{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SSPO5RS53NJVPCP252JKHVNA4X","short_pith_number":"pith:SSPO5RS5","schema_version":"1.0","canonical_sha256":"949eeec65ddb535789faee92a3d5a0e5e7908869fa49fa8deb0fb4ef9331d4dd","source":{"kind":"arxiv","id":"2510.24108","version":2},"attestation_state":"computed","paper":{"title":"Zero-Human Demonstration End-to-end Autonomous Driving with Trajectory Scorer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Jingde Chen, Jingyu Song, Jose M. Alvarez, Kailin Li, Maying Shen, Nadine Chang, Shiyi Lan, Wenhao Yao, Xinglong Sun, Zhenxin Li, Zi Wang, Zuxuan Wu","submitted_at":"2025-10-28T06:26:36Z","abstract_excerpt":"Human demonstrations are widely considered the cornerstone of end-to-end (E2E) autonomous driving despite human demonstration's scarcity for long-tail and safety-critical scenarios. Nonetheless, current E2E autonomous driving (AD) training paradigms continue to rely on human demonstrations. Imitation learning (IL) requires human demonstrations for training, whereas reinforcement learning (RL) has emerged as a promising alternative to reduce this dependency. However, most existing RL methods for E2E AD still rely implicitly on human demonstrations. A pure rewards-based RL method can overcome th"},"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":"2510.24108","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-10-28T06:26:36Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"adbee29fcfb86048494ffd60983af3550381898896f65f4cbbfb78da75702a77","abstract_canon_sha256":"9c09eaa43f71b3eb0f980b8183b5c4b35710384d71d15e9a6845d9e91056a8eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T01:19:48.520701Z","signature_b64":"Qjq+dfvRLk1OS5myZct/x2TOd0pIj1kCJ5Bld0Sl5mZ2yBrKnZkxI9g9EEVdiw1pBOhkZs2MRtRW8A/2I2YoCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"949eeec65ddb535789faee92a3d5a0e5e7908869fa49fa8deb0fb4ef9331d4dd","last_reissued_at":"2026-07-09T01:19:48.520135Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T01:19:48.520135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Human Demonstration End-to-end Autonomous Driving with Trajectory Scorer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Jingde Chen, Jingyu Song, Jose M. Alvarez, Kailin Li, Maying Shen, Nadine Chang, Shiyi Lan, Wenhao Yao, Xinglong Sun, Zhenxin Li, Zi Wang, Zuxuan Wu","submitted_at":"2025-10-28T06:26:36Z","abstract_excerpt":"Human demonstrations are widely considered the cornerstone of end-to-end (E2E) autonomous driving despite human demonstration's scarcity for long-tail and safety-critical scenarios. Nonetheless, current E2E autonomous driving (AD) training paradigms continue to rely on human demonstrations. Imitation learning (IL) requires human demonstrations for training, whereas reinforcement learning (RL) has emerged as a promising alternative to reduce this dependency. However, most existing RL methods for E2E AD still rely implicitly on human demonstrations. A pure rewards-based RL method can overcome th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.24108","kind":"arxiv","version":2},"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/2510.24108/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":"2510.24108","created_at":"2026-07-09T01:19:48.520192+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.24108v2","created_at":"2026-07-09T01:19:48.520192+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.24108","created_at":"2026-07-09T01:19:48.520192+00:00"},{"alias_kind":"pith_short_12","alias_value":"SSPO5RS53NJV","created_at":"2026-07-09T01:19:48.520192+00:00"},{"alias_kind":"pith_short_16","alias_value":"SSPO5RS53NJVPCP2","created_at":"2026-07-09T01:19:48.520192+00:00"},{"alias_kind":"pith_short_8","alias_value":"SSPO5RS5","created_at":"2026-07-09T01:19:48.520192+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":11,"sample":[{"citing_arxiv_id":"2606.20458","citing_title":"Slow Brain, Fast Planner: Latency-Resilient VLM-Augmented Urban Navigation","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2606.19641","citing_title":"Scaling Self-Play for End-to-End Driving","ref_index":94,"is_internal_anchor":true},{"citing_arxiv_id":"2606.17362","citing_title":"DriveJudge: Rethinking Autonomous Driving Evaluation with Vision-Language Models","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2606.07170","citing_title":"Test-Time Trajectory Optimization for Autonomous Driving","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2606.31830","citing_title":"PriorEye: Geospatial Visual Priors for End-to-End Autonomous Driving","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2604.28111","citing_title":"GSDrive: Reinforcing Driving Policies by Multi-mode Future Trajectory Probing with 3D Gaussian Splatting Environment","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2511.23369","citing_title":"SimScale: Learning to Drive via Real-World Simulation at Scale","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2604.28111","citing_title":"GSDrive: Reinforcing Driving Policies by Multi-mode Future Trajectory Probing with 3D Gaussian Splatting Environment","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09701","citing_title":"DriveFuture: Future-Aware Latent World Models for Autonomous Driving","ref_index":56,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10856","citing_title":"BridgeSim: Unveiling the OL-CL Gap in End-to-End Autonomous Driving","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15308","citing_title":"RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SSPO5RS53NJVPCP252JKHVNA4X","json":"https://pith.science/pith/SSPO5RS53NJVPCP252JKHVNA4X.json","graph_json":"https://pith.science/api/pith-number/SSPO5RS53NJVPCP252JKHVNA4X/graph.json","events_json":"https://pith.science/api/pith-number/SSPO5RS53NJVPCP252JKHVNA4X/events.json","paper":"https://pith.science/paper/SSPO5RS5"},"agent_actions":{"view_html":"https://pith.science/pith/SSPO5RS53NJVPCP252JKHVNA4X","download_json":"https://pith.science/pith/SSPO5RS53NJVPCP252JKHVNA4X.json","view_paper":"https://pith.science/paper/SSPO5RS5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.24108&json=true","fetch_graph":"https://pith.science/api/pith-number/SSPO5RS53NJVPCP252JKHVNA4X/graph.json","fetch_events":"https://pith.science/api/pith-number/SSPO5RS53NJVPCP252JKHVNA4X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SSPO5RS53NJVPCP252JKHVNA4X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SSPO5RS53NJVPCP252JKHVNA4X/action/storage_attestation","attest_author":"https://pith.science/pith/SSPO5RS53NJVPCP252JKHVNA4X/action/author_attestation","sign_citation":"https://pith.science/pith/SSPO5RS53NJVPCP252JKHVNA4X/action/citation_signature","submit_replication":"https://pith.science/pith/SSPO5RS53NJVPCP252JKHVNA4X/action/replication_record"}},"created_at":"2026-07-09T01:19:48.520192+00:00","updated_at":"2026-07-09T01:19:48.520192+00:00"}