{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:SBQHRZIQNP75QHADG5OQ4MSM4N","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":"cbc359a7b457c1947050ab9e4fd0a721d7eb99580011985a19982cc41a4b966a","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-15T19:56:47Z","title_canon_sha256":"d4c70716f0b3bbad65f730d2147ef1fb0a5e7928759158e6dfdf4eeec9bad230"},"schema_version":"1.0","source":{"id":"2010.07999","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.07999","created_at":"2026-07-05T01:43:30Z"},{"alias_kind":"arxiv_version","alias_value":"2010.07999v1","created_at":"2026-07-05T01:43:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.07999","created_at":"2026-07-05T01:43:30Z"},{"alias_kind":"pith_short_12","alias_value":"SBQHRZIQNP75","created_at":"2026-07-05T01:43:30Z"},{"alias_kind":"pith_short_16","alias_value":"SBQHRZIQNP75QHAD","created_at":"2026-07-05T01:43:30Z"},{"alias_kind":"pith_short_8","alias_value":"SBQHRZIQ","created_at":"2026-07-05T01:43:30Z"}],"graph_snapshots":[{"event_id":"sha256:d35d2b2b5e1eabb9ce9b93fa1442905f033b83c21de60685fae42221c99eecb1","target":"graph","created_at":"2026-07-05T01:43:30Z","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/2010.07999/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Given a video with aligned dialogue, people can often infer what is more likely to happen next. Making such predictions requires not only a deep understanding of the rich dynamics underlying the video and dialogue, but also a significant amount of commonsense knowledge. In this work, we explore whether AI models are able to learn to make such multimodal commonsense next-event predictions. To support research in this direction, we collect a new dataset, named Video-and-Language Event Prediction (VLEP), with 28,726 future event prediction examples (along with their rationales) from 10,234 divers","authors_text":"Jie Lei, Licheng Yu, Mohit Bansal, Tamara L. Berg","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-15T19:56:47Z","title":"What is More Likely to Happen Next? Video-and-Language Future Event Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.07999","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":"sha256:904cf6cc76abf69ab7dff2afe066872c0a643aa13754431f87b7a92c96ace52d","target":"record","created_at":"2026-07-05T01:43:30Z","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":"cbc359a7b457c1947050ab9e4fd0a721d7eb99580011985a19982cc41a4b966a","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-15T19:56:47Z","title_canon_sha256":"d4c70716f0b3bbad65f730d2147ef1fb0a5e7928759158e6dfdf4eeec9bad230"},"schema_version":"1.0","source":{"id":"2010.07999","kind":"arxiv","version":1}},"canonical_sha256":"906078e5106bffd81c03375d0e324ce35184786a48342896c4a8d5cb066328dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"906078e5106bffd81c03375d0e324ce35184786a48342896c4a8d5cb066328dc","first_computed_at":"2026-07-05T01:43:30.453655Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:43:30.453655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uuhWkhQfeNX3PpopKQnX8O7MfmeHA1J52mW2kiUX3CrzOgI82VKUEpxU3e6pULsBSklKGw1OoLXNyLmzYE7zCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:43:30.454109Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.07999","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:904cf6cc76abf69ab7dff2afe066872c0a643aa13754431f87b7a92c96ace52d","sha256:d35d2b2b5e1eabb9ce9b93fa1442905f033b83c21de60685fae42221c99eecb1"],"state_sha256":"93a13bac19899fe11f5f12b2f5bbc39c5eddcbd4bbc87e8299b543c37ed11ca5"}