{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OJ3IFZYQQFBN5TXJPLFB3W4N5T","short_pith_number":"pith:OJ3IFZYQ","canonical_record":{"source":{"id":"2512.11061","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-11T19:21:47Z","cross_cats_sorted":[],"title_canon_sha256":"cfabeb35b70de4429fbbfb7db39454db90e55a340b620ddd72a3271ac14f447a","abstract_canon_sha256":"e858fcc65019a07d2525ef5950467da0fbbe6f2d06b99078fdf462882fd7314f"},"schema_version":"1.0"},"canonical_sha256":"727682e7108142decee97aca1ddb8decc81f5ec5869a3cfe7fd4004378f11162","source":{"kind":"arxiv","id":"2512.11061","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OJ3IFZYQQFBN5TXJPLFB3W4N5T","target":"record","payload":{"canonical_record":{"source":{"id":"2512.11061","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-11T19:21:47Z","cross_cats_sorted":[],"title_canon_sha256":"cfabeb35b70de4429fbbfb7db39454db90e55a340b620ddd72a3271ac14f447a","abstract_canon_sha256":"e858fcc65019a07d2525ef5950467da0fbbe6f2d06b99078fdf462882fd7314f"},"schema_version":"1.0"},"canonical_sha256":"727682e7108142decee97aca1ddb8decc81f5ec5869a3cfe7fd4004378f11162","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:50.623724Z","signature_b64":"gvBn9ZP7PvSgfsHjxIcN7nWcJGaSDHqJOifyV43hagR5W8h5w3iAJUzZ7tl/ilwuPqPYw2E4LZLr3Ulv4qPSCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"727682e7108142decee97aca1ddb8decc81f5ec5869a3cfe7fd4004378f11162","last_reissued_at":"2026-06-23T01:12:50.623102Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:50.623102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2512.11061","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":"2026-06-23T01:12:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2B6gJ3JkB5gbovza8rwrQaxjR640XzTXcPvyxlg4Jg1YhuazkoQiLIKnQ68QZsHma59QOKO74Oqsxjfm2M3iAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T15:27:32.822876Z"},"content_sha256":"1fd91b5e500d4f17a0817d6b6e15ff5b28803873ff5f7daba2339f704f0e1be0","schema_version":"1.0","event_id":"sha256:1fd91b5e500d4f17a0817d6b6e15ff5b28803873ff5f7daba2339f704f0e1be0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OJ3IFZYQQFBN5TXJPLFB3W4N5T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VDAWorld: World Modelling via VLM-Directed Abstraction and Simulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ayush Tewari, Felix O'Mahony, Roberto Cipolla","submitted_at":"2025-12-11T19:21:47Z","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) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.11061","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/2512.11061/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":"2026-06-23T01:12:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ogczBsH+J7BFlDwJzmth1r6sZc90VUSGAHXIViPHWGBv14HbI/lXJRPSS57KV4ApaPQjWHLXS5wtPWII2waEBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T15:27:32.823258Z"},"content_sha256":"117a271ca8f94f53bd06df0df1dcc60e12a19332b0b2571f63640b1a30b42d37","schema_version":"1.0","event_id":"sha256:117a271ca8f94f53bd06df0df1dcc60e12a19332b0b2571f63640b1a30b42d37"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OJ3IFZYQQFBN5TXJPLFB3W4N5T/bundle.json","state_url":"https://pith.science/pith/OJ3IFZYQQFBN5TXJPLFB3W4N5T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OJ3IFZYQQFBN5TXJPLFB3W4N5T/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":"2026-06-29T15:27:32Z","links":{"resolver":"https://pith.science/pith/OJ3IFZYQQFBN5TXJPLFB3W4N5T","bundle":"https://pith.science/pith/OJ3IFZYQQFBN5TXJPLFB3W4N5T/bundle.json","state":"https://pith.science/pith/OJ3IFZYQQFBN5TXJPLFB3W4N5T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OJ3IFZYQQFBN5TXJPLFB3W4N5T/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XYxXaYnJ4ypuX7+6aoGW24rNeHBu6BNkRAawB1d6X97HUZPHILTOTBPSLMsMZ+Uims8Epgrn8Yka014JEQurDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T15:27:32.825410Z","bundle_sha256":"540e86f3731a9563bc2e87969b2c37f92aee72489119779f5d7108e5a3883570"}}