{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DLYS3JLSQZ7XFN6UTMP335JYMH","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":"06d3cea63da75478b679b7149446bd9cbffc660f5823cb66c6a73be4b375e780","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-12T18:09:04Z","title_canon_sha256":"6bad7dda4b8daf3536989115aef7ed15e5ad0ae7520f41cc9dbee5ef2d6176e5"},"schema_version":"1.0","source":{"id":"2605.12622","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12622","created_at":"2026-05-18T03:10:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12622v2","created_at":"2026-05-18T03:10:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12622","created_at":"2026-05-18T03:10:00Z"},{"alias_kind":"pith_short_12","alias_value":"DLYS3JLSQZ7X","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"DLYS3JLSQZ7XFN6U","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"DLYS3JLS","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:1a20002c0ed7ee58b38b6b6102f6a061230d535690a4893e053cd48fc0c0c9ec","target":"graph","created_at":"2026-05-18T03:10:00Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"SI achieves intent-faithful controllability to our knowledge for the first time in a fully end-to-end VLA: for a fixed scene, varying the intent class at inference yields qualitatively distinct yet consistently high-quality plans arising purely from data-driven learning without any pre-built trajectory bank or hand-coded post-hoc selector."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that the autoregressive chain-of-thought decoding causally derives semantically appropriate intent from scene understanding in a manner that enables generalization to arbitrary long-tail traffic scenes."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A new VLA model called SI uses a four-step chain-of-thought to derive driving intent and applies it via classifier-free guidance to a flow-matching trajectory generator, showing competitive Waymo scores and intent-controllable plans."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Streaming Intent lets an end-to-end driving model generate distinct, high-quality trajectories by deriving and steering with reasoned intent classes."}],"snapshot_sha256":"2ff0b60625f789855444061395dcb653a0cf013df6b64b5463feae599647adea"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"9a5252224309d98e3737eb2d44b0941adeb55c51181b6b1312a89bada01addf2"},"paper":{"abstract_excerpt":"We formalize action emergence as a target capability for end-to-end autonomous driving: the ability to generate physically feasible, semantically appropriate, and safety-compliant actions in arbitrary, long-tail traffic scenes through scene-conditioned reasoning rather than retrieval or interpolation of learned scene-action mappings. We show that previous paradigms cannot deliver action emergence: autoregressive trajectory decoders collapse the inherently multimodal future into a single averaged output, while diffusion and flow-matching generators express multimodality but are not steerable by","authors_text":"Benjin Zhu, Hengtong Lu, Jifeng Dai, Pengfei Jing, Victor Shea-Jay Huang, Xie Yan","cross_cats":["cs.CV"],"headline":"Streaming Intent lets an end-to-end driving model generate distinct, high-quality trajectories by deriving and steering with reasoned intent classes.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-12T18:09:04Z","title":"Action Emergence from Streaming Intent"},"references":{"count":65,"internal_anchors":9,"resolved_work":65,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Advances in Neural Information Processing Systems , year =","work_id":"83c92541-e6ba-485f-a1f7-db898d79f6d2","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Transactions on Machine Learning Research , year =","work_id":"532ecbf1-56d7-47c5-9913-d815bd63b1b9","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Wod-e2e: Waymo open dataset for end-to-end driving in challenging long-tail scenarios","work_id":"4a3f7018-e4da-4130-8356-de2679f76155","year":null},{"cited_arxiv_id":"2506.13757","doi":"","is_internal_anchor":true,"ref_index":4,"title":"AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning","work_id":"945172fb-0f3b-43be-88b4-ae61042517e9","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"arXiv preprint arXiv:2506.11234 (2025)","work_id":"b9c5c925-4544-4d63-aca5-0cabbb44906f","year":null}],"snapshot_sha256":"dbdbbd86bb982b58e3e2946575c23938653dc6d0ee2e64aab634fd48796f861e"},"source":{"id":"2605.12622","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T05:09:16.671310Z","id":"b02276a1-381f-4b6c-8f21-6aeed293c982","model_set":{"reader":"grok-4.3"},"one_line_summary":"A new VLA model called SI uses a four-step chain-of-thought to derive driving intent and applies it via classifier-free guidance to a flow-matching trajectory generator, showing competitive Waymo scores and intent-controllable plans.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Streaming Intent lets an end-to-end driving model generate distinct, high-quality trajectories by deriving and steering with reasoned intent classes.","strongest_claim":"SI achieves intent-faithful controllability to our knowledge for the first time in a fully end-to-end VLA: for a fixed scene, varying the intent class at inference yields qualitatively distinct yet consistently high-quality plans arising purely from data-driven learning without any pre-built trajectory bank or hand-coded post-hoc selector.","weakest_assumption":"The assumption that the autoregressive chain-of-thought decoding causally derives semantically appropriate intent from scene understanding in a manner that enables generalization to arbitrary long-tail traffic scenes."}},"verdict_id":"b02276a1-381f-4b6c-8f21-6aeed293c982"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:89b789ed7dff19aaee1fd51beaff194f5d75e3980d1a2538b527275eeccb2027","target":"record","created_at":"2026-05-18T03:10:00Z","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":"06d3cea63da75478b679b7149446bd9cbffc660f5823cb66c6a73be4b375e780","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-12T18:09:04Z","title_canon_sha256":"6bad7dda4b8daf3536989115aef7ed15e5ad0ae7520f41cc9dbee5ef2d6176e5"},"schema_version":"1.0","source":{"id":"2605.12622","kind":"arxiv","version":2}},"canonical_sha256":"1af12da572867f72b7d49b1fbdf53861f03c969f67bd14bfa560737527c09106","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1af12da572867f72b7d49b1fbdf53861f03c969f67bd14bfa560737527c09106","first_computed_at":"2026-05-18T03:10:00.425675Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:10:00.425675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cUxridRvOoGH1aq69VR/fK7yQnfx8LYFT80Mp045YfC5h8jtORqV2bLsOELvYM3CCwO4r+kH6PDnxWdmOmsoCg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:10:00.426504Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12622","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89b789ed7dff19aaee1fd51beaff194f5d75e3980d1a2538b527275eeccb2027","sha256:1a20002c0ed7ee58b38b6b6102f6a061230d535690a4893e053cd48fc0c0c9ec"],"state_sha256":"8e92cb802ebc5f55f248088dbabe6b8e07269749ba09faba670cec23248ac869"}