{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UTT6BK5FB5GBBV4NDHMBVCAM2K","short_pith_number":"pith:UTT6BK5F","canonical_record":{"source":{"id":"2409.08012","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-12T12:56:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"463f5e248d8afcb28708f78fea26496494d3a5ad9166071f12c786fbab78b2bb","abstract_canon_sha256":"05ffffaeb1cc921d86bfa521d6e5e2c9a8feff90b2eb1798f4a54067ca8ceffb"},"schema_version":"1.0"},"canonical_sha256":"a4e7e0aba50f4c10d78d19d81a880cd2a44a71a4933c3978f36775c82018de52","source":{"kind":"arxiv","id":"2409.08012","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08012","created_at":"2026-07-05T09:06:18Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08012v1","created_at":"2026-07-05T09:06:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08012","created_at":"2026-07-05T09:06:18Z"},{"alias_kind":"pith_short_12","alias_value":"UTT6BK5FB5GB","created_at":"2026-07-05T09:06:18Z"},{"alias_kind":"pith_short_16","alias_value":"UTT6BK5FB5GBBV4N","created_at":"2026-07-05T09:06:18Z"},{"alias_kind":"pith_short_8","alias_value":"UTT6BK5F","created_at":"2026-07-05T09:06:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UTT6BK5FB5GBBV4NDHMBVCAM2K","target":"record","payload":{"canonical_record":{"source":{"id":"2409.08012","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-12T12:56:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"463f5e248d8afcb28708f78fea26496494d3a5ad9166071f12c786fbab78b2bb","abstract_canon_sha256":"05ffffaeb1cc921d86bfa521d6e5e2c9a8feff90b2eb1798f4a54067ca8ceffb"},"schema_version":"1.0"},"canonical_sha256":"a4e7e0aba50f4c10d78d19d81a880cd2a44a71a4933c3978f36775c82018de52","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:18.754926Z","signature_b64":"3d7y+RhLFl4RY+TogJB4dF/cU6Pneh6UkC2TUVCDOJJ4/vW6JQLTWNWMG4xox3oyMN7MaPI+05ym5p+PMLleBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4e7e0aba50f4c10d78d19d81a880cd2a44a71a4933c3978f36775c82018de52","last_reissued_at":"2026-07-05T09:06:18.754433Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:18.754433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.08012","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":"2026-07-05T09:06:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o3IJJRdcr394EfzHiyU1a1IbKYmKgz6usEFxP08yMfUwzCBcNVzXzjZvScQmOK8jcNDhFMM5R3jwzvQARg4BDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T14:30:54.813487Z"},"content_sha256":"623e220b7d89993644e7dc46c32d25d40557d79883a80c5677a7b55c3f048d0c","schema_version":"1.0","event_id":"sha256:623e220b7d89993644e7dc46c32d25d40557d79883a80c5677a7b55c3f048d0c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UTT6BK5FB5GBBV4NDHMBVCAM2K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Causally Invariant Reward Functions from Diverse Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Eugene Bykovets, Ivan Ovinnikov, Joachim M. Buhmann","submitted_at":"2024-09-12T12:56:24Z","abstract_excerpt":"Inverse reinforcement learning methods aim to retrieve the reward function of a Markov decision process based on a dataset of expert demonstrations. The commonplace scarcity and heterogeneous sources of such demonstrations can lead to the absorption of spurious correlations in the data by the learned reward function. Consequently, this adaptation often exhibits behavioural overfitting to the expert data set when a policy is trained on the obtained reward function under distribution shift of the environment dynamics. In this work, we explore a novel regularization approach for inverse reinforce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08012","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/2409.08012/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":"2026-07-05T09:06:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kktanyu3j1XvGtm+YMuhjLVafQGQWFJ9kT4i3cKFdxQP1ZIgTjXLc5y4/Fi6XgzUZWLgquELMr/UmElrNVupCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T14:30:54.814135Z"},"content_sha256":"c7b51f709e499f0c38740eba51badb825c7ca5ef81a60e59a4aed6939e67348e","schema_version":"1.0","event_id":"sha256:c7b51f709e499f0c38740eba51badb825c7ca5ef81a60e59a4aed6939e67348e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UTT6BK5FB5GBBV4NDHMBVCAM2K/bundle.json","state_url":"https://pith.science/pith/UTT6BK5FB5GBBV4NDHMBVCAM2K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UTT6BK5FB5GBBV4NDHMBVCAM2K/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":"2026-07-05T14:30:54Z","links":{"resolver":"https://pith.science/pith/UTT6BK5FB5GBBV4NDHMBVCAM2K","bundle":"https://pith.science/pith/UTT6BK5FB5GBBV4NDHMBVCAM2K/bundle.json","state":"https://pith.science/pith/UTT6BK5FB5GBBV4NDHMBVCAM2K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UTT6BK5FB5GBBV4NDHMBVCAM2K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UTT6BK5FB5GBBV4NDHMBVCAM2K","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":"05ffffaeb1cc921d86bfa521d6e5e2c9a8feff90b2eb1798f4a54067ca8ceffb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-12T12:56:24Z","title_canon_sha256":"463f5e248d8afcb28708f78fea26496494d3a5ad9166071f12c786fbab78b2bb"},"schema_version":"1.0","source":{"id":"2409.08012","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08012","created_at":"2026-07-05T09:06:18Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08012v1","created_at":"2026-07-05T09:06:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08012","created_at":"2026-07-05T09:06:18Z"},{"alias_kind":"pith_short_12","alias_value":"UTT6BK5FB5GB","created_at":"2026-07-05T09:06:18Z"},{"alias_kind":"pith_short_16","alias_value":"UTT6BK5FB5GBBV4N","created_at":"2026-07-05T09:06:18Z"},{"alias_kind":"pith_short_8","alias_value":"UTT6BK5F","created_at":"2026-07-05T09:06:18Z"}],"graph_snapshots":[{"event_id":"sha256:c7b51f709e499f0c38740eba51badb825c7ca5ef81a60e59a4aed6939e67348e","target":"graph","created_at":"2026-07-05T09:06:18Z","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/2409.08012/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inverse reinforcement learning methods aim to retrieve the reward function of a Markov decision process based on a dataset of expert demonstrations. The commonplace scarcity and heterogeneous sources of such demonstrations can lead to the absorption of spurious correlations in the data by the learned reward function. Consequently, this adaptation often exhibits behavioural overfitting to the expert data set when a policy is trained on the obtained reward function under distribution shift of the environment dynamics. In this work, we explore a novel regularization approach for inverse reinforce","authors_text":"Eugene Bykovets, Ivan Ovinnikov, Joachim M. Buhmann","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-12T12:56:24Z","title":"Learning Causally Invariant Reward Functions from Diverse Demonstrations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08012","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":"sha256:623e220b7d89993644e7dc46c32d25d40557d79883a80c5677a7b55c3f048d0c","target":"record","created_at":"2026-07-05T09:06:18Z","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":"05ffffaeb1cc921d86bfa521d6e5e2c9a8feff90b2eb1798f4a54067ca8ceffb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-12T12:56:24Z","title_canon_sha256":"463f5e248d8afcb28708f78fea26496494d3a5ad9166071f12c786fbab78b2bb"},"schema_version":"1.0","source":{"id":"2409.08012","kind":"arxiv","version":1}},"canonical_sha256":"a4e7e0aba50f4c10d78d19d81a880cd2a44a71a4933c3978f36775c82018de52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4e7e0aba50f4c10d78d19d81a880cd2a44a71a4933c3978f36775c82018de52","first_computed_at":"2026-07-05T09:06:18.754433Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:06:18.754433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3d7y+RhLFl4RY+TogJB4dF/cU6Pneh6UkC2TUVCDOJJ4/vW6JQLTWNWMG4xox3oyMN7MaPI+05ym5p+PMLleBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:06:18.754926Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.08012","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:623e220b7d89993644e7dc46c32d25d40557d79883a80c5677a7b55c3f048d0c","sha256:c7b51f709e499f0c38740eba51badb825c7ca5ef81a60e59a4aed6939e67348e"],"state_sha256":"f3e5af3a07cf526eeaaf6040e02e310a3ef4692947088f77872411032b5eee0b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xyQoQUrN/IttWbVGvkOlivxZTQEZwUUBLuzmw3BFeJw3R83ZZJe2AsdKEvPb86ugHudK7VqDfuvbmA7FFg07BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T14:30:54.817531Z","bundle_sha256":"ad0dea4ab3c58a4e121b26767483b6cc2be8db5423d5f5d721abd301ed2d37ac"}}