{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:NHAMFU256TMSJU6MBFYIRLADDI","short_pith_number":"pith:NHAMFU25","schema_version":"1.0","canonical_sha256":"69c0c2d35df4d924d3cc097088ac031a384b1476541ef63fbd2b448f4aa6486a","source":{"kind":"arxiv","id":"2008.08812","version":2},"attestation_state":"computed","paper":{"title":"Expressing Diverse Human Driving Behavior with Probabilistic Rewards and Online Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Hengbo Ma, Liting Sun, Masayoshi Tomizuka, Zheng Wu","submitted_at":"2020-08-20T07:32:45Z","abstract_excerpt":"In human-robot interaction (HRI) systems, such as autonomous vehicles, understanding and representing human behavior are important. Human behavior is naturally rich and diverse. Cost/reward learning, as an efficient way to learn and represent human behavior, has been successfully applied in many domains. Most of traditional inverse reinforcement learning (IRL) algorithms, however, cannot adequately capture the diversity of human behavior since they assume that all behavior in a given dataset is generated by a single cost function.In this paper, we propose a probabilistic IRL framework that dir"},"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":"2008.08812","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-08-20T07:32:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c1890c5ba8e00d6188097fa018e47aa92aa32a355a6dda807299976a7626c96c","abstract_canon_sha256":"c618307f4d4db6b58dd4d678712ac93074fea2bf240768b73ac69e531121116d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:28:52.306572Z","signature_b64":"eLqY30LuwObEqVU8Zm6YirvCUfcExO6v+fMPDrWmBgx0Uona5TDUnZkRB8a2L0dMUnig3U4i3sYCn/RDUDUcAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69c0c2d35df4d924d3cc097088ac031a384b1476541ef63fbd2b448f4aa6486a","last_reissued_at":"2026-07-05T01:28:52.306060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:28:52.306060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Expressing Diverse Human Driving Behavior with Probabilistic Rewards and Online Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Hengbo Ma, Liting Sun, Masayoshi Tomizuka, Zheng Wu","submitted_at":"2020-08-20T07:32:45Z","abstract_excerpt":"In human-robot interaction (HRI) systems, such as autonomous vehicles, understanding and representing human behavior are important. Human behavior is naturally rich and diverse. Cost/reward learning, as an efficient way to learn and represent human behavior, has been successfully applied in many domains. Most of traditional inverse reinforcement learning (IRL) algorithms, however, cannot adequately capture the diversity of human behavior since they assume that all behavior in a given dataset is generated by a single cost function.In this paper, we propose a probabilistic IRL framework that dir"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.08812","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/2008.08812/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":"2008.08812","created_at":"2026-07-05T01:28:52.306122+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.08812v2","created_at":"2026-07-05T01:28:52.306122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.08812","created_at":"2026-07-05T01:28:52.306122+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHAMFU256TMS","created_at":"2026-07-05T01:28:52.306122+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHAMFU256TMSJU6M","created_at":"2026-07-05T01:28:52.306122+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHAMFU25","created_at":"2026-07-05T01:28:52.306122+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/NHAMFU256TMSJU6MBFYIRLADDI","json":"https://pith.science/pith/NHAMFU256TMSJU6MBFYIRLADDI.json","graph_json":"https://pith.science/api/pith-number/NHAMFU256TMSJU6MBFYIRLADDI/graph.json","events_json":"https://pith.science/api/pith-number/NHAMFU256TMSJU6MBFYIRLADDI/events.json","paper":"https://pith.science/paper/NHAMFU25"},"agent_actions":{"view_html":"https://pith.science/pith/NHAMFU256TMSJU6MBFYIRLADDI","download_json":"https://pith.science/pith/NHAMFU256TMSJU6MBFYIRLADDI.json","view_paper":"https://pith.science/paper/NHAMFU25","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.08812&json=true","fetch_graph":"https://pith.science/api/pith-number/NHAMFU256TMSJU6MBFYIRLADDI/graph.json","fetch_events":"https://pith.science/api/pith-number/NHAMFU256TMSJU6MBFYIRLADDI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHAMFU256TMSJU6MBFYIRLADDI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHAMFU256TMSJU6MBFYIRLADDI/action/storage_attestation","attest_author":"https://pith.science/pith/NHAMFU256TMSJU6MBFYIRLADDI/action/author_attestation","sign_citation":"https://pith.science/pith/NHAMFU256TMSJU6MBFYIRLADDI/action/citation_signature","submit_replication":"https://pith.science/pith/NHAMFU256TMSJU6MBFYIRLADDI/action/replication_record"}},"created_at":"2026-07-05T01:28:52.306122+00:00","updated_at":"2026-07-05T01:28:52.306122+00:00"}