{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SBFVWLWBIMEU7FBLACCHPFCV5X","short_pith_number":"pith:SBFVWLWB","schema_version":"1.0","canonical_sha256":"904b5b2ec143094f942b0084779455edd28542a43102a15b6c0eab7fbfa87dc0","source":{"kind":"arxiv","id":"2505.12489","version":2},"attestation_state":"computed","paper":{"title":"Video-GPT via Next Clip Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Binxin Yang, Canmiao Fu, Chen Li, Chong Sun, Fangyikang Wang, Shaobin Zhuang, Yali Wang, Ying Zhang, Zhipeng Huang","submitted_at":"2025-05-18T16:22:58Z","abstract_excerpt":"GPT has shown its remarkable success in natural language processing. However, the language sequence is not sufficient to describe spatial-temporal details in the visual world. Alternatively, the video sequence is good at capturing such details. Motivated by this fact, we propose a concise Video-GPT in this paper by treating video as new language for visual world modeling. By analogy to next token prediction in GPT, we introduce a novel next clip diffusion paradigm for pretraining Video-GPT. Different from the previous works, this distinct paradigm allows Video-GPT to tackle both short-term gen"},"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":"2505.12489","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-18T16:22:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2e1331ced01a402db0a19882fa789c68b724ac9468bce719e121faf4f9e520f6","abstract_canon_sha256":"02353822ff93ea728f1ed18e6fe29d497c45299f682881db1da547be5d3c5788"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:32.748853Z","signature_b64":"3XIMrthDQPljrHi9VQiIFZ3rxyUMp/PN9MXhv3Z+mPODxUJxByiOvyZ/kocz8stDcfq4z1HR6h+gkobkrPkWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"904b5b2ec143094f942b0084779455edd28542a43102a15b6c0eab7fbfa87dc0","last_reissued_at":"2026-07-05T11:06:32.748307Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:32.748307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video-GPT via Next Clip Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Binxin Yang, Canmiao Fu, Chen Li, Chong Sun, Fangyikang Wang, Shaobin Zhuang, Yali Wang, Ying Zhang, Zhipeng Huang","submitted_at":"2025-05-18T16:22:58Z","abstract_excerpt":"GPT has shown its remarkable success in natural language processing. However, the language sequence is not sufficient to describe spatial-temporal details in the visual world. Alternatively, the video sequence is good at capturing such details. Motivated by this fact, we propose a concise Video-GPT in this paper by treating video as new language for visual world modeling. By analogy to next token prediction in GPT, we introduce a novel next clip diffusion paradigm for pretraining Video-GPT. Different from the previous works, this distinct paradigm allows Video-GPT to tackle both short-term gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12489","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/2505.12489/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":"2505.12489","created_at":"2026-07-05T11:06:32.748384+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12489v2","created_at":"2026-07-05T11:06:32.748384+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12489","created_at":"2026-07-05T11:06:32.748384+00:00"},{"alias_kind":"pith_short_12","alias_value":"SBFVWLWBIMEU","created_at":"2026-07-05T11:06:32.748384+00:00"},{"alias_kind":"pith_short_16","alias_value":"SBFVWLWBIMEU7FBL","created_at":"2026-07-05T11:06:32.748384+00:00"},{"alias_kind":"pith_short_8","alias_value":"SBFVWLWB","created_at":"2026-07-05T11:06:32.748384+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18943","citing_title":"Physics-IQ Verified","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16214","citing_title":"GAViD: A Large-Scale Multimodal Dataset for Context-Aware Group Affect Recognition from Videos","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16592","citing_title":"Human Cognition in Machines: A Unified Perspective of World Models","ref_index":237,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SBFVWLWBIMEU7FBLACCHPFCV5X","json":"https://pith.science/pith/SBFVWLWBIMEU7FBLACCHPFCV5X.json","graph_json":"https://pith.science/api/pith-number/SBFVWLWBIMEU7FBLACCHPFCV5X/graph.json","events_json":"https://pith.science/api/pith-number/SBFVWLWBIMEU7FBLACCHPFCV5X/events.json","paper":"https://pith.science/paper/SBFVWLWB"},"agent_actions":{"view_html":"https://pith.science/pith/SBFVWLWBIMEU7FBLACCHPFCV5X","download_json":"https://pith.science/pith/SBFVWLWBIMEU7FBLACCHPFCV5X.json","view_paper":"https://pith.science/paper/SBFVWLWB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12489&json=true","fetch_graph":"https://pith.science/api/pith-number/SBFVWLWBIMEU7FBLACCHPFCV5X/graph.json","fetch_events":"https://pith.science/api/pith-number/SBFVWLWBIMEU7FBLACCHPFCV5X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SBFVWLWBIMEU7FBLACCHPFCV5X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SBFVWLWBIMEU7FBLACCHPFCV5X/action/storage_attestation","attest_author":"https://pith.science/pith/SBFVWLWBIMEU7FBLACCHPFCV5X/action/author_attestation","sign_citation":"https://pith.science/pith/SBFVWLWBIMEU7FBLACCHPFCV5X/action/citation_signature","submit_replication":"https://pith.science/pith/SBFVWLWBIMEU7FBLACCHPFCV5X/action/replication_record"}},"created_at":"2026-07-05T11:06:32.748384+00:00","updated_at":"2026-07-05T11:06:32.748384+00:00"}