{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4YOKZKTWTJYRV2S7TJQQXPWGLU","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":"cbaf3caf64c5d6079b9abbc617b693aaa8138e636407b79124b12fd8e219ac15","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T14:36:26Z","title_canon_sha256":"f307a111066f462e5c62cc87efea06ca58a8a9c4dfeaafd9facfcfccb4223228"},"schema_version":"1.0","source":{"id":"2605.28544","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28544","created_at":"2026-05-28T02:04:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28544v1","created_at":"2026-05-28T02:04:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28544","created_at":"2026-05-28T02:04:55Z"},{"alias_kind":"pith_short_12","alias_value":"4YOKZKTWTJYR","created_at":"2026-05-28T02:04:55Z"},{"alias_kind":"pith_short_16","alias_value":"4YOKZKTWTJYRV2S7","created_at":"2026-05-28T02:04:55Z"},{"alias_kind":"pith_short_8","alias_value":"4YOKZKTW","created_at":"2026-05-28T02:04:55Z"}],"graph_snapshots":[{"event_id":"sha256:26d4516704f45223872af67d0a992d2b65b191ab538275d7fd3c840dc5085886","target":"graph","created_at":"2026-05-28T02:04:55Z","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/2605.28544/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretrained foundation models have become an important basis for end-to-end autonomous driving. In contrast to vision-language models pretrained primarily on static image-text pairs, video generative models capture temporal dynamics and motion priors that are naturally suited for driving. We present DriveWAM, a driving world-action model that adapts a pretrained video diffusion transformer into an autoregressive video-action policy. DriveWAM organizes video and action streams into a unified temporal token sequence and trains them under a joint flow-matching objective, preserving the pretrained ","authors_text":"Bo Zhang, Chen Shi, Jinrui Xu, Kehua Sheng, Li Jiang, Shaoshuai Shi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T14:36:26Z","title":"DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Driving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28544","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":"sha256:2c2c83b707df9fc83d421ad996d9ed74b4fabdd7eb552f7828bcaa208dbf6e74","target":"record","created_at":"2026-05-28T02:04:55Z","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":"cbaf3caf64c5d6079b9abbc617b693aaa8138e636407b79124b12fd8e219ac15","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T14:36:26Z","title_canon_sha256":"f307a111066f462e5c62cc87efea06ca58a8a9c4dfeaafd9facfcfccb4223228"},"schema_version":"1.0","source":{"id":"2605.28544","kind":"arxiv","version":1}},"canonical_sha256":"e61cacaa769a711aea5f9a610bbec65d0c596d02a41881564690ae0679068c20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e61cacaa769a711aea5f9a610bbec65d0c596d02a41881564690ae0679068c20","first_computed_at":"2026-05-28T02:04:55.922394Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T02:04:55.922394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mc3A7pux6WEf398cbEI1WLtvUjGkJjMmkFIMN1CatkhP4BFSg3Y0vps6lcldo0IbRjHAU1Kf3ihFqAoj2bKeBA==","signature_status":"signed_v1","signed_at":"2026-05-28T02:04:55.922823Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28544","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c2c83b707df9fc83d421ad996d9ed74b4fabdd7eb552f7828bcaa208dbf6e74","sha256:26d4516704f45223872af67d0a992d2b65b191ab538275d7fd3c840dc5085886"],"state_sha256":"a665e1eb5da3bc576f32bf236441b462a1e8dddba920eac16c1a05a91de3ce6d"}