{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:47NZQJKUXNV7TJGINCL7Q6IAUZ","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":"81692509445b93349d972e9bd287c54acc3e0b08cb85d1eeb06aa6caafc1145c","cross_cats_sorted":["cs.CV","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-07T06:30:05Z","title_canon_sha256":"ff635ba172f86b5029f93dbc2c10677fcb8b9d4b9559ff96f67bc223742b108b"},"schema_version":"1.0","source":{"id":"2508.06571","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.06571","created_at":"2026-07-05T11:54:13Z"},{"alias_kind":"arxiv_version","alias_value":"2508.06571v3","created_at":"2026-07-05T11:54:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06571","created_at":"2026-07-05T11:54:13Z"},{"alias_kind":"pith_short_12","alias_value":"47NZQJKUXNV7","created_at":"2026-07-05T11:54:13Z"},{"alias_kind":"pith_short_16","alias_value":"47NZQJKUXNV7TJGI","created_at":"2026-07-05T11:54:13Z"},{"alias_kind":"pith_short_8","alias_value":"47NZQJKU","created_at":"2026-07-05T11:54:13Z"}],"graph_snapshots":[{"event_id":"sha256:52ed1bfcb929aa2e9cc16a00e24d5f784fc9fc06715670abaeb8f3ecae139890","target":"graph","created_at":"2026-07-05T11:54:13Z","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/2508.06571/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language-Action (VLA) models have demonstrated potential in autonomous driving. However, two critical challenges hinder their development: (1) Existing VLA architectures are typically based on imitation learning in open-loop setup which tends to capture the recorded behaviors in the dataset, leading to suboptimal and constrained performance, (2) Close-loop training relies heavily on high-fidelity sensor simulation, where domain gaps and computational inefficiencies pose significant barriers. In this paper, we introduce IRL-VLA, a novel close-loop Reinforcement Learning via \\textbf{I}nve","authors_text":"Anqing Jiang, Hao Jiang, Hao Sun, Jijun Wang, Jinhao Chai, Lijuan Zhu, Li Sun, Shichen Tang, Shuo Wang, Yiru Wang, Yu Gao, Yuwen Heng, Zhigang Sun, Zichong Gu","cross_cats":["cs.CV","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-07T06:30:05Z","title":"IRL-VLA: Training an Vision-Language-Action Policy via Reward World Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06571","kind":"arxiv","version":3},"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:b1dc5aa1f8389ac8fdebe7d0583d9317dd476ef339df0eb36f12e2d0f2ad98b2","target":"record","created_at":"2026-07-05T11:54:13Z","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":"81692509445b93349d972e9bd287c54acc3e0b08cb85d1eeb06aa6caafc1145c","cross_cats_sorted":["cs.CV","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-07T06:30:05Z","title_canon_sha256":"ff635ba172f86b5029f93dbc2c10677fcb8b9d4b9559ff96f67bc223742b108b"},"schema_version":"1.0","source":{"id":"2508.06571","kind":"arxiv","version":3}},"canonical_sha256":"e7db982554bb6bf9a4c86897f87900a65f1df2efe5b814e61e62edc1a10bb6de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7db982554bb6bf9a4c86897f87900a65f1df2efe5b814e61e62edc1a10bb6de","first_computed_at":"2026-07-05T11:54:13.448970Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:54:13.448970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MzX/QIgM6G5/kcB72Q+Ba6cpNSgN8BJZpyrCIRufe1FD+3GQtknjoPjbUDY77phlN/RhyndZjuw3dLnYj9x5AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:54:13.449455Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.06571","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1dc5aa1f8389ac8fdebe7d0583d9317dd476ef339df0eb36f12e2d0f2ad98b2","sha256:52ed1bfcb929aa2e9cc16a00e24d5f784fc9fc06715670abaeb8f3ecae139890"],"state_sha256":"12840bd2bc7ff5ee6f84f1059bdc46439fdfb271ebbd42336149b8ed9f049390"}