{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7IPDXT2VRQT3CDT62P3ZAYVWOM","short_pith_number":"pith:7IPDXT2V","schema_version":"1.0","canonical_sha256":"fa1e3bcf558c27b10e7ed3f79062b6733d5e9041610070b92b54551b9cc6911b","source":{"kind":"arxiv","id":"2104.15060","version":1},"attestation_state":"computed","paper":{"title":"DriveGAN: Towards a Controllable High-Quality Neural Simulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Antonio Torralba, Jonah Philion, Sanja Fidler, Seung Wook Kim","submitted_at":"2021-04-30T15:30:05Z","abstract_excerpt":"Realistic simulators are critical for training and verifying robotics systems. While most of the contemporary simulators are hand-crafted, a scaleable way to build simulators is to use machine learning to learn how the environment behaves in response to an action, directly from data. In this work, we aim to learn to simulate a dynamic environment directly in pixel-space, by watching unannotated sequences of frames and their associated action pairs. We introduce a novel high-quality neural simulator referred to as DriveGAN that achieves controllability by disentangling different components with"},"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":"2104.15060","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-30T15:30:05Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"cd3c038da726e935c57f2c0759bb3602016a10759bfafec2ef194deda711f84f","abstract_canon_sha256":"483a8c2f570ff54f54bdbc3fdada0e3d48372932874650053ad54d729b13bdc8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:36:29.530595Z","signature_b64":"On78URFforPglsTUnzBUPEE5aiRz/Ror+1oSFXtT6kn46qiQdFFJ7LAirykFFx4Sk9RqCUrijhWDOgR8vTIMCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa1e3bcf558c27b10e7ed3f79062b6733d5e9041610070b92b54551b9cc6911b","last_reissued_at":"2026-07-05T02:36:29.530143Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:36:29.530143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DriveGAN: Towards a Controllable High-Quality Neural Simulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Antonio Torralba, Jonah Philion, Sanja Fidler, Seung Wook Kim","submitted_at":"2021-04-30T15:30:05Z","abstract_excerpt":"Realistic simulators are critical for training and verifying robotics systems. While most of the contemporary simulators are hand-crafted, a scaleable way to build simulators is to use machine learning to learn how the environment behaves in response to an action, directly from data. In this work, we aim to learn to simulate a dynamic environment directly in pixel-space, by watching unannotated sequences of frames and their associated action pairs. We introduce a novel high-quality neural simulator referred to as DriveGAN that achieves controllability by disentangling different components with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.15060","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/2104.15060/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":"2104.15060","created_at":"2026-07-05T02:36:29.530195+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.15060v1","created_at":"2026-07-05T02:36:29.530195+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.15060","created_at":"2026-07-05T02:36:29.530195+00:00"},{"alias_kind":"pith_short_12","alias_value":"7IPDXT2VRQT3","created_at":"2026-07-05T02:36:29.530195+00:00"},{"alias_kind":"pith_short_16","alias_value":"7IPDXT2VRQT3CDT6","created_at":"2026-07-05T02:36:29.530195+00:00"},{"alias_kind":"pith_short_8","alias_value":"7IPDXT2V","created_at":"2026-07-05T02:36:29.530195+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31109","citing_title":"InfiniVerse: Occupancy Guided Unbounded Scene Generation for Autonomous Driving","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7IPDXT2VRQT3CDT62P3ZAYVWOM","json":"https://pith.science/pith/7IPDXT2VRQT3CDT62P3ZAYVWOM.json","graph_json":"https://pith.science/api/pith-number/7IPDXT2VRQT3CDT62P3ZAYVWOM/graph.json","events_json":"https://pith.science/api/pith-number/7IPDXT2VRQT3CDT62P3ZAYVWOM/events.json","paper":"https://pith.science/paper/7IPDXT2V"},"agent_actions":{"view_html":"https://pith.science/pith/7IPDXT2VRQT3CDT62P3ZAYVWOM","download_json":"https://pith.science/pith/7IPDXT2VRQT3CDT62P3ZAYVWOM.json","view_paper":"https://pith.science/paper/7IPDXT2V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.15060&json=true","fetch_graph":"https://pith.science/api/pith-number/7IPDXT2VRQT3CDT62P3ZAYVWOM/graph.json","fetch_events":"https://pith.science/api/pith-number/7IPDXT2VRQT3CDT62P3ZAYVWOM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7IPDXT2VRQT3CDT62P3ZAYVWOM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7IPDXT2VRQT3CDT62P3ZAYVWOM/action/storage_attestation","attest_author":"https://pith.science/pith/7IPDXT2VRQT3CDT62P3ZAYVWOM/action/author_attestation","sign_citation":"https://pith.science/pith/7IPDXT2VRQT3CDT62P3ZAYVWOM/action/citation_signature","submit_replication":"https://pith.science/pith/7IPDXT2VRQT3CDT62P3ZAYVWOM/action/replication_record"}},"created_at":"2026-07-05T02:36:29.530195+00:00","updated_at":"2026-07-05T02:36:29.530195+00:00"}