{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MGC2G6REVAC2WFZ5JP4UUIUK5E","short_pith_number":"pith:MGC2G6RE","canonical_record":{"source":{"id":"2406.16782","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-24T16:44:45Z","cross_cats_sorted":[],"title_canon_sha256":"0c75d179b89eaa043cc6d13eb894271e8d6e72ec5690623365f83b4f5ee95667","abstract_canon_sha256":"f2e052f9b298d53aecdf614a46ad6eafd20fa32a20446f1f4264e8d2f31e5c74"},"schema_version":"1.0"},"canonical_sha256":"6185a37a24a805ab173d4bf94a228ae9392a31c7d9a2989a917d41849e533ddd","source":{"kind":"arxiv","id":"2406.16782","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.16782","created_at":"2026-07-05T08:36:03Z"},{"alias_kind":"arxiv_version","alias_value":"2406.16782v1","created_at":"2026-07-05T08:36:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16782","created_at":"2026-07-05T08:36:03Z"},{"alias_kind":"pith_short_12","alias_value":"MGC2G6REVAC2","created_at":"2026-07-05T08:36:03Z"},{"alias_kind":"pith_short_16","alias_value":"MGC2G6REVAC2WFZ5","created_at":"2026-07-05T08:36:03Z"},{"alias_kind":"pith_short_8","alias_value":"MGC2G6RE","created_at":"2026-07-05T08:36:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MGC2G6REVAC2WFZ5JP4UUIUK5E","target":"record","payload":{"canonical_record":{"source":{"id":"2406.16782","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-24T16:44:45Z","cross_cats_sorted":[],"title_canon_sha256":"0c75d179b89eaa043cc6d13eb894271e8d6e72ec5690623365f83b4f5ee95667","abstract_canon_sha256":"f2e052f9b298d53aecdf614a46ad6eafd20fa32a20446f1f4264e8d2f31e5c74"},"schema_version":"1.0"},"canonical_sha256":"6185a37a24a805ab173d4bf94a228ae9392a31c7d9a2989a917d41849e533ddd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:03.623388Z","signature_b64":"ofin/4y+SzOBO9UpStLRY9rQKvfX4KXVNwhoC3PpIh3cCV8eu2T94kflGnURNw4aFSuY/P22m3OkN/cNx0UHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6185a37a24a805ab173d4bf94a228ae9392a31c7d9a2989a917d41849e533ddd","last_reissued_at":"2026-07-05T08:36:03.622840Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:03.622840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.16782","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:36:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mtsZyNr4pDd4GHSFEmjBEWGm95sMdHKQNORtMgRz7wXwZf8EE50FbDGCcBaHKy9MJhEBxdZVy6NqHjJ4Z0d4Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:47:45.351040Z"},"content_sha256":"fe8f80b6d99154cdb0ab0b0802c2d23df87d68462d83e8ea572f1c1bbe52c0e0","schema_version":"1.0","event_id":"sha256:fe8f80b6d99154cdb0ab0b0802c2d23df87d68462d83e8ea572f1c1bbe52c0e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MGC2G6REVAC2WFZ5JP4UUIUK5E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Confidence Aware Inverse Constrained Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Guiliang Liu, Kasra Rezaee, Mohammed Elmahgiubi, Pascal Poupart, Sriram Ganapathi Subramanian","submitted_at":"2024-06-24T16:44:45Z","abstract_excerpt":"In coming up with solutions to real-world problems, humans implicitly adhere to constraints that are too numerous and complex to be specified completely. However, reinforcement learning (RL) agents need these constraints to learn the correct optimal policy in these settings. The field of Inverse Constraint Reinforcement Learning (ICRL) deals with this problem and provides algorithms that aim to estimate the constraints from expert demonstrations collected offline. Practitioners prefer to know a measure of confidence in the estimated constraints, before deciding to use these constraints, which "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16782","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/2406.16782/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":"2026-07-05T08:36:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J3WQ+grKZVKPnKEgkInhczGHWgnGz+OGV22Yfcu8iUTtxbONvzGmk707A4j5MZYXqmLrxvmr+sZXdngTO/AXAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:47:45.351558Z"},"content_sha256":"3edaea1ae7dd7e81ea8a552632de853c215ed3f484413d48fa0849edaff7261b","schema_version":"1.0","event_id":"sha256:3edaea1ae7dd7e81ea8a552632de853c215ed3f484413d48fa0849edaff7261b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MGC2G6REVAC2WFZ5JP4UUIUK5E/bundle.json","state_url":"https://pith.science/pith/MGC2G6REVAC2WFZ5JP4UUIUK5E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MGC2G6REVAC2WFZ5JP4UUIUK5E/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":"2026-08-04T06:47:45Z","links":{"resolver":"https://pith.science/pith/MGC2G6REVAC2WFZ5JP4UUIUK5E","bundle":"https://pith.science/pith/MGC2G6REVAC2WFZ5JP4UUIUK5E/bundle.json","state":"https://pith.science/pith/MGC2G6REVAC2WFZ5JP4UUIUK5E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MGC2G6REVAC2WFZ5JP4UUIUK5E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MGC2G6REVAC2WFZ5JP4UUIUK5E","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":"f2e052f9b298d53aecdf614a46ad6eafd20fa32a20446f1f4264e8d2f31e5c74","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-24T16:44:45Z","title_canon_sha256":"0c75d179b89eaa043cc6d13eb894271e8d6e72ec5690623365f83b4f5ee95667"},"schema_version":"1.0","source":{"id":"2406.16782","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.16782","created_at":"2026-07-05T08:36:03Z"},{"alias_kind":"arxiv_version","alias_value":"2406.16782v1","created_at":"2026-07-05T08:36:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16782","created_at":"2026-07-05T08:36:03Z"},{"alias_kind":"pith_short_12","alias_value":"MGC2G6REVAC2","created_at":"2026-07-05T08:36:03Z"},{"alias_kind":"pith_short_16","alias_value":"MGC2G6REVAC2WFZ5","created_at":"2026-07-05T08:36:03Z"},{"alias_kind":"pith_short_8","alias_value":"MGC2G6RE","created_at":"2026-07-05T08:36:03Z"}],"graph_snapshots":[{"event_id":"sha256:3edaea1ae7dd7e81ea8a552632de853c215ed3f484413d48fa0849edaff7261b","target":"graph","created_at":"2026-07-05T08:36:03Z","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/2406.16782/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In coming up with solutions to real-world problems, humans implicitly adhere to constraints that are too numerous and complex to be specified completely. However, reinforcement learning (RL) agents need these constraints to learn the correct optimal policy in these settings. The field of Inverse Constraint Reinforcement Learning (ICRL) deals with this problem and provides algorithms that aim to estimate the constraints from expert demonstrations collected offline. Practitioners prefer to know a measure of confidence in the estimated constraints, before deciding to use these constraints, which ","authors_text":"Guiliang Liu, Kasra Rezaee, Mohammed Elmahgiubi, Pascal Poupart, Sriram Ganapathi Subramanian","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-24T16:44:45Z","title":"Confidence Aware Inverse Constrained Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16782","kind":"arxiv","version":1},"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:fe8f80b6d99154cdb0ab0b0802c2d23df87d68462d83e8ea572f1c1bbe52c0e0","target":"record","created_at":"2026-07-05T08:36:03Z","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":"f2e052f9b298d53aecdf614a46ad6eafd20fa32a20446f1f4264e8d2f31e5c74","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-24T16:44:45Z","title_canon_sha256":"0c75d179b89eaa043cc6d13eb894271e8d6e72ec5690623365f83b4f5ee95667"},"schema_version":"1.0","source":{"id":"2406.16782","kind":"arxiv","version":1}},"canonical_sha256":"6185a37a24a805ab173d4bf94a228ae9392a31c7d9a2989a917d41849e533ddd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6185a37a24a805ab173d4bf94a228ae9392a31c7d9a2989a917d41849e533ddd","first_computed_at":"2026-07-05T08:36:03.622840Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:03.622840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ofin/4y+SzOBO9UpStLRY9rQKvfX4KXVNwhoC3PpIh3cCV8eu2T94kflGnURNw4aFSuY/P22m3OkN/cNx0UHAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:03.623388Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.16782","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe8f80b6d99154cdb0ab0b0802c2d23df87d68462d83e8ea572f1c1bbe52c0e0","sha256:3edaea1ae7dd7e81ea8a552632de853c215ed3f484413d48fa0849edaff7261b"],"state_sha256":"3c673ab3d7dd60488d992a8c29cf9c8a903afdfc27054f57569d5658a3b7bb1a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SGPwl5wLLU062jiB1iXX+2y09XdjMM8Gg0MBqaso5D/T8s5frOry8mnvloL/Qk+yP+VaKOqlAbF+sQbwSaZsBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T06:47:45.356142Z","bundle_sha256":"0661bd674062e566d4bef0b65ff5d21530f36101768ab28557dfd6413534aa45"}}