{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:R7TQ5SYZNVYMD77VVGFDTLDRQR","short_pith_number":"pith:R7TQ5SYZ","canonical_record":{"source":{"id":"2605.12831","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T23:56:36Z","cross_cats_sorted":[],"title_canon_sha256":"9c6a72a2b9ee1080f36adecfac989fb8c517bb054331f4bd3914f7d92fa7a6d2","abstract_canon_sha256":"86184f0aed966e2c388423ef4badbd55bb65c46c86ee55a250cfc87277cb81de"},"schema_version":"1.0"},"canonical_sha256":"8fe70ecb196d70c1fff5a98a39ac71845e4fe48b19403bb1bdbf2a30e6d7aea4","source":{"kind":"arxiv","id":"2605.12831","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12831","created_at":"2026-05-18T03:09:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12831v1","created_at":"2026-05-18T03:09:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12831","created_at":"2026-05-18T03:09:12Z"},{"alias_kind":"pith_short_12","alias_value":"R7TQ5SYZNVYM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"R7TQ5SYZNVYMD77V","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"R7TQ5SYZ","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:R7TQ5SYZNVYMD77VVGFDTLDRQR","target":"record","payload":{"canonical_record":{"source":{"id":"2605.12831","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T23:56:36Z","cross_cats_sorted":[],"title_canon_sha256":"9c6a72a2b9ee1080f36adecfac989fb8c517bb054331f4bd3914f7d92fa7a6d2","abstract_canon_sha256":"86184f0aed966e2c388423ef4badbd55bb65c46c86ee55a250cfc87277cb81de"},"schema_version":"1.0"},"canonical_sha256":"8fe70ecb196d70c1fff5a98a39ac71845e4fe48b19403bb1bdbf2a30e6d7aea4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:12.089805Z","signature_b64":"PhMUXDgsdCoNOMIIBpovueFmd6Z61bbglPe0Ij9tb3oORiryKxrY/TGnq17AJt+TpBeYNxIYzIwX0pz7RLXRDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fe70ecb196d70c1fff5a98a39ac71845e4fe48b19403bb1bdbf2a30e6d7aea4","last_reissued_at":"2026-05-18T03:09:12.089069Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:12.089069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.12831","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":"2026-05-18T03:09:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SEQO7qULiaBt13KDo74oEKzibQZ3W24+1LexlZ4Y9s1wv6ISY/ifEDMECoTRW8vUGEUfmY9nIefHiNVuKtdBDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:44:51.348569Z"},"content_sha256":"a29171afcb07d0cffa9d22b90e828f396a299d0650cf3b535fc4d7dc62626851","schema_version":"1.0","event_id":"sha256:a29171afcb07d0cffa9d22b90e828f396a299d0650cf3b535fc4d7dc62626851"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:R7TQ5SYZNVYMD77VVGFDTLDRQR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quantifying Potential Observation Missingness in Inverse Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Missing observations in IRL can be quantified by finding the minimal perturbations that make expert actions appear optimal.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Abhishek Sharma, Alihan Huyuk, Finale Doshi-Velez, Leo Benac","submitted_at":"2026-05-12T23:56:36Z","abstract_excerpt":"Inverse reinforcement learning (IRL), which infers reward functions from demonstrations, is a valuable tool for modeling and understanding decision-making behavior. Many variants of IRL have been developed to capture complexities of human decision-making, such as subjective beliefs, imperfect planning, and dynamic goals. However, an often-overlooked issue in real-world behavioral datasets is that the recorded data may be missing observations that were available to the original decision-maker. In use-inspired settings such as healthcare, this can make expert actions appear suboptimal, even when"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We identify the minimal perturbations to the recorded observations needed for the expert's actions to appear optimal. We develop a practical algorithm for this problem and demonstrate its utility for quantifying the possible extent of missing observations in behavioral datasets through extensive experiments on synthetic navigation tasks, a cancer treatment simulator, and ICU treatment data.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the minimal perturbations identified correspond to plausible unobserved observations available to the original decision-maker and that standard IRL optimality assumptions hold once those observations are restored.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A practical algorithm quantifies potential missing observations in IRL by computing minimal perturbations to recorded data that render expert actions optimal.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Missing observations in IRL can be quantified by finding the minimal perturbations that make expert actions appear optimal.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"00779c056a8109a15852afebe4b6be1866a9d8f49a6d01690855a33d2c290674"},"source":{"id":"2605.12831","kind":"arxiv","version":1},"verdict":{"id":"97210000-b0a9-447e-9b1c-5d12342cadd5","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:40:05.127295Z","strongest_claim":"We identify the minimal perturbations to the recorded observations needed for the expert's actions to appear optimal. We develop a practical algorithm for this problem and demonstrate its utility for quantifying the possible extent of missing observations in behavioral datasets through extensive experiments on synthetic navigation tasks, a cancer treatment simulator, and ICU treatment data.","one_line_summary":"A practical algorithm quantifies potential missing observations in IRL by computing minimal perturbations to recorded data that render expert actions optimal.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the minimal perturbations identified correspond to plausible unobserved observations available to the original decision-maker and that standard IRL optimality assumptions hold once those observations are restored.","pith_extraction_headline":"Missing observations in IRL can be quantified by finding the minimal perturbations that make expert actions appear optimal."},"references":{"count":43,"sample":[{"doi":"","year":null,"title":"Algorithms for inverse reinforcement learning. , author=. International Conference on Machine Learning , year=","work_id":"f5d97198-9e72-435a-b8e4-1698fcfed900","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Bayesian Inverse Transition Learning: Learning Dynamics From Near-Optimal Trajectories","work_id":"5511fe45-1a49-4f94-ad48-f4ec610da3ee","ref_index":2,"cited_arxiv_id":"2411.05174","is_internal_anchor":true},{"doi":"","year":2013,"title":"New England Journal of Medicine , volume=","work_id":"0a66328c-dd13-48b8-896c-2c0333b9aff4","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"Canadian Journal of Anesthesia/Journal canadien d'anesth","work_id":"0b356b15-cfaa-409f-aa84-67fb5e89a0f4","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Journal of Critical Care , volume=","work_id":"4d77bf63-09d4-4add-82af-4dfd49962af3","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":43,"snapshot_sha256":"59e29770ab8e228eedc25732d766f84a4fb8c51fe87fe6b90efb0d569683c329","internal_anchors":3},"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":"97210000-b0a9-447e-9b1c-5d12342cadd5"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XVfHs/saK5h8wA0Uno1EoKRRFI/lUYlA1nWzhBGTv6y4HjTUurg3z35B4O2lLPbvVEdlp5Cx2UiNJPWBzs+gBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:44:51.349122Z"},"content_sha256":"1efc01705b4dc90e63707fb209ff682451fc8ebc32b62d1754f87b3c9c2a8ec3","schema_version":"1.0","event_id":"sha256:1efc01705b4dc90e63707fb209ff682451fc8ebc32b62d1754f87b3c9c2a8ec3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R7TQ5SYZNVYMD77VVGFDTLDRQR/bundle.json","state_url":"https://pith.science/pith/R7TQ5SYZNVYMD77VVGFDTLDRQR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R7TQ5SYZNVYMD77VVGFDTLDRQR/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":"2026-05-25T20:44:51Z","links":{"resolver":"https://pith.science/pith/R7TQ5SYZNVYMD77VVGFDTLDRQR","bundle":"https://pith.science/pith/R7TQ5SYZNVYMD77VVGFDTLDRQR/bundle.json","state":"https://pith.science/pith/R7TQ5SYZNVYMD77VVGFDTLDRQR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R7TQ5SYZNVYMD77VVGFDTLDRQR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:R7TQ5SYZNVYMD77VVGFDTLDRQR","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":"86184f0aed966e2c388423ef4badbd55bb65c46c86ee55a250cfc87277cb81de","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T23:56:36Z","title_canon_sha256":"9c6a72a2b9ee1080f36adecfac989fb8c517bb054331f4bd3914f7d92fa7a6d2"},"schema_version":"1.0","source":{"id":"2605.12831","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12831","created_at":"2026-05-18T03:09:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12831v1","created_at":"2026-05-18T03:09:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12831","created_at":"2026-05-18T03:09:12Z"},{"alias_kind":"pith_short_12","alias_value":"R7TQ5SYZNVYM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"R7TQ5SYZNVYMD77V","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"R7TQ5SYZ","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:1efc01705b4dc90e63707fb209ff682451fc8ebc32b62d1754f87b3c9c2a8ec3","target":"graph","created_at":"2026-05-18T03:09:12Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We identify the minimal perturbations to the recorded observations needed for the expert's actions to appear optimal. We develop a practical algorithm for this problem and demonstrate its utility for quantifying the possible extent of missing observations in behavioral datasets through extensive experiments on synthetic navigation tasks, a cancer treatment simulator, and ICU treatment data."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the minimal perturbations identified correspond to plausible unobserved observations available to the original decision-maker and that standard IRL optimality assumptions hold once those observations are restored."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A practical algorithm quantifies potential missing observations in IRL by computing minimal perturbations to recorded data that render expert actions optimal."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Missing observations in IRL can be quantified by finding the minimal perturbations that make expert actions appear optimal."}],"snapshot_sha256":"00779c056a8109a15852afebe4b6be1866a9d8f49a6d01690855a33d2c290674"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Inverse reinforcement learning (IRL), which infers reward functions from demonstrations, is a valuable tool for modeling and understanding decision-making behavior. Many variants of IRL have been developed to capture complexities of human decision-making, such as subjective beliefs, imperfect planning, and dynamic goals. However, an often-overlooked issue in real-world behavioral datasets is that the recorded data may be missing observations that were available to the original decision-maker. In use-inspired settings such as healthcare, this can make expert actions appear suboptimal, even when","authors_text":"Abhishek Sharma, Alihan Huyuk, Finale Doshi-Velez, Leo Benac","cross_cats":[],"headline":"Missing observations in IRL can be quantified by finding the minimal perturbations that make expert actions appear optimal.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T23:56:36Z","title":"Quantifying Potential Observation Missingness in Inverse Reinforcement Learning"},"references":{"count":43,"internal_anchors":3,"resolved_work":43,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Algorithms for inverse reinforcement learning. , author=. International Conference on Machine Learning , year=","work_id":"f5d97198-9e72-435a-b8e4-1698fcfed900","year":null},{"cited_arxiv_id":"2411.05174","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Bayesian Inverse Transition Learning: Learning Dynamics From Near-Optimal Trajectories","work_id":"5511fe45-1a49-4f94-ad48-f4ec610da3ee","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"New England Journal of Medicine , volume=","work_id":"0a66328c-dd13-48b8-896c-2c0333b9aff4","year":2013},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Canadian Journal of Anesthesia/Journal canadien d'anesth","work_id":"0b356b15-cfaa-409f-aa84-67fb5e89a0f4","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Journal of Critical Care , volume=","work_id":"4d77bf63-09d4-4add-82af-4dfd49962af3","year":2022}],"snapshot_sha256":"59e29770ab8e228eedc25732d766f84a4fb8c51fe87fe6b90efb0d569683c329"},"source":{"id":"2605.12831","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:40:05.127295Z","id":"97210000-b0a9-447e-9b1c-5d12342cadd5","model_set":{"reader":"grok-4.3"},"one_line_summary":"A practical algorithm quantifies potential missing observations in IRL by computing minimal perturbations to recorded data that render expert actions optimal.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Missing observations in IRL can be quantified by finding the minimal perturbations that make expert actions appear optimal.","strongest_claim":"We identify the minimal perturbations to the recorded observations needed for the expert's actions to appear optimal. We develop a practical algorithm for this problem and demonstrate its utility for quantifying the possible extent of missing observations in behavioral datasets through extensive experiments on synthetic navigation tasks, a cancer treatment simulator, and ICU treatment data.","weakest_assumption":"That the minimal perturbations identified correspond to plausible unobserved observations available to the original decision-maker and that standard IRL optimality assumptions hold once those observations are restored."}},"verdict_id":"97210000-b0a9-447e-9b1c-5d12342cadd5"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a29171afcb07d0cffa9d22b90e828f396a299d0650cf3b535fc4d7dc62626851","target":"record","created_at":"2026-05-18T03:09:12Z","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":"86184f0aed966e2c388423ef4badbd55bb65c46c86ee55a250cfc87277cb81de","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T23:56:36Z","title_canon_sha256":"9c6a72a2b9ee1080f36adecfac989fb8c517bb054331f4bd3914f7d92fa7a6d2"},"schema_version":"1.0","source":{"id":"2605.12831","kind":"arxiv","version":1}},"canonical_sha256":"8fe70ecb196d70c1fff5a98a39ac71845e4fe48b19403bb1bdbf2a30e6d7aea4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8fe70ecb196d70c1fff5a98a39ac71845e4fe48b19403bb1bdbf2a30e6d7aea4","first_computed_at":"2026-05-18T03:09:12.089069Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:12.089069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PhMUXDgsdCoNOMIIBpovueFmd6Z61bbglPe0Ij9tb3oORiryKxrY/TGnq17AJt+TpBeYNxIYzIwX0pz7RLXRDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:12.089805Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12831","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a29171afcb07d0cffa9d22b90e828f396a299d0650cf3b535fc4d7dc62626851","sha256:1efc01705b4dc90e63707fb209ff682451fc8ebc32b62d1754f87b3c9c2a8ec3"],"state_sha256":"7c181cb5828ca06957e245a412a6ce8cad78eebe42f51ffe8a2f9a75fd9e6a42"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GkZBuwPJeFggy10cbIdmlAvgT+McCVQuh4W1LC/330/td8pYSYF5e4xp0Z6qNQa+phnOatxxuUXNXxlk4OjOCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T20:44:51.352433Z","bundle_sha256":"cb2b5d90d60ab10b5daa051fa0f0bcb0f9ab5011938687e30b7ed706a1596d44"}}