{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NEZZ5N6ZAFYUONX34ND2XGDYIT","short_pith_number":"pith:NEZZ5N6Z","schema_version":"1.0","canonical_sha256":"69339eb7d901714736fbe347ab987844e7df6f74a197ffaf43bb919d68606b9f","source":{"kind":"arxiv","id":"2606.31226","version":1},"attestation_state":"computed","paper":{"title":"ForgeDrive: Bidirectional Cross-Conditioning for Unified Visual-Action Generation in Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohua Wang, Chenxu Zhao, Congyang Zhao, Hangqi Fan, He Zheng, Leigang Luo, Tianxiong Lv, Xuchang Zhong, Yang Cai, Yushan Liu, Zhihao Liao","submitted_at":"2026-06-30T07:05:48Z","abstract_excerpt":"World-model-based autonomous driving endows the model with the ability to understand scene evolution. Yet this promise is undermined by the prevailing imagine-then-act paradigm, which allows errors from the more challenging visual generation stage to cascade into action planning. We introduce ForgeDrive, a unified autoregressive diffusion framework with visual-action cross-conditioning that closes this gap through act-then-imagine paradigm. ForgeDrive factorizes the future as a sequence of per-timestep frame-action pairs, intertwining each action with its corresponding visual observation. Duri"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.31226","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T07:05:48Z","cross_cats_sorted":[],"title_canon_sha256":"6b029f213b0cf4539c3c00528d027a949d63d32403876b16e8397bbc764f5f3f","abstract_canon_sha256":"a5cea5e5627c12b310d568fc926b34422270f1c87d81aa83b428544f8a933c29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:56.241834Z","signature_b64":"A+yoHqeR6lD1TC1R2k+a/P5MZ7gbLQvBd02dSTZhPaGqoKlHbZLwz+9QUV+DyE41bIo62Pb58/rJbeR0YMIsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69339eb7d901714736fbe347ab987844e7df6f74a197ffaf43bb919d68606b9f","last_reissued_at":"2026-07-01T01:17:56.241396Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:56.241396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ForgeDrive: Bidirectional Cross-Conditioning for Unified Visual-Action Generation in Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohua Wang, Chenxu Zhao, Congyang Zhao, Hangqi Fan, He Zheng, Leigang Luo, Tianxiong Lv, Xuchang Zhong, Yang Cai, Yushan Liu, Zhihao Liao","submitted_at":"2026-06-30T07:05:48Z","abstract_excerpt":"World-model-based autonomous driving endows the model with the ability to understand scene evolution. Yet this promise is undermined by the prevailing imagine-then-act paradigm, which allows errors from the more challenging visual generation stage to cascade into action planning. We introduce ForgeDrive, a unified autoregressive diffusion framework with visual-action cross-conditioning that closes this gap through act-then-imagine paradigm. ForgeDrive factorizes the future as a sequence of per-timestep frame-action pairs, intertwining each action with its corresponding visual observation. Duri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31226","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/2606.31226/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.31226","created_at":"2026-07-01T01:17:56.241456+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31226v1","created_at":"2026-07-01T01:17:56.241456+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31226","created_at":"2026-07-01T01:17:56.241456+00:00"},{"alias_kind":"pith_short_12","alias_value":"NEZZ5N6ZAFYU","created_at":"2026-07-01T01:17:56.241456+00:00"},{"alias_kind":"pith_short_16","alias_value":"NEZZ5N6ZAFYUONX3","created_at":"2026-07-01T01:17:56.241456+00:00"},{"alias_kind":"pith_short_8","alias_value":"NEZZ5N6Z","created_at":"2026-07-01T01:17:56.241456+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NEZZ5N6ZAFYUONX34ND2XGDYIT","json":"https://pith.science/pith/NEZZ5N6ZAFYUONX34ND2XGDYIT.json","graph_json":"https://pith.science/api/pith-number/NEZZ5N6ZAFYUONX34ND2XGDYIT/graph.json","events_json":"https://pith.science/api/pith-number/NEZZ5N6ZAFYUONX34ND2XGDYIT/events.json","paper":"https://pith.science/paper/NEZZ5N6Z"},"agent_actions":{"view_html":"https://pith.science/pith/NEZZ5N6ZAFYUONX34ND2XGDYIT","download_json":"https://pith.science/pith/NEZZ5N6ZAFYUONX34ND2XGDYIT.json","view_paper":"https://pith.science/paper/NEZZ5N6Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31226&json=true","fetch_graph":"https://pith.science/api/pith-number/NEZZ5N6ZAFYUONX34ND2XGDYIT/graph.json","fetch_events":"https://pith.science/api/pith-number/NEZZ5N6ZAFYUONX34ND2XGDYIT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NEZZ5N6ZAFYUONX34ND2XGDYIT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NEZZ5N6ZAFYUONX34ND2XGDYIT/action/storage_attestation","attest_author":"https://pith.science/pith/NEZZ5N6ZAFYUONX34ND2XGDYIT/action/author_attestation","sign_citation":"https://pith.science/pith/NEZZ5N6ZAFYUONX34ND2XGDYIT/action/citation_signature","submit_replication":"https://pith.science/pith/NEZZ5N6ZAFYUONX34ND2XGDYIT/action/replication_record"}},"created_at":"2026-07-01T01:17:56.241456+00:00","updated_at":"2026-07-01T01:17:56.241456+00:00"}