{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6DPQ633YCDIZZFOSKROJDZF5CH","short_pith_number":"pith:6DPQ633Y","schema_version":"1.0","canonical_sha256":"f0df0f6f7810d19c95d2545c91e4bd11ec55b8025ba9af66684cb28bebe0d6ad","source":{"kind":"arxiv","id":"2411.10503","version":2},"attestation_state":"computed","paper":{"title":"Everything is a Video: Unifying Modalities through Next-Frame Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chenghao Xiao, Dean Slack, G. Thomas Hudson, Jamie Sterling, Junjie Shentu, Noura Al Moubayed, Thomas Winterbottom","submitted_at":"2024-11-15T12:59:37Z","abstract_excerpt":"Multimodal learning, which involves integrating information from various modalities such as text, images, audio, and video, is pivotal for numerous complex tasks like visual question answering, cross-modal retrieval, and caption generation. Traditional approaches rely on modality-specific encoders and late fusion techniques, which can hinder scalability and flexibility when adapting to new tasks or modalities. To address these limitations, we introduce a novel framework that extends the concept of task reformulation beyond natural language processing (NLP) to multimodal learning. We propose to"},"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":"2411.10503","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-15T12:59:37Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"29f4a48f75a0837199e8d97381931b4fb89f31bd7536a9cdc3cbfbee278576be","abstract_canon_sha256":"21abef648b167983142eac80e43be3e8d04cda4757a112e88ba6014d2b9e21cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:58.603926Z","signature_b64":"NzhZiDn7yP3rQFbgxMVlQR2qgggblNcgLtHtlnADyyY3DyYFOT0TIXG6eedrOgonFH8LYJIcmzAtBZ01wkKaAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0df0f6f7810d19c95d2545c91e4bd11ec55b8025ba9af66684cb28bebe0d6ad","last_reissued_at":"2026-07-05T11:43:58.603436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:58.603436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Everything is a Video: Unifying Modalities through Next-Frame Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chenghao Xiao, Dean Slack, G. Thomas Hudson, Jamie Sterling, Junjie Shentu, Noura Al Moubayed, Thomas Winterbottom","submitted_at":"2024-11-15T12:59:37Z","abstract_excerpt":"Multimodal learning, which involves integrating information from various modalities such as text, images, audio, and video, is pivotal for numerous complex tasks like visual question answering, cross-modal retrieval, and caption generation. Traditional approaches rely on modality-specific encoders and late fusion techniques, which can hinder scalability and flexibility when adapting to new tasks or modalities. To address these limitations, we introduce a novel framework that extends the concept of task reformulation beyond natural language processing (NLP) to multimodal learning. We propose to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10503","kind":"arxiv","version":2},"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/2411.10503/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":"2411.10503","created_at":"2026-07-05T11:43:58.603494+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.10503v2","created_at":"2026-07-05T11:43:58.603494+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10503","created_at":"2026-07-05T11:43:58.603494+00:00"},{"alias_kind":"pith_short_12","alias_value":"6DPQ633YCDIZ","created_at":"2026-07-05T11:43:58.603494+00:00"},{"alias_kind":"pith_short_16","alias_value":"6DPQ633YCDIZZFOS","created_at":"2026-07-05T11:43:58.603494+00:00"},{"alias_kind":"pith_short_8","alias_value":"6DPQ633Y","created_at":"2026-07-05T11:43:58.603494+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01364","citing_title":"Unraveling Spatio-Temporal Foundation Models via the Pipeline Lens: A Comprehensive Review","ref_index":135,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6DPQ633YCDIZZFOSKROJDZF5CH","json":"https://pith.science/pith/6DPQ633YCDIZZFOSKROJDZF5CH.json","graph_json":"https://pith.science/api/pith-number/6DPQ633YCDIZZFOSKROJDZF5CH/graph.json","events_json":"https://pith.science/api/pith-number/6DPQ633YCDIZZFOSKROJDZF5CH/events.json","paper":"https://pith.science/paper/6DPQ633Y"},"agent_actions":{"view_html":"https://pith.science/pith/6DPQ633YCDIZZFOSKROJDZF5CH","download_json":"https://pith.science/pith/6DPQ633YCDIZZFOSKROJDZF5CH.json","view_paper":"https://pith.science/paper/6DPQ633Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.10503&json=true","fetch_graph":"https://pith.science/api/pith-number/6DPQ633YCDIZZFOSKROJDZF5CH/graph.json","fetch_events":"https://pith.science/api/pith-number/6DPQ633YCDIZZFOSKROJDZF5CH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6DPQ633YCDIZZFOSKROJDZF5CH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6DPQ633YCDIZZFOSKROJDZF5CH/action/storage_attestation","attest_author":"https://pith.science/pith/6DPQ633YCDIZZFOSKROJDZF5CH/action/author_attestation","sign_citation":"https://pith.science/pith/6DPQ633YCDIZZFOSKROJDZF5CH/action/citation_signature","submit_replication":"https://pith.science/pith/6DPQ633YCDIZZFOSKROJDZF5CH/action/replication_record"}},"created_at":"2026-07-05T11:43:58.603494+00:00","updated_at":"2026-07-05T11:43:58.603494+00:00"}