{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EOWIDIE3HJLLVWVUSNIWBV5J4K","short_pith_number":"pith:EOWIDIE3","schema_version":"1.0","canonical_sha256":"23ac81a09b3a56badab4935160d7a9e2908ab9faa3acf94ecdbc78e86344ab8c","source":{"kind":"arxiv","id":"2606.20110","version":1},"attestation_state":"computed","paper":{"title":"FrozenDrive: Zero-Shot Text-Guided Driving Scene Generation and Data Augmentation with Parameter-Free Frozen Diffusion Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daehyun We, Hyeonseong Kim, Hyun-Kurl Jang, Jinnyeong Yang, Kuk-Jin Yoon, Seonkyu Song, Youngho Yoon, Yuhwan Jeong","submitted_at":"2026-06-18T11:34:26Z","abstract_excerpt":"Synthetic data for autonomous driving is surging, powered by diffusion models that promise scalable scene generation. Yet key obstacles remain, as enforcing multi-view and temporal consistency often relies on backbone fine-tuning or added layers, which erodes pre-trained knowledge and weakens text alignment. Models also stay close to the training distribution, struggling under adverse weather and unseen configurations, and fidelity favors frequent over rare classes. We address these gaps with FrozenDrive, a controllable generative framework that preserves a pretrained diffusion models knowledg"},"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":"2606.20110","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T11:34:26Z","cross_cats_sorted":[],"title_canon_sha256":"47bfa1424290f41501513fd3be207239a1019b766062ee621b5733e2858baed9","abstract_canon_sha256":"a023df18bd24662870f18db958ce64a7acd325d8066033b2c68710659bcb1769"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:13:03.123290Z","signature_b64":"Z9KUTPIg7JDXO8g8SqcgihNstQue1glfSJT9yNRYr649leMX/fvZDWKQ3MoohzPpPZSPzPpQBYauTAZsbblqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23ac81a09b3a56badab4935160d7a9e2908ab9faa3acf94ecdbc78e86344ab8c","last_reissued_at":"2026-06-19T16:13:03.122868Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:13:03.122868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FrozenDrive: Zero-Shot Text-Guided Driving Scene Generation and Data Augmentation with Parameter-Free Frozen Diffusion Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daehyun We, Hyeonseong Kim, Hyun-Kurl Jang, Jinnyeong Yang, Kuk-Jin Yoon, Seonkyu Song, Youngho Yoon, Yuhwan Jeong","submitted_at":"2026-06-18T11:34:26Z","abstract_excerpt":"Synthetic data for autonomous driving is surging, powered by diffusion models that promise scalable scene generation. Yet key obstacles remain, as enforcing multi-view and temporal consistency often relies on backbone fine-tuning or added layers, which erodes pre-trained knowledge and weakens text alignment. Models also stay close to the training distribution, struggling under adverse weather and unseen configurations, and fidelity favors frequent over rare classes. We address these gaps with FrozenDrive, a controllable generative framework that preserves a pretrained diffusion models knowledg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20110","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/2606.20110/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":"2606.20110","created_at":"2026-06-19T16:13:03.122933+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20110v1","created_at":"2026-06-19T16:13:03.122933+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20110","created_at":"2026-06-19T16:13:03.122933+00:00"},{"alias_kind":"pith_short_12","alias_value":"EOWIDIE3HJLL","created_at":"2026-06-19T16:13:03.122933+00:00"},{"alias_kind":"pith_short_16","alias_value":"EOWIDIE3HJLLVWVU","created_at":"2026-06-19T16:13:03.122933+00:00"},{"alias_kind":"pith_short_8","alias_value":"EOWIDIE3","created_at":"2026-06-19T16:13:03.122933+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/EOWIDIE3HJLLVWVUSNIWBV5J4K","json":"https://pith.science/pith/EOWIDIE3HJLLVWVUSNIWBV5J4K.json","graph_json":"https://pith.science/api/pith-number/EOWIDIE3HJLLVWVUSNIWBV5J4K/graph.json","events_json":"https://pith.science/api/pith-number/EOWIDIE3HJLLVWVUSNIWBV5J4K/events.json","paper":"https://pith.science/paper/EOWIDIE3"},"agent_actions":{"view_html":"https://pith.science/pith/EOWIDIE3HJLLVWVUSNIWBV5J4K","download_json":"https://pith.science/pith/EOWIDIE3HJLLVWVUSNIWBV5J4K.json","view_paper":"https://pith.science/paper/EOWIDIE3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20110&json=true","fetch_graph":"https://pith.science/api/pith-number/EOWIDIE3HJLLVWVUSNIWBV5J4K/graph.json","fetch_events":"https://pith.science/api/pith-number/EOWIDIE3HJLLVWVUSNIWBV5J4K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EOWIDIE3HJLLVWVUSNIWBV5J4K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EOWIDIE3HJLLVWVUSNIWBV5J4K/action/storage_attestation","attest_author":"https://pith.science/pith/EOWIDIE3HJLLVWVUSNIWBV5J4K/action/author_attestation","sign_citation":"https://pith.science/pith/EOWIDIE3HJLLVWVUSNIWBV5J4K/action/citation_signature","submit_replication":"https://pith.science/pith/EOWIDIE3HJLLVWVUSNIWBV5J4K/action/replication_record"}},"created_at":"2026-06-19T16:13:03.122933+00:00","updated_at":"2026-06-19T16:13:03.122933+00:00"}