{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HNJ2C5W4ZVUXVILAXNE6ZRM32U","short_pith_number":"pith:HNJ2C5W4","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"},"canonical_sha256":"3b53a176dccd697aa160bb49ecc59bd5280ab5da50f88f04ae0144d3b09e5665","source":{"kind":"arxiv","id":"2509.02722","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02722","created_at":"2026-07-05T12:06:19Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02722v2","created_at":"2026-07-05T12:06:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02722","created_at":"2026-07-05T12:06:19Z"},{"alias_kind":"pith_short_12","alias_value":"HNJ2C5W4ZVUX","created_at":"2026-07-05T12:06:19Z"},{"alias_kind":"pith_short_16","alias_value":"HNJ2C5W4ZVUXVILA","created_at":"2026-07-05T12:06:19Z"},{"alias_kind":"pith_short_8","alias_value":"HNJ2C5W4","created_at":"2026-07-05T12:06:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HNJ2C5W4ZVUXVILAXNE6ZRM32U","target":"record","payload":{"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"},"canonical_sha256":"3b53a176dccd697aa160bb49ecc59bd5280ab5da50f88f04ae0144d3b09e5665","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"},"source_kind":"arxiv","source_id":"2509.02722","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:06:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nh9hPuC8yeZtxszI1Xvg9tcQuMiJDo80Cs5OzwLq14kFw1JrI2Q0zsHxE2G3Fcq6p+pFFCNUbzeLAFP1OvVgCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T15:07:09.302099Z"},"content_sha256":"82c6d5d32665ca484104aececfc9196e57635515bfd5ecfda4bbf7d7c2fedad8","schema_version":"1.0","event_id":"sha256:82c6d5d32665ca484104aececfc9196e57635515bfd5ecfda4bbf7d7c2fedad8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HNJ2C5W4ZVUXVILAXNE6ZRM32U","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:06:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4X4mIqgQSkDi6FLii67z4wm8xd7bisftaO4h/8OA18m64GnAxycA++T8QprELL4W9k8FJWRSsRAk2ISsmI5gCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T15:07:09.302642Z"},"content_sha256":"53a6adba7056b698ff1d27a61ecbfcde917a8b3daf6d47f0b0104f46b3ebcc84","schema_version":"1.0","event_id":"sha256:53a6adba7056b698ff1d27a61ecbfcde917a8b3daf6d47f0b0104f46b3ebcc84"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HNJ2C5W4ZVUXVILAXNE6ZRM32U/bundle.json","state_url":"https://pith.science/pith/HNJ2C5W4ZVUXVILAXNE6ZRM32U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HNJ2C5W4ZVUXVILAXNE6ZRM32U/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-12T15:07:09Z","links":{"resolver":"https://pith.science/pith/HNJ2C5W4ZVUXVILAXNE6ZRM32U","bundle":"https://pith.science/pith/HNJ2C5W4ZVUXVILAXNE6ZRM32U/bundle.json","state":"https://pith.science/pith/HNJ2C5W4ZVUXVILAXNE6ZRM32U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HNJ2C5W4ZVUXVILAXNE6ZRM32U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HNJ2C5W4ZVUXVILAXNE6ZRM32U","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":"710e7712459859b238bd2ed108dca75ac8f9edd74de65dff3d6961aafdccbd0d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-02T18:18:57Z","title_canon_sha256":"843ac127e038f08f1dedf7bf0dda971dd80da261ea6d59caca28d8c0ce59112e"},"schema_version":"1.0","source":{"id":"2509.02722","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02722","created_at":"2026-07-05T12:06:19Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02722v2","created_at":"2026-07-05T12:06:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02722","created_at":"2026-07-05T12:06:19Z"},{"alias_kind":"pith_short_12","alias_value":"HNJ2C5W4ZVUX","created_at":"2026-07-05T12:06:19Z"},{"alias_kind":"pith_short_16","alias_value":"HNJ2C5W4ZVUXVILA","created_at":"2026-07-05T12:06:19Z"},{"alias_kind":"pith_short_8","alias_value":"HNJ2C5W4","created_at":"2026-07-05T12:06:19Z"}],"graph_snapshots":[{"event_id":"sha256:53a6adba7056b698ff1d27a61ecbfcde917a8b3daf6d47f0b0104f46b3ebcc84","target":"graph","created_at":"2026-07-05T12:06:19Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2509.02722/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Allen Bolourchi, Delong Chen, Pascale Fung, Theo Moutakanni, Willy Chung, Yejin Bang, Ziwei Ji","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-02T18:18:57Z","title":"Planning with Reasoning using Vision Language World Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02722","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:82c6d5d32665ca484104aececfc9196e57635515bfd5ecfda4bbf7d7c2fedad8","target":"record","created_at":"2026-07-05T12:06:19Z","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":"710e7712459859b238bd2ed108dca75ac8f9edd74de65dff3d6961aafdccbd0d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-02T18:18:57Z","title_canon_sha256":"843ac127e038f08f1dedf7bf0dda971dd80da261ea6d59caca28d8c0ce59112e"},"schema_version":"1.0","source":{"id":"2509.02722","kind":"arxiv","version":2}},"canonical_sha256":"3b53a176dccd697aa160bb49ecc59bd5280ab5da50f88f04ae0144d3b09e5665","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b53a176dccd697aa160bb49ecc59bd5280ab5da50f88f04ae0144d3b09e5665","first_computed_at":"2026-07-05T12:06:19.961146Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:19.961146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iQXnOI+6PWQZbFJJY97SZKYf/TzO98Vt/cIyP0vykrQnktHuUazvtSJ26RnPjEHMq4lK1DVaJkJyuds0NPjCBw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:19.961636Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.02722","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82c6d5d32665ca484104aececfc9196e57635515bfd5ecfda4bbf7d7c2fedad8","sha256:53a6adba7056b698ff1d27a61ecbfcde917a8b3daf6d47f0b0104f46b3ebcc84"],"state_sha256":"174d17a453a41569916117cc755d5bcf73f57d93e1488ded7cb0c9c3c6f20f8f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4A83ghiB/FlVRHrTxvIRmk5Vc12ihAjv+RFIWMLvSx5xWeKSUXGHMqMX9O2TJd7TQL76//e1vv8Wk8tVuP4yCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T15:07:09.305285Z","bundle_sha256":"5f12ebd822b4c520815c96781f55e41cdd5d3efbe8cc19b03cff7f95dc07b0d7"}}