288a4072fec943b17ca8aa606ed8532e5d0a19b9981e74c94282"],"state_sha256":"9df10bca456b1504cf19b053ad20a4e08e52c71a0967341bb22ec56a686fec0a"}