{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HNJ2C5W4ZVUXVILAXNE6ZRM32U","short_pith_number":"pith:HNJ2C5W4","schema_version":"1.0","canonical_sha256":"3b53a176dccd697aa160bb49ecc59bd5280ab5da50f88f04ae0144d3b09e5665","source":{"kind":"arxiv","id":"2509.02722","version":2},"attestation_state":"computed","paper":{"title":"Planning with Reasoning using Vision Language World Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Allen Bolourchi, Delong Chen, Pascale Fung, Theo Moutakanni, Willy Chung, Yejin Bang, Ziwei Ji","submitted_at":"2025-09-02T18:18:57Z","abstract_excerpt":"Effective planning requires strong world models, but high-level world models that can understand and reason about actions with semantic and temporal abstraction remain largely underdeveloped. We introduce the Vision Language World Model (VLWM), a foundation model trained for language-based world modeling on natural videos. Given visual observations, the VLWM first infers the overall goal achievements then predicts a trajectory composed of interleaved actions and world state changes. Those targets are extracted by iterative LLM Self-Refine conditioned on compressed future observations represent"},"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":"2509.02722","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-02T18:18:57Z","cross_cats_sorted":[],"title_canon_sha256":"843ac127e038f08f1dedf7bf0dda971dd80da261ea6d59caca28d8c0ce59112e","abstract_canon_sha256":"710e7712459859b238bd2ed108dca75ac8f9edd74de65dff3d6961aafdccbd0d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:19.961636Z","signature_b64":"iQXnOI+6PWQZbFJJY97SZKYf/TzO98Vt/cIyP0vykrQnktHuUazvtSJ26RnPjEHMq4lK1DVaJkJyuds0NPjCBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b53a176dccd697aa160bb49ecc59bd5280ab5da50f88f04ae0144d3b09e5665","last_reissued_at":"2026-07-05T12:06:19.961146Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:19.961146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Planning with Reasoning using Vision Language World Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Allen Bolourchi, Delong Chen, Pascale Fung, Theo Moutakanni, Willy Chung, Yejin Bang, Ziwei Ji","submitted_at":"2025-09-02T18:18:57Z","abstract_excerpt":"Effective planning requires strong world models, but high-level world models that can understand and reason about actions with semantic and temporal abstraction remain largely underdeveloped. We introduce the Vision Language World Model (VLWM), a foundation model trained for language-based world modeling on natural videos. Given visual observations, the VLWM first infers the overall goal achievements then predicts a trajectory composed of interleaved actions and world state changes. Those targets are extracted by iterative LLM Self-Refine conditioned on compressed future observations represent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02722","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/2509.02722/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":"2509.02722","created_at":"2026-07-05T12:06:19.961197+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.02722v2","created_at":"2026-07-05T12:06:19.961197+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02722","created_at":"2026-07-05T12:06:19.961197+00:00"},{"alias_kind":"pith_short_12","alias_value":"HNJ2C5W4ZVUX","created_at":"2026-07-05T12:06:19.961197+00:00"},{"alias_kind":"pith_short_16","alias_value":"HNJ2C5W4ZVUXVILA","created_at":"2026-07-05T12:06:19.961197+00:00"},{"alias_kind":"pith_short_8","alias_value":"HNJ2C5W4","created_at":"2026-07-05T12:06:19.961197+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.06925","citing_title":"Grounding Spatial Relations in a Compact World Model: Instruction Leakage and a Goal-Free Dynamics Fix","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2607.06018","citing_title":"RoboTALES: Learning Reasoning-Guided Robot Policies via Task-Aligned Simulated Futures","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2606.00133","citing_title":"World Models: A Comprehensive Survey of Architectures, Methodologies, Reasoning Paradigms, and Applications","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12191","citing_title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","ref_index":207,"is_internal_anchor":false},{"citing_arxiv_id":"2602.23058","citing_title":"GeoWorld: Geometric World Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20388","citing_title":"How You Move Tells What You'll Do: Trajectory-Conditioned Egocentric Prediction","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19976","citing_title":"RECIPE: Procedural Planning via Grounding in Instructional Video","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20899","citing_title":"Concepts in Motion: Temporal Concept Bottleneck Model for Interpretable Video Classification","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2511.00062","citing_title":"World Simulation with Video Foundation Models for Physical AI","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09037","citing_title":"SiMing-Bench: Evaluating Procedural Correctness from Continuous Interactions in Clinical Skill Videos","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07079","citing_title":"Learning Visual Feature-Based World Models via Residual Latent Action","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HNJ2C5W4ZVUXVILAXNE6ZRM32U","json":"https://pith.science/pith/HNJ2C5W4ZVUXVILAXNE6ZRM32U.json","graph_json":"https://pith.science/api/pith-number/HNJ2C5W4ZVUXVILAXNE6ZRM32U/graph.json","events_json":"https://pith.science/api/pith-number/HNJ2C5W4ZVUXVILAXNE6ZRM32U/events.json","paper":"https://pith.science/paper/HNJ2C5W4"},"agent_actions":{"view_html":"https://pith.science/pith/HNJ2C5W4ZVUXVILAXNE6ZRM32U","download_json":"https://pith.science/pith/HNJ2C5W4ZVUXVILAXNE6ZRM32U.json","view_paper":"https://pith.science/paper/HNJ2C5W4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.02722&json=true","fetch_graph":"https://pith.science/api/pith-number/HNJ2C5W4ZVUXVILAXNE6ZRM32U/graph.json","fetch_events":"https://pith.science/api/pith-number/HNJ2C5W4ZVUXVILAXNE6ZRM32U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HNJ2C5W4ZVUXVILAXNE6ZRM32U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HNJ2C5W4ZVUXVILAXNE6ZRM32U/action/storage_attestation","attest_author":"https://pith.science/pith/HNJ2C5W4ZVUXVILAXNE6ZRM32U/action/author_attestation","sign_citation":"https://pith.science/pith/HNJ2C5W4ZVUXVILAXNE6ZRM32U/action/citation_signature","submit_replication":"https://pith.science/pith/HNJ2C5W4ZVUXVILAXNE6ZRM32U/action/replication_record"}},"created_at":"2026-07-05T12:06:19.961197+00:00","updated_at":"2026-07-05T12:06:19.961197+00:00"}