{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:TBYNHKOVON6ACW24CEN5M4DERG","short_pith_number":"pith:TBYNHKOV","canonical_record":{"source":{"id":"2606.13460","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T15:15:34Z","cross_cats_sorted":[],"title_canon_sha256":"c1fd23de6e983a39f7de3edbc86083442d2c177efedcd5d3331e073172ae9acb","abstract_canon_sha256":"153e80ebe103fcc8480f1c9abc741cc0fb7101c7303cef027c61b981c86b3d82"},"schema_version":"1.0"},"canonical_sha256":"9870d3a9d5737c015b5c111bd6706489a95f638798f52588788b94b346ba283b","source":{"kind":"arxiv","id":"2606.13460","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.13460","created_at":"2026-06-12T01:10:03Z"},{"alias_kind":"arxiv_version","alias_value":"2606.13460v1","created_at":"2026-06-12T01:10:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13460","created_at":"2026-06-12T01:10:03Z"},{"alias_kind":"pith_short_12","alias_value":"TBYNHKOVON6A","created_at":"2026-06-12T01:10:03Z"},{"alias_kind":"pith_short_16","alias_value":"TBYNHKOVON6ACW24","created_at":"2026-06-12T01:10:03Z"},{"alias_kind":"pith_short_8","alias_value":"TBYNHKOV","created_at":"2026-06-12T01:10:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:TBYNHKOVON6ACW24CEN5M4DERG","target":"record","payload":{"canonical_record":{"source":{"id":"2606.13460","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T15:15:34Z","cross_cats_sorted":[],"title_canon_sha256":"c1fd23de6e983a39f7de3edbc86083442d2c177efedcd5d3331e073172ae9acb","abstract_canon_sha256":"153e80ebe103fcc8480f1c9abc741cc0fb7101c7303cef027c61b981c86b3d82"},"schema_version":"1.0"},"canonical_sha256":"9870d3a9d5737c015b5c111bd6706489a95f638798f52588788b94b346ba283b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:10:03.729960Z","signature_b64":"+tiHlXn6uFykUyOXvEwbSjDEyp7utj3wD1PavKVVsvq3R6VxWqXwfhy8j5Tl2T/cY/khzcOPCutJ8ZtkoYfRDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9870d3a9d5737c015b5c111bd6706489a95f638798f52588788b94b346ba283b","last_reissued_at":"2026-06-12T01:10:03.728943Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:10:03.728943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.13460","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-12T01:10:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gTqsK49XheVNDKVLmeCmkGhXXV/EolfLMPPI+boXXh4VRb5oGOITcRfTe4ny+J/jR/bWbw4FOcE49zyxw0mODQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T23:34:28.319956Z"},"content_sha256":"41d02f9b0dea4b8e8b6146031b336c7889b3ceb7fd1cf372d3812e524ea5464b","schema_version":"1.0","event_id":"sha256:41d02f9b0dea4b8e8b6146031b336c7889b3ceb7fd1cf372d3812e524ea5464b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:TBYNHKOVON6ACW24CEN5M4DERG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VISA: VLM-Guided Instance Semantic Auditing for 3D Occupancy World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dinesh Manocha, Jing Liang, Ruiqi Xian, Xuewei Qi, Yuehan Xian","submitted_at":"2026-06-11T15:15:34Z","abstract_excerpt":"Semantic 3D occupancy provides a voxelized world state for autonomous driving and robot decision making, but object and rare-class errors can affect free-space interpretation, collision checking, and temporal state propagation. We show that a common VLM strategy, aligning 3D voxel or object features with crop-caption embeddings, improves text-space similarity without reliably improving closed-set occupancy mIoU. Motivated by this mismatch, we propose VISA, a training-time semantic auditing approach for existing occupancy world models. VISA queries an offline VLM on a representative crop of eac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13460","kind":"arxiv","version":1},"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/2606.13460/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":"2026-06-12T01:10:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dBHIGFwGqu5OkTWCOWRaAygWUIu43MOCBKScDfQ9wPJI6xJN1q3BhwLI/mSzuFa0Yb/O2Wxs5JiRFEeNmSt1Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T23:34:28.320343Z"},"content_sha256":"2aee67465e2759efa91d07d69cae72ff4c20ed9a2196a45b98636241b8eba75d","schema_version":"1.0","event_id":"sha256:2aee67465e2759efa91d07d69cae72ff4c20ed9a2196a45b98636241b8eba75d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TBYNHKOVON6ACW24CEN5M4DERG/bundle.json","state_url":"https://pith.science/pith/TBYNHKOVON6ACW24CEN5M4DERG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TBYNHKOVON6ACW24CEN5M4DERG/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":"2026-06-30T23:34:28Z","links":{"resolver":"https://pith.science/pith/TBYNHKOVON6ACW24CEN5M4DERG","bundle":"https://pith.science/pith/TBYNHKOVON6ACW24CEN5M4DERG/bundle.json","state":"https://pith.science/pith/TBYNHKOVON6ACW24CEN5M4DERG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TBYNHKOVON6ACW24CEN5M4DERG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TBYNHKOVON6ACW24CEN5M4DERG","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":"153e80ebe103fcc8480f1c9abc741cc0fb7101c7303cef027c61b981c86b3d82","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T15:15:34Z","title_canon_sha256":"c1fd23de6e983a39f7de3edbc86083442d2c177efedcd5d3331e073172ae9acb"},"schema_version":"1.0","source":{"id":"2606.13460","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.13460","created_at":"2026-06-12T01:10:03Z"},{"alias_kind":"arxiv_version","alias_value":"2606.13460v1","created_at":"2026-06-12T01:10:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13460","created_at":"2026-06-12T01:10:03Z"},{"alias_kind":"pith_short_12","alias_value":"TBYNHKOVON6A","created_at":"2026-06-12T01:10:03Z"},{"alias_kind":"pith_short_16","alias_value":"TBYNHKOVON6ACW24","created_at":"2026-06-12T01:10:03Z"},{"alias_kind":"pith_short_8","alias_value":"TBYNHKOV","created_at":"2026-06-12T01:10:03Z"}],"graph_snapshots":[{"event_id":"sha256:2aee67465e2759efa91d07d69cae72ff4c20ed9a2196a45b98636241b8eba75d","target":"graph","created_at":"2026-06-12T01:10:03Z","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/2606.13460/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Semantic 3D occupancy provides a voxelized world state for autonomous driving and robot decision making, but object and rare-class errors can affect free-space interpretation, collision checking, and temporal state propagation. We show that a common VLM strategy, aligning 3D voxel or object features with crop-caption embeddings, improves text-space similarity without reliably improving closed-set occupancy mIoU. Motivated by this mismatch, we propose VISA, a training-time semantic auditing approach for existing occupancy world models. VISA queries an offline VLM on a representative crop of eac","authors_text":"Dinesh Manocha, Jing Liang, Ruiqi Xian, Xuewei Qi, Yuehan Xian","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T15:15:34Z","title":"VISA: VLM-Guided Instance Semantic Auditing for 3D Occupancy World Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13460","kind":"arxiv","version":1},"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":"sha256:41d02f9b0dea4b8e8b6146031b336c7889b3ceb7fd1cf372d3812e524ea5464b","target":"record","created_at":"2026-06-12T01:10:03Z","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":"153e80ebe103fcc8480f1c9abc741cc0fb7101c7303cef027c61b981c86b3d82","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T15:15:34Z","title_canon_sha256":"c1fd23de6e983a39f7de3edbc86083442d2c177efedcd5d3331e073172ae9acb"},"schema_version":"1.0","source":{"id":"2606.13460","kind":"arxiv","version":1}},"canonical_sha256":"9870d3a9d5737c015b5c111bd6706489a95f638798f52588788b94b346ba283b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9870d3a9d5737c015b5c111bd6706489a95f638798f52588788b94b346ba283b","first_computed_at":"2026-06-12T01:10:03.728943Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:10:03.728943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+tiHlXn6uFykUyOXvEwbSjDEyp7utj3wD1PavKVVsvq3R6VxWqXwfhy8j5Tl2T/cY/khzcOPCutJ8ZtkoYfRDw==","signature_status":"signed_v1","signed_at":"2026-06-12T01:10:03.729960Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.13460","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41d02f9b0dea4b8e8b6146031b336c7889b3ceb7fd1cf372d3812e524ea5464b","sha256:2aee67465e2759efa91d07d69cae72ff4c20ed9a2196a45b98636241b8eba75d"],"state_sha256":"7f082bee625d1c03c11ea67202eeda0eff0b6e4afe69c492ca82d568d4374681"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TqbgQrvpFFGGBLCW4XbEJa7Q/3ZSXcFo7hJ1XTDUime38Iw5Jg99IUgN8XwwB0Z+zxhbzT95oyqkdZzkiLekCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T23:34:28.322439Z","bundle_sha256":"fab8dac321b4dfc7e5851214e94594a01498da0ab64f6938680f05c4781244e5"}}