{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:HYEOS4Q7IOT3GTE3WDZNTHEDF2","short_pith_number":"pith:HYEOS4Q7","canonical_record":{"source":{"id":"1709.07597","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-22T05:12:04Z","cross_cats_sorted":[],"title_canon_sha256":"0225743ce08aa86431351f70fe1f53b1d96f90ed1be41e9a14e04eec580fe41c","abstract_canon_sha256":"58f43d98157ae37f0e9278fe0aa4ec4df11707e2bf4708e0207752c915fbbe72"},"schema_version":"1.0"},"canonical_sha256":"3e08e9721f43a7b34c9bb0f2d99c832eb2888d244d8873006a8307e059e94343","source":{"kind":"arxiv","id":"1709.07597","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.07597","created_at":"2026-05-18T00:34:32Z"},{"alias_kind":"arxiv_version","alias_value":"1709.07597v1","created_at":"2026-05-18T00:34:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.07597","created_at":"2026-05-18T00:34:32Z"},{"alias_kind":"pith_short_12","alias_value":"HYEOS4Q7IOT3","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"HYEOS4Q7IOT3GTE3","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"HYEOS4Q7","created_at":"2026-05-18T12:31:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:HYEOS4Q7IOT3GTE3WDZNTHEDF2","target":"record","payload":{"canonical_record":{"source":{"id":"1709.07597","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-22T05:12:04Z","cross_cats_sorted":[],"title_canon_sha256":"0225743ce08aa86431351f70fe1f53b1d96f90ed1be41e9a14e04eec580fe41c","abstract_canon_sha256":"58f43d98157ae37f0e9278fe0aa4ec4df11707e2bf4708e0207752c915fbbe72"},"schema_version":"1.0"},"canonical_sha256":"3e08e9721f43a7b34c9bb0f2d99c832eb2888d244d8873006a8307e059e94343","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:32.753146Z","signature_b64":"BrIYBFGAnEFbVZJ6N7fi+yQSz74QrEbB181YjHdV0CTeXZBCZJcSLqgI0GwTwrKXuxrhhSKw9cBYpbj7pq70Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e08e9721f43a7b34c9bb0f2d99c832eb2888d244d8873006a8307e059e94343","last_reissued_at":"2026-05-18T00:34:32.752753Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:32.752753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.07597","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":"2026-05-18T00:34:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vorI/TpCYdAlvEIhG+8ppcSC09slT/HtQME/GPeqVos1rBbjR2w+l7nK82VabWfsdJ2koXu3meyGjhguzXh4DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T08:42:54.575091Z"},"content_sha256":"2fe576fac6552fb68146329d33398157f5e260d1da76df207c657698787f8c29","schema_version":"1.0","event_id":"sha256:2fe576fac6552fb68146329d33398157f5e260d1da76df207c657698787f8c29"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:HYEOS4Q7IOT3GTE3WDZNTHEDF2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Inverse Reinforcement Learning with Conditional Choice Probabilities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Joachim Groeger, Kris M. Kitani, Mohit Sharma","submitted_at":"2017-09-22T05:12:04Z","abstract_excerpt":"We make an important connection to existing results in econometrics to describe an alternative formulation of inverse reinforcement learning (IRL). In particular, we describe an algorithm using Conditional Choice Probabilities (CCP), which are maximum likelihood estimates of the policy estimated from expert demonstrations, to solve the IRL problem. Using the language of structural econometrics, we re-frame the optimal decision problem and introduce an alternative representation of value functions due to (Hotz and Miller 1993). In addition to presenting the theoretical connections that bridge t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.07597","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":""},"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":"2026-05-18T00:34:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j9THZUfrZ3FFn8rDGnOnYSjpncSnvEd949b6sPoGlcq4LJ12z6qTBB+xw2U+O7jPRve61n46QqGBJENS2mAoBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T08:42:54.575464Z"},"content_sha256":"643fa8f5028b9ba55a08e395becf0a7d54f0d44d55658a3f09bc4cadbeec2409","schema_version":"1.0","event_id":"sha256:643fa8f5028b9ba55a08e395becf0a7d54f0d44d55658a3f09bc4cadbeec2409"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HYEOS4Q7IOT3GTE3WDZNTHEDF2/bundle.json","state_url":"https://pith.science/pith/HYEOS4Q7IOT3GTE3WDZNTHEDF2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HYEOS4Q7IOT3GTE3WDZNTHEDF2/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":"2026-05-30T08:42:54Z","links":{"resolver":"https://pith.science/pith/HYEOS4Q7IOT3GTE3WDZNTHEDF2","bundle":"https://pith.science/pith/HYEOS4Q7IOT3GTE3WDZNTHEDF2/bundle.json","state":"https://pith.science/pith/HYEOS4Q7IOT3GTE3WDZNTHEDF2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HYEOS4Q7IOT3GTE3WDZNTHEDF2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:HYEOS4Q7IOT3GTE3WDZNTHEDF2","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":"58f43d98157ae37f0e9278fe0aa4ec4df11707e2bf4708e0207752c915fbbe72","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-22T05:12:04Z","title_canon_sha256":"0225743ce08aa86431351f70fe1f53b1d96f90ed1be41e9a14e04eec580fe41c"},"schema_version":"1.0","source":{"id":"1709.07597","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.07597","created_at":"2026-05-18T00:34:32Z"},{"alias_kind":"arxiv_version","alias_value":"1709.07597v1","created_at":"2026-05-18T00:34:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.07597","created_at":"2026-05-18T00:34:32Z"},{"alias_kind":"pith_short_12","alias_value":"HYEOS4Q7IOT3","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"HYEOS4Q7IOT3GTE3","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"HYEOS4Q7","created_at":"2026-05-18T12:31:21Z"}],"graph_snapshots":[{"event_id":"sha256:643fa8f5028b9ba55a08e395becf0a7d54f0d44d55658a3f09bc4cadbeec2409","target":"graph","created_at":"2026-05-18T00:34:32Z","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"},"paper":{"abstract_excerpt":"We make an important connection to existing results in econometrics to describe an alternative formulation of inverse reinforcement learning (IRL). In particular, we describe an algorithm using Conditional Choice Probabilities (CCP), which are maximum likelihood estimates of the policy estimated from expert demonstrations, to solve the IRL problem. Using the language of structural econometrics, we re-frame the optimal decision problem and introduce an alternative representation of value functions due to (Hotz and Miller 1993). In addition to presenting the theoretical connections that bridge t","authors_text":"Joachim Groeger, Kris M. Kitani, Mohit Sharma","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-22T05:12:04Z","title":"Inverse Reinforcement Learning with Conditional Choice Probabilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.07597","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":"sha256:2fe576fac6552fb68146329d33398157f5e260d1da76df207c657698787f8c29","target":"record","created_at":"2026-05-18T00:34:32Z","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":"58f43d98157ae37f0e9278fe0aa4ec4df11707e2bf4708e0207752c915fbbe72","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-22T05:12:04Z","title_canon_sha256":"0225743ce08aa86431351f70fe1f53b1d96f90ed1be41e9a14e04eec580fe41c"},"schema_version":"1.0","source":{"id":"1709.07597","kind":"arxiv","version":1}},"canonical_sha256":"3e08e9721f43a7b34c9bb0f2d99c832eb2888d244d8873006a8307e059e94343","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e08e9721f43a7b34c9bb0f2d99c832eb2888d244d8873006a8307e059e94343","first_computed_at":"2026-05-18T00:34:32.752753Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:34:32.752753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BrIYBFGAnEFbVZJ6N7fi+yQSz74QrEbB181YjHdV0CTeXZBCZJcSLqgI0GwTwrKXuxrhhSKw9cBYpbj7pq70Cg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:34:32.753146Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.07597","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2fe576fac6552fb68146329d33398157f5e260d1da76df207c657698787f8c29","sha256:643fa8f5028b9ba55a08e395becf0a7d54f0d44d55658a3f09bc4cadbeec2409"],"state_sha256":"7f6da3d2243a1df949de4d9f6f044eadb525fc7dae4d139a6f39e3ab9ed7b0c6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N7TcNho51IhUcBrXCUXwiTFSv9pzdpHULZdse2L8ooC23YiyTW9J5cwEXvtvUTvFHHfRq63E7bBMm6O2TPUfBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T08:42:54.577574Z","bundle_sha256":"8faf4b7921e83ae39242ae8c9f63f6df453f16027424e13f6bb95f6b49069cc4"}}