{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SBQHRZIQNP75QHADG5OQ4MSM4N","short_pith_number":"pith:SBQHRZIQ","schema_version":"1.0","canonical_sha256":"906078e5106bffd81c03375d0e324ce35184786a48342896c4a8d5cb066328dc","source":{"kind":"arxiv","id":"2010.07999","version":1},"attestation_state":"computed","paper":{"title":"What is More Likely to Happen Next? Video-and-Language Future Event Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Jie Lei, Licheng Yu, Mohit Bansal, Tamara L. Berg","submitted_at":"2020-10-15T19:56:47Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2010.07999","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-15T19:56:47Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"d4c70716f0b3bbad65f730d2147ef1fb0a5e7928759158e6dfdf4eeec9bad230","abstract_canon_sha256":"cbc359a7b457c1947050ab9e4fd0a721d7eb99580011985a19982cc41a4b966a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:30.454109Z","signature_b64":"uuhWkhQfeNX3PpopKQnX8O7MfmeHA1J52mW2kiUX3CrzOgI82VKUEpxU3e6pULsBSklKGw1OoLXNyLmzYE7zCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"906078e5106bffd81c03375d0e324ce35184786a48342896c4a8d5cb066328dc","last_reissued_at":"2026-07-05T01:43:30.453655Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:30.453655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What is More Likely to Happen Next? Video-and-Language Future Event Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Jie Lei, Licheng Yu, Mohit Bansal, Tamara L. Berg","submitted_at":"2020-10-15T19:56:47Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.07999","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/2010.07999/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2010.07999","created_at":"2026-07-05T01:43:30.453716+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.07999v1","created_at":"2026-07-05T01:43:30.453716+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.07999","created_at":"2026-07-05T01:43:30.453716+00:00"},{"alias_kind":"pith_short_12","alias_value":"SBQHRZIQNP75","created_at":"2026-07-05T01:43:30.453716+00:00"},{"alias_kind":"pith_short_16","alias_value":"SBQHRZIQNP75QHAD","created_at":"2026-07-05T01:43:30.453716+00:00"},{"alias_kind":"pith_short_8","alias_value":"SBQHRZIQ","created_at":"2026-07-05T01:43:30.453716+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31069","citing_title":"Towards Effective Long-Video Event Prediction via Multi-Level Event Semantics Mining","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2204.00598","citing_title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","ref_index":82,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SBQHRZIQNP75QHADG5OQ4MSM4N","json":"https://pith.science/pith/SBQHRZIQNP75QHADG5OQ4MSM4N.json","graph_json":"https://pith.science/api/pith-number/SBQHRZIQNP75QHADG5OQ4MSM4N/graph.json","events_json":"https://pith.science/api/pith-number/SBQHRZIQNP75QHADG5OQ4MSM4N/events.json","paper":"https://pith.science/paper/SBQHRZIQ"},"agent_actions":{"view_html":"https://pith.science/pith/SBQHRZIQNP75QHADG5OQ4MSM4N","download_json":"https://pith.science/pith/SBQHRZIQNP75QHADG5OQ4MSM4N.json","view_paper":"https://pith.science/paper/SBQHRZIQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.07999&json=true","fetch_graph":"https://pith.science/api/pith-number/SBQHRZIQNP75QHADG5OQ4MSM4N/graph.json","fetch_events":"https://pith.science/api/pith-number/SBQHRZIQNP75QHADG5OQ4MSM4N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SBQHRZIQNP75QHADG5OQ4MSM4N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SBQHRZIQNP75QHADG5OQ4MSM4N/action/storage_attestation","attest_author":"https://pith.science/pith/SBQHRZIQNP75QHADG5OQ4MSM4N/action/author_attestation","sign_citation":"https://pith.science/pith/SBQHRZIQNP75QHADG5OQ4MSM4N/action/citation_signature","submit_replication":"https://pith.science/pith/SBQHRZIQNP75QHADG5OQ4MSM4N/action/replication_record"}},"created_at":"2026-07-05T01:43:30.453716+00:00","updated_at":"2026-07-05T01:43:30.453716+00:00"}