{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BDLC7ME7EULMZBMMVGLL2XJRKR","short_pith_number":"pith:BDLC7ME7","schema_version":"1.0","canonical_sha256":"08d62fb09f2516cc858ca996bd5d31545f31f9102791c500a49fdf3561d907b8","source":{"kind":"arxiv","id":"2501.09781","version":2},"attestation_state":"computed","paper":{"title":"VideoWorld: Exploring Knowledge Learning from Unlabeled Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingyi Kang, Jiashi Feng, Xiaojie Jin, Xun Guo, Yao Zhao, Yunchao Wei, Zhongwei Ren","submitted_at":"2025-01-16T18:59:10Z","abstract_excerpt":"This work explores whether a deep generative model can learn complex knowledge solely from visual input, in contrast to the prevalent focus on text-based models like large language models (LLMs). We develop VideoWorld, an auto-regressive video generation model trained on unlabeled video data, and test its knowledge acquisition abilities in video-based Go and robotic control tasks. Our experiments reveal two key findings: (1) video-only training provides sufficient information for learning knowledge, including rules, reasoning and planning capabilities, and (2) the representation of visual chan"},"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":"2501.09781","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-16T18:59:10Z","cross_cats_sorted":[],"title_canon_sha256":"2f75d56b664ed6290c94b27d6201bd6a34fea24aeb6ffe5d228937fbe427f9bc","abstract_canon_sha256":"2316b416e7d1777926e4ca685c59b7569aa2c026755213aa2c663d6a72b60aff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:30.091174Z","signature_b64":"PkaRTqSbC7M69efInnkYwzbZdHDV3qn9CHDSEiGHtT22EBzzc71ZGxDTg1mMseXEruQJu7HTGAl2tExlQN9gAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08d62fb09f2516cc858ca996bd5d31545f31f9102791c500a49fdf3561d907b8","last_reissued_at":"2026-07-05T10:24:30.090746Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:30.090746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoWorld: Exploring Knowledge Learning from Unlabeled Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingyi Kang, Jiashi Feng, Xiaojie Jin, Xun Guo, Yao Zhao, Yunchao Wei, Zhongwei Ren","submitted_at":"2025-01-16T18:59:10Z","abstract_excerpt":"This work explores whether a deep generative model can learn complex knowledge solely from visual input, in contrast to the prevalent focus on text-based models like large language models (LLMs). We develop VideoWorld, an auto-regressive video generation model trained on unlabeled video data, and test its knowledge acquisition abilities in video-based Go and robotic control tasks. Our experiments reveal two key findings: (1) video-only training provides sufficient information for learning knowledge, including rules, reasoning and planning capabilities, and (2) the representation of visual chan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09781","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/2501.09781/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":"2501.09781","created_at":"2026-07-05T10:24:30.090809+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.09781v2","created_at":"2026-07-05T10:24:30.090809+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09781","created_at":"2026-07-05T10:24:30.090809+00:00"},{"alias_kind":"pith_short_12","alias_value":"BDLC7ME7EULM","created_at":"2026-07-05T10:24:30.090809+00:00"},{"alias_kind":"pith_short_16","alias_value":"BDLC7ME7EULMZBMM","created_at":"2026-07-05T10:24:30.090809+00:00"},{"alias_kind":"pith_short_8","alias_value":"BDLC7ME7","created_at":"2026-07-05T10:24:30.090809+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.11991","citing_title":"VGR: Visual Grounded Reasoning","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2505.12705","citing_title":"DreamGen: Unlocking Generalization in Robot Learning through Video World Models","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2503.14734","citing_title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","ref_index":79,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BDLC7ME7EULMZBMMVGLL2XJRKR","json":"https://pith.science/pith/BDLC7ME7EULMZBMMVGLL2XJRKR.json","graph_json":"https://pith.science/api/pith-number/BDLC7ME7EULMZBMMVGLL2XJRKR/graph.json","events_json":"https://pith.science/api/pith-number/BDLC7ME7EULMZBMMVGLL2XJRKR/events.json","paper":"https://pith.science/paper/BDLC7ME7"},"agent_actions":{"view_html":"https://pith.science/pith/BDLC7ME7EULMZBMMVGLL2XJRKR","download_json":"https://pith.science/pith/BDLC7ME7EULMZBMMVGLL2XJRKR.json","view_paper":"https://pith.science/paper/BDLC7ME7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.09781&json=true","fetch_graph":"https://pith.science/api/pith-number/BDLC7ME7EULMZBMMVGLL2XJRKR/graph.json","fetch_events":"https://pith.science/api/pith-number/BDLC7ME7EULMZBMMVGLL2XJRKR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BDLC7ME7EULMZBMMVGLL2XJRKR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BDLC7ME7EULMZBMMVGLL2XJRKR/action/storage_attestation","attest_author":"https://pith.science/pith/BDLC7ME7EULMZBMMVGLL2XJRKR/action/author_attestation","sign_citation":"https://pith.science/pith/BDLC7ME7EULMZBMMVGLL2XJRKR/action/citation_signature","submit_replication":"https://pith.science/pith/BDLC7ME7EULMZBMMVGLL2XJRKR/action/replication_record"}},"created_at":"2026-07-05T10:24:30.090809+00:00","updated_at":"2026-07-05T10:24:30.090809+00:00"}