{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OJ3IFZYQQFBN5TXJPLFB3W4N5T","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":"e858fcc65019a07d2525ef5950467da0fbbe6f2d06b99078fdf462882fd7314f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-11T19:21:47Z","title_canon_sha256":"cfabeb35b70de4429fbbfb7db39454db90e55a340b620ddd72a3271ac14f447a"},"schema_version":"1.0","source":{"id":"2512.11061","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.11061","created_at":"2026-06-23T01:12:50Z"},{"alias_kind":"arxiv_version","alias_value":"2512.11061v2","created_at":"2026-06-23T01:12:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.11061","created_at":"2026-06-23T01:12:50Z"},{"alias_kind":"pith_short_12","alias_value":"OJ3IFZYQQFBN","created_at":"2026-06-23T01:12:50Z"},{"alias_kind":"pith_short_16","alias_value":"OJ3IFZYQQFBN5TXJ","created_at":"2026-06-23T01:12:50Z"},{"alias_kind":"pith_short_8","alias_value":"OJ3IFZYQ","created_at":"2026-06-23T01:12:50Z"}],"graph_snapshots":[{"event_id":"sha256:117a271ca8f94f53bd06df0df1dcc60e12a19332b0b2571f63640b1a30b42d37","target":"graph","created_at":"2026-06-23T01:12:50Z","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/2512.11061/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative video models, a leading approach to world modelling, face fundamental limitations. They often violate physical and logical rules, lack interactivity, and operate as opaque black boxes ill-suited for building structured, queryable worlds. To overcome these challenges, we propose a new paradigm focused on distilling an image caption pair into a tractable, abstract representation optimized for simulation. We introduce VDAWorld, a framework where a Vision-Language Model (VLM) acts as an intelligent agent to orchestrate this process. The VLM autonomously constructs a grounded (2D or 3D) ","authors_text":"Ayush Tewari, Felix O'Mahony, Roberto Cipolla","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-11T19:21:47Z","title":"VDAWorld: World Modelling via VLM-Directed Abstraction and Simulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.11061","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":"sha256:1fd91b5e500d4f17a0817d6b6e15ff5b28803873ff5f7daba2339f704f0e1be0","target":"record","created_at":"2026-06-23T01:12:50Z","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":"e858fcc65019a07d2525ef5950467da0fbbe6f2d06b99078fdf462882fd7314f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-11T19:21:47Z","title_canon_sha256":"cfabeb35b70de4429fbbfb7db39454db90e55a340b620ddd72a3271ac14f447a"},"schema_version":"1.0","source":{"id":"2512.11061","kind":"arxiv","version":2}},"canonical_sha256":"727682e7108142decee97aca1ddb8decc81f5ec5869a3cfe7fd4004378f11162","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"727682e7108142decee97aca1ddb8decc81f5ec5869a3cfe7fd4004378f11162","first_computed_at":"2026-06-23T01:12:50.623102Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:12:50.623102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gvBn9ZP7PvSgfsHjxIcN7nWcJGaSDHqJOifyV43hagR5W8h5w3iAJUzZ7tl/ilwuPqPYw2E4LZLr3Ulv4qPSCg==","signature_status":"signed_v1","signed_at":"2026-06-23T01:12:50.623724Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.11061","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1fd91b5e500d4f17a0817d6b6e15ff5b28803873ff5f7daba2339f704f0e1be0","sha256:117a271ca8f94f53bd06df0df1dcc60e12a19332b0b2571f63640b1a30b42d37"],"state_sha256":"fa7412d4f7b7e232aca3c07d17d0121877d834ff69014fe03efec45334748fb1"}