{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:AMWIMYADSOUYABBBOEJNZF4QCU","short_pith_number":"pith:AMWIMYAD","canonical_record":{"source":{"id":"2206.09670","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-20T09:22:20Z","cross_cats_sorted":[],"title_canon_sha256":"5866a061ffb685c8cd32d19bbe887435e79c5671106ceb204d5d48231532aee2","abstract_canon_sha256":"fe68487f6f0351c685f20782fdae6876adaa188cd4e46eb5e8d8f4758744cae7"},"schema_version":"1.0"},"canonical_sha256":"032c86600393a98004217112dc9790152ef9ef1e1b34490c028806c22569762f","source":{"kind":"arxiv","id":"2206.09670","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.09670","created_at":"2026-07-05T05:47:16Z"},{"alias_kind":"arxiv_version","alias_value":"2206.09670v3","created_at":"2026-07-05T05:47:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.09670","created_at":"2026-07-05T05:47:16Z"},{"alias_kind":"pith_short_12","alias_value":"AMWIMYADSOUY","created_at":"2026-07-05T05:47:16Z"},{"alias_kind":"pith_short_16","alias_value":"AMWIMYADSOUYABBB","created_at":"2026-07-05T05:47:16Z"},{"alias_kind":"pith_short_8","alias_value":"AMWIMYAD","created_at":"2026-07-05T05:47:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:AMWIMYADSOUYABBBOEJNZF4QCU","target":"record","payload":{"canonical_record":{"source":{"id":"2206.09670","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-20T09:22:20Z","cross_cats_sorted":[],"title_canon_sha256":"5866a061ffb685c8cd32d19bbe887435e79c5671106ceb204d5d48231532aee2","abstract_canon_sha256":"fe68487f6f0351c685f20782fdae6876adaa188cd4e46eb5e8d8f4758744cae7"},"schema_version":"1.0"},"canonical_sha256":"032c86600393a98004217112dc9790152ef9ef1e1b34490c028806c22569762f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:16.169684Z","signature_b64":"16FuQaAv4OXWUayElDPrg+9/lFg4at5g+8YJvGzj+Le3HsVF0eNhAJSjUWFoZT+pO2V/YsQu5hhk/vYB3xz6BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"032c86600393a98004217112dc9790152ef9ef1e1b34490c028806c22569762f","last_reissued_at":"2026-07-05T05:47:16.169168Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:16.169168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.09670","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:47:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fPZ7/N0BPD+igHSKEXcrxNovtYfSgcydTofGuG5YohpjAgLPoCweaWnu2EXUmFZcrPtygpoNq+6vtNDFRK3SDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T21:21:39.282031Z"},"content_sha256":"1a59b39e5359a994b4b73c337d267601aeae0fbff66299cdb0544eb4ddbf88f7","schema_version":"1.0","event_id":"sha256:1a59b39e5359a994b4b73c337d267601aeae0fbff66299cdb0544eb4ddbf88f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:AMWIMYADSOUYABBBOEJNZF4QCU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benchmarking Constraint Inference in Inverse Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ashish Gaurav, Guiliang Liu, Kasra Rezaee, Pascal Poupart, Yudong Luo","submitted_at":"2022-06-20T09:22:20Z","abstract_excerpt":"When deploying Reinforcement Learning (RL) agents into a physical system, we must ensure that these agents are well aware of the underlying constraints. In many real-world problems, however, the constraints are often hard to specify mathematically and unknown to the RL agents. To tackle these issues, Inverse Constrained Reinforcement Learning (ICRL) empirically estimates constraints from expert demonstrations. As an emerging research topic, ICRL does not have common benchmarks, and previous works tested algorithms under hand-crafted environments with manually-generated expert demonstrations. I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.09670","kind":"arxiv","version":3},"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/2206.09670/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:47:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"enfo8RG1gunxyaHcGTQ016GPwoXwYlpm3G7EsSwkisQIFCZzVtkhlPq25XKyVDi+IOrioASBflLYmrFrV9VSDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T21:21:39.282574Z"},"content_sha256":"ee656d1b8ec8545882cc93d00c21b999d88c249ff12a780ae611da3da43bf847","schema_version":"1.0","event_id":"sha256:ee656d1b8ec8545882cc93d00c21b999d88c249ff12a780ae611da3da43bf847"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AMWIMYADSOUYABBBOEJNZF4QCU/bundle.json","state_url":"https://pith.science/pith/AMWIMYADSOUYABBBOEJNZF4QCU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AMWIMYADSOUYABBBOEJNZF4QCU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-14T21:21:39Z","links":{"resolver":"https://pith.science/pith/AMWIMYADSOUYABBBOEJNZF4QCU","bundle":"https://pith.science/pith/AMWIMYADSOUYABBBOEJNZF4QCU/bundle.json","state":"https://pith.science/pith/AMWIMYADSOUYABBBOEJNZF4QCU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AMWIMYADSOUYABBBOEJNZF4QCU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:AMWIMYADSOUYABBBOEJNZF4QCU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fe68487f6f0351c685f20782fdae6876adaa188cd4e46eb5e8d8f4758744cae7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-20T09:22:20Z","title_canon_sha256":"5866a061ffb685c8cd32d19bbe887435e79c5671106ceb204d5d48231532aee2"},"schema_version":"1.0","source":{"id":"2206.09670","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.09670","created_at":"2026-07-05T05:47:16Z"},{"alias_kind":"arxiv_version","alias_value":"2206.09670v3","created_at":"2026-07-05T05:47:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.09670","created_at":"2026-07-05T05:47:16Z"},{"alias_kind":"pith_short_12","alias_value":"AMWIMYADSOUY","created_at":"2026-07-05T05:47:16Z"},{"alias_kind":"pith_short_16","alias_value":"AMWIMYADSOUYABBB","created_at":"2026-07-05T05:47:16Z"},{"alias_kind":"pith_short_8","alias_value":"AMWIMYAD","created_at":"2026-07-05T05:47:16Z"}],"graph_snapshots":[{"event_id":"sha256:ee656d1b8ec8545882cc93d00c21b999d88c249ff12a780ae611da3da43bf847","target":"graph","created_at":"2026-07-05T05:47:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2206.09670/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When deploying Reinforcement Learning (RL) agents into a physical system, we must ensure that these agents are well aware of the underlying constraints. In many real-world problems, however, the constraints are often hard to specify mathematically and unknown to the RL agents. To tackle these issues, Inverse Constrained Reinforcement Learning (ICRL) empirically estimates constraints from expert demonstrations. As an emerging research topic, ICRL does not have common benchmarks, and previous works tested algorithms under hand-crafted environments with manually-generated expert demonstrations. I","authors_text":"Ashish Gaurav, Guiliang Liu, Kasra Rezaee, Pascal Poupart, Yudong Luo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-20T09:22:20Z","title":"Benchmarking Constraint Inference in Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.09670","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1a59b39e5359a994b4b73c337d267601aeae0fbff66299cdb0544eb4ddbf88f7","target":"record","created_at":"2026-07-05T05:47:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fe68487f6f0351c685f20782fdae6876adaa188cd4e46eb5e8d8f4758744cae7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-20T09:22:20Z","title_canon_sha256":"5866a061ffb685c8cd32d19bbe887435e79c5671106ceb204d5d48231532aee2"},"schema_version":"1.0","source":{"id":"2206.09670","kind":"arxiv","version":3}},"canonical_sha256":"032c86600393a98004217112dc9790152ef9ef1e1b34490c028806c22569762f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"032c86600393a98004217112dc9790152ef9ef1e1b34490c028806c22569762f","first_computed_at":"2026-07-05T05:47:16.169168Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:47:16.169168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"16FuQaAv4OXWUayElDPrg+9/lFg4at5g+8YJvGzj+Le3HsVF0eNhAJSjUWFoZT+pO2V/YsQu5hhk/vYB3xz6BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:47:16.169684Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.09670","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a59b39e5359a994b4b73c337d267601aeae0fbff66299cdb0544eb4ddbf88f7","sha256:ee656d1b8ec8545882cc93d00c21b999d88c249ff12a780ae611da3da43bf847"],"state_sha256":"91256e1e7b06c233390980142638c129a57a161d5125b2dde414055909570349"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ao10zi0TAKbMRLhm/Gu/iuFaYPyEK3+yvKcE2Sd9cXh5Dpwgs7/N+Qq96MHBrk13eMROHcby/J+mQfteK48GDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T21:21:39.286249Z","bundle_sha256":"7117ed914b4ce88df2bcf657d15e2db396ac1d657915f10636b21a266e05bab9"}}