{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KUM423SR63W5CHLCB5JQL7XCOA","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":"b1142824d02058844455b327d4b9cf0e776de1b19b5b9295e36ee69d35bbfeaf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-23T07:11:41Z","title_canon_sha256":"eeb504b79a1d522c2a215e277ddef1aed0640d630681125ae5e93ff18776bdf0"},"schema_version":"1.0","source":{"id":"2607.20988","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.20988","created_at":"2026-07-24T01:23:45Z"},{"alias_kind":"arxiv_version","alias_value":"2607.20988v1","created_at":"2026-07-24T01:23:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20988","created_at":"2026-07-24T01:23:45Z"},{"alias_kind":"pith_short_12","alias_value":"KUM423SR63W5","created_at":"2026-07-24T01:23:45Z"},{"alias_kind":"pith_short_16","alias_value":"KUM423SR63W5CHLC","created_at":"2026-07-24T01:23:45Z"},{"alias_kind":"pith_short_8","alias_value":"KUM423SR","created_at":"2026-07-24T01:23:45Z"}],"graph_snapshots":[{"event_id":"sha256:2eea0bb21ee0cf586a5011f54c87d3f9da3e480d4e6eab323afc2eb7b6af4c3c","target":"graph","created_at":"2026-07-24T01:23:45Z","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/2607.20988/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language-Action (VLA) models augmented with world modeling represent a promising paradigm for end-to-end autonomous driving. While pixel-level future prediction enables fine-grained spatiotemporal reasoning, it compromises robustness in noisy driving scenarios. Conversely, latent-based world models alleviate this sensitivity but often incur limited interpretability and representational degradation due to absent pixel-level grounding. To reconcile this trade-off, we propose HyWorldVLA, a hybrid world-VLA framework that unifies pixel-level supervision and latent representation learning. I","authors_text":"Hao Xu, Liulong Ma, Quanfu Yu, Xian Wu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-23T07:11:41Z","title":"HyWorldVLA: A Vision-Language-Action Model with Hybrid World Modeling for Autonomous Driving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20988","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":"sha256:8bb28931865e289a9b5ada5b5d9caaaedef85b6c66abea8d06f6f4aa0b66c422","target":"record","created_at":"2026-07-24T01:23:45Z","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":"b1142824d02058844455b327d4b9cf0e776de1b19b5b9295e36ee69d35bbfeaf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-23T07:11:41Z","title_canon_sha256":"eeb504b79a1d522c2a215e277ddef1aed0640d630681125ae5e93ff18776bdf0"},"schema_version":"1.0","source":{"id":"2607.20988","kind":"arxiv","version":1}},"canonical_sha256":"5519cd6e51f6edd11d620f5305fee2700597aa34b782e913703e68663b3bed85","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5519cd6e51f6edd11d620f5305fee2700597aa34b782e913703e68663b3bed85","first_computed_at":"2026-07-24T01:23:45.829025Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-24T01:23:45.829025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pCKNZpQhY3d6hnQr7k0MbS8lEfgcJpvbFEPkC3rrgxHPBa86xm5EU3bnLD5CtDpEiUWKAtVB9QkkjlPd0AywAg==","signature_status":"signed_v1","signed_at":"2026-07-24T01:23:45.829937Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.20988","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8bb28931865e289a9b5ada5b5d9caaaedef85b6c66abea8d06f6f4aa0b66c422","sha256:2eea0bb21ee0cf586a5011f54c87d3f9da3e480d4e6eab323afc2eb7b6af4c3c"],"state_sha256":"2bfdd9dbc76d0637d3f9d4428d13744de400a7347219c65cb0b5b5de5ba4d8d7"}