{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IYQZ4DM5MI37TAMW3GXOOVAWRJ","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":"d242eafbeda86a6bdbae04e1f946f5b06519148473ba0b4c902caa22d9fe1caa","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-06-15T04:59:19Z","title_canon_sha256":"0fe516bb1dc4491dab76721846d8530eacfa14d39432dba6ca8494b81e2e4d2a"},"schema_version":"1.0","source":{"id":"2407.12002","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12002","created_at":"2026-07-05T08:44:58Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12002v1","created_at":"2026-07-05T08:44:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12002","created_at":"2026-07-05T08:44:58Z"},{"alias_kind":"pith_short_12","alias_value":"IYQZ4DM5MI37","created_at":"2026-07-05T08:44:58Z"},{"alias_kind":"pith_short_16","alias_value":"IYQZ4DM5MI37TAMW","created_at":"2026-07-05T08:44:58Z"},{"alias_kind":"pith_short_8","alias_value":"IYQZ4DM5","created_at":"2026-07-05T08:44:58Z"}],"graph_snapshots":[{"event_id":"sha256:15c8a76ba9f910c9048733e9dda4313a64c255b5d84a159a9265de3f9df6e5b2","target":"graph","created_at":"2026-07-05T08:44:58Z","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/2407.12002/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, live streaming platforms have gained immense popularity. Traditional video highlight detection mainly focuses on visual features and utilizes both past and future content for prediction. However, live streaming requires models to infer without future frames and process complex multimodal interactions, including images, audio and text comments. To address these issues, we propose a multimodal transformer that incorporates historical look-back windows. We introduce a novel Modality Temporal Alignment Module to handle the temporal shift of cross-modal signals. Additionally, using existi","authors_text":"Dong Shen, Fan Yang, Gaofeng Meng, Guorui Zhou, Jiaxin Deng, Liqin Zhao, Shiyao Wang","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-06-15T04:59:19Z","title":"A Multimodal Transformer for Live Streaming Highlight Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12002","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":"sha256:28774200bb26cfe9f1c3269fac701c73c490618d8313d08a14ffd26611377dd2","target":"record","created_at":"2026-07-05T08:44:58Z","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":"d242eafbeda86a6bdbae04e1f946f5b06519148473ba0b4c902caa22d9fe1caa","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-06-15T04:59:19Z","title_canon_sha256":"0fe516bb1dc4491dab76721846d8530eacfa14d39432dba6ca8494b81e2e4d2a"},"schema_version":"1.0","source":{"id":"2407.12002","kind":"arxiv","version":1}},"canonical_sha256":"46219e0d9d6237f98196d9aee754168a4fa2a981a0d19d1f36c9df4b78e4309d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46219e0d9d6237f98196d9aee754168a4fa2a981a0d19d1f36c9df4b78e4309d","first_computed_at":"2026-07-05T08:44:58.657626Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:58.657626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I7lq7Z1ZaLh0icwn6AKcvAr7d/x2D2i+VXBhm5o9BG/9GHSTeT7pXbX15GpxT5TEyfYcVb9vC63GmhQX8SP1AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:58.658021Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12002","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28774200bb26cfe9f1c3269fac701c73c490618d8313d08a14ffd26611377dd2","sha256:15c8a76ba9f910c9048733e9dda4313a64c255b5d84a159a9265de3f9df6e5b2"],"state_sha256":"d115ad96fc5f19b697cbdb703d334b3a1afc7fdcb9d861af2fc8cf0c6f52d121"}