{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AB5OYI3QWC6J5DBHFP374UCGTC","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":"21c914ce64dfc70a482581f938246ca5411da0dccdb7629a162004911adf78f4","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-24T17:17:27Z","title_canon_sha256":"71d3cd4322b4002941d6b5b5741e8571148bd602b0cb7ea08d2b9a2ffff8c90e"},"schema_version":"1.0","source":{"id":"2509.20328","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.20328","created_at":"2026-05-18T02:40:55Z"},{"alias_kind":"arxiv_version","alias_value":"2509.20328v2","created_at":"2026-05-18T02:40:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.20328","created_at":"2026-05-18T02:40:55Z"},{"alias_kind":"pith_short_12","alias_value":"AB5OYI3QWC6J","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"AB5OYI3QWC6J5DBH","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"AB5OYI3Q","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:ade2542507aec44d6686dd45f531b3d01a32e8ad610c9433fc0f43ec72880dfc","target":"graph","created_at":"2026-05-18T02:40:55Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Veo 3 can solve a broad variety of tasks it wasn't explicitly trained for: segmenting objects, detecting edges, editing images, understanding physical properties, recognizing object affordances, simulating tool use, and more. These abilities enable early forms of visual reasoning like maze and symmetry solving."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the demonstrated capabilities are genuinely zero-shot and not the result of implicit task information in the prompts, data contamination, or post-hoc selection of successful examples."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Generative video models exhibit emergent zero-shot capabilities across perception, manipulation, and basic reasoning tasks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Generative video models like Veo 3 perform zero-shot object segmentation, edge detection, physics understanding, affordance recognition, tool simulation, and early visual reasoning such as maze and symmetry solving."}],"snapshot_sha256":"ff0c595c84bd51c5e2400df16dae0c52e3aeab41d2f12f05e722417cba55e8d9"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"72b87a91f7f0f708c7eea993a55ddf90800983ff1e85b7072e7aead1f82d25f4"},"paper":{"abstract_excerpt":"The remarkable zero-shot capabilities of Large Language Models (LLMs) have propelled natural language processing from task-specific models to unified, generalist foundation models. This transformation emerged from simple primitives: large, generative models trained on web-scale data. Curiously, the same primitives apply to today's generative video models. Could video models be on a trajectory towards general-purpose vision understanding, much like LLMs developed general-purpose language understanding? We demonstrate that Veo 3 can solve a broad variety of tasks it wasn't explicitly trained for","authors_text":"Been Kim, Kevin Swersky, Nick Matarese, Paul Vicol, Priyank Jaini, Robert Geirhos, Shixiang Shane Gu, Thadd\\\"aus Wiedemer, Yuxuan Li","cross_cats":["cs.AI","cs.CV","cs.RO"],"headline":"Generative video models like Veo 3 perform zero-shot object segmentation, edge detection, physics understanding, affordance recognition, tool simulation, and early visual reasoning such as maze and symmetry solving.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-24T17:17:27Z","title":"Video models are zero-shot learners and reasoners"},"references":{"count":98,"internal_anchors":15,"resolved_work":98,"sample":[{"cited_arxiv_id":"2406.00515","doi":"","is_internal_anchor":true,"ref_index":1,"title":"A Survey on Large Language Models for Code Generation","work_id":"7d829146-3160-44c7-9ce4-4201ed9b654c","year":2024},{"cited_arxiv_id":"2507.06261","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","work_id":"008df105-2fdd-45d8-857a-8e35868aecb6","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Weaver: Foundation models for creative writing","work_id":"1d3d18bc-fb96-451d-b2e5-aec2c15eb603","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Multilingual machine translation with large language models: Empirical results and analysis","work_id":"8aedba3a-0fa4-4db0-94b7-ed63580404df","year":2023},{"cited_arxiv_id":"2408.06292","doi":"","is_internal_anchor":true,"ref_index":5,"title":"The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery","work_id":"56b6b58d-e73a-4317-896e-36ac5f84e957","year":2024}],"snapshot_sha256":"f08f5b262f8e19d6e3a421f4ce2444e499a2bf0eed658cf2405abffc07e7ee8f"},"source":{"id":"2509.20328","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-14T02:11:09.410472Z","id":"5e2c70ea-d0de-416b-a455-834dd2668077","model_set":{"reader":"grok-4.3"},"one_line_summary":"Generative video models exhibit emergent zero-shot capabilities across perception, manipulation, and basic reasoning tasks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Generative video models like Veo 3 perform zero-shot object segmentation, edge detection, physics understanding, affordance recognition, tool simulation, and early visual reasoning such as maze and symmetry solving.","strongest_claim":"Veo 3 can solve a broad variety of tasks it wasn't explicitly trained for: segmenting objects, detecting edges, editing images, understanding physical properties, recognizing object affordances, simulating tool use, and more. These abilities enable early forms of visual reasoning like maze and symmetry solving.","weakest_assumption":"That the demonstrated capabilities are genuinely zero-shot and not the result of implicit task information in the prompts, data contamination, or post-hoc selection of successful examples."}},"verdict_id":"5e2c70ea-d0de-416b-a455-834dd2668077"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:826ec5a4aa563d61e4bba6c8b70c212c049adc6ea76f42ce5aed39cfbe3d17e8","target":"record","created_at":"2026-05-18T02:40:55Z","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":"21c914ce64dfc70a482581f938246ca5411da0dccdb7629a162004911adf78f4","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-24T17:17:27Z","title_canon_sha256":"71d3cd4322b4002941d6b5b5741e8571148bd602b0cb7ea08d2b9a2ffff8c90e"},"schema_version":"1.0","source":{"id":"2509.20328","kind":"arxiv","version":2}},"canonical_sha256":"007aec2370b0bc9e8c272bf7fe504698857211fc963f2d5295a18ea4842ad671","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"007aec2370b0bc9e8c272bf7fe504698857211fc963f2d5295a18ea4842ad671","first_computed_at":"2026-05-18T02:40:55.632229Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:40:55.632229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jLxpoau8yw7togBodVcjwoadkRSwXywr8D2V62GegU1mnHfNB0EnfxjxGYgw72bJJt0obkD1eW1A5ulK3tfrCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:40:55.632905Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.20328","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:826ec5a4aa563d61e4bba6c8b70c212c049adc6ea76f42ce5aed39cfbe3d17e8","sha256:ade2542507aec44d6686dd45f531b3d01a32e8ad610c9433fc0f43ec72880dfc"],"state_sha256":"5eb6b0758163f3c34ebcdf68d9d003e6c4377de19c8f5867ab59a6c155e718ad"}