{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4GPDGZIAR7O7H65TUVUFO7JHAT","short_pith_number":"pith:4GPDGZIA","schema_version":"1.0","canonical_sha256":"e19e3365008fddf3fbb3a568577d2704d43b873b39b2c5baa6a22781efb81311","source":{"kind":"arxiv","id":"2101.01251","version":1},"attestation_state":"computed","paper":{"title":"Robust Maximum Entropy Behavior Cloning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Brendan Crowe, Marek Petrik, Momotaz Begum, Mostafa Hussein","submitted_at":"2021-01-04T22:08:46Z","abstract_excerpt":"Imitation learning (IL) algorithms use expert demonstrations to learn a specific task. Most of the existing approaches assume that all expert demonstrations are reliable and trustworthy, but what if there exist some adversarial demonstrations among the given data-set? This may result in poor decision-making performance. We propose a novel general frame-work to directly generate a policy from demonstrations that autonomously detect the adversarial demonstrations and exclude them from the data set. At the same time, it's sample, time-efficient, and does not require a simulator. To model such adv"},"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":"2101.01251","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-04T22:08:46Z","cross_cats_sorted":[],"title_canon_sha256":"40830ad63d542b07f0ef582faf0ae12b5fa5b5cee73d8fce27149bd3ccaca9b5","abstract_canon_sha256":"c61a20edb428809d22fcbd0772e882315c9b1f84154f35b8c326d16da5278e7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:04:30.454949Z","signature_b64":"8LR8oSKsPzrBqToRvJCuxMdJ4B8MJWHy9SUcROGvMdmRiowqKTxpQ1zaxC77+6pfVBe72lYbmWCHkGkQOCihBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e19e3365008fddf3fbb3a568577d2704d43b873b39b2c5baa6a22781efb81311","last_reissued_at":"2026-07-05T02:04:30.454513Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:04:30.454513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Maximum Entropy Behavior Cloning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Brendan Crowe, Marek Petrik, Momotaz Begum, Mostafa Hussein","submitted_at":"2021-01-04T22:08:46Z","abstract_excerpt":"Imitation learning (IL) algorithms use expert demonstrations to learn a specific task. Most of the existing approaches assume that all expert demonstrations are reliable and trustworthy, but what if there exist some adversarial demonstrations among the given data-set? This may result in poor decision-making performance. We propose a novel general frame-work to directly generate a policy from demonstrations that autonomously detect the adversarial demonstrations and exclude them from the data set. At the same time, it's sample, time-efficient, and does not require a simulator. To model such adv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.01251","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/2101.01251/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":"2101.01251","created_at":"2026-07-05T02:04:30.454576+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.01251v1","created_at":"2026-07-05T02:04:30.454576+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.01251","created_at":"2026-07-05T02:04:30.454576+00:00"},{"alias_kind":"pith_short_12","alias_value":"4GPDGZIAR7O7","created_at":"2026-07-05T02:04:30.454576+00:00"},{"alias_kind":"pith_short_16","alias_value":"4GPDGZIAR7O7H65T","created_at":"2026-07-05T02:04:30.454576+00:00"},{"alias_kind":"pith_short_8","alias_value":"4GPDGZIA","created_at":"2026-07-05T02:04:30.454576+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.07617","citing_title":"Swarm Behavior Cloning","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4GPDGZIAR7O7H65TUVUFO7JHAT","json":"https://pith.science/pith/4GPDGZIAR7O7H65TUVUFO7JHAT.json","graph_json":"https://pith.science/api/pith-number/4GPDGZIAR7O7H65TUVUFO7JHAT/graph.json","events_json":"https://pith.science/api/pith-number/4GPDGZIAR7O7H65TUVUFO7JHAT/events.json","paper":"https://pith.science/paper/4GPDGZIA"},"agent_actions":{"view_html":"https://pith.science/pith/4GPDGZIAR7O7H65TUVUFO7JHAT","download_json":"https://pith.science/pith/4GPDGZIAR7O7H65TUVUFO7JHAT.json","view_paper":"https://pith.science/paper/4GPDGZIA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.01251&json=true","fetch_graph":"https://pith.science/api/pith-number/4GPDGZIAR7O7H65TUVUFO7JHAT/graph.json","fetch_events":"https://pith.science/api/pith-number/4GPDGZIAR7O7H65TUVUFO7JHAT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4GPDGZIAR7O7H65TUVUFO7JHAT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4GPDGZIAR7O7H65TUVUFO7JHAT/action/storage_attestation","attest_author":"https://pith.science/pith/4GPDGZIAR7O7H65TUVUFO7JHAT/action/author_attestation","sign_citation":"https://pith.science/pith/4GPDGZIAR7O7H65TUVUFO7JHAT/action/citation_signature","submit_replication":"https://pith.science/pith/4GPDGZIAR7O7H65TUVUFO7JHAT/action/replication_record"}},"created_at":"2026-07-05T02:04:30.454576+00:00","updated_at":"2026-07-05T02:04:30.454576+00:00"}