{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DUD6NJPAC4BOQDQNPMEVS4HW3J","short_pith_number":"pith:DUD6NJPA","canonical_record":{"source":{"id":"2402.08848","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-13T23:29:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"72ee7ae4d094aea124d0d5b29330751eead2f61995f545a2871b8a52888541b5","abstract_canon_sha256":"dba7f182f5c21223d0f1c9c5234f2ab02232ef2e84a1990fd3c9f05b46d73299"},"schema_version":"1.0"},"canonical_sha256":"1d07e6a5e01702e80e0d7b095970f6da7f57eb5b78373b5a0c3b2efe3c40617e","source":{"kind":"arxiv","id":"2402.08848","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.08848","created_at":"2026-07-05T08:27:24Z"},{"alias_kind":"arxiv_version","alias_value":"2402.08848v2","created_at":"2026-07-05T08:27:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08848","created_at":"2026-07-05T08:27:24Z"},{"alias_kind":"pith_short_12","alias_value":"DUD6NJPAC4BO","created_at":"2026-07-05T08:27:24Z"},{"alias_kind":"pith_short_16","alias_value":"DUD6NJPAC4BOQDQN","created_at":"2026-07-05T08:27:24Z"},{"alias_kind":"pith_short_8","alias_value":"DUD6NJPA","created_at":"2026-07-05T08:27:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DUD6NJPAC4BOQDQNPMEVS4HW3J","target":"record","payload":{"canonical_record":{"source":{"id":"2402.08848","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-13T23:29:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"72ee7ae4d094aea124d0d5b29330751eead2f61995f545a2871b8a52888541b5","abstract_canon_sha256":"dba7f182f5c21223d0f1c9c5234f2ab02232ef2e84a1990fd3c9f05b46d73299"},"schema_version":"1.0"},"canonical_sha256":"1d07e6a5e01702e80e0d7b095970f6da7f57eb5b78373b5a0c3b2efe3c40617e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:24.679991Z","signature_b64":"u3hfm+MZ0N3AAxgM3q1Xn10Jvy8AYHJFP4saiZyyZy+479gdOKJstnnbZ4jvk6VnmrYkUQYLyjgrwNkvTQDVDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d07e6a5e01702e80e0d7b095970f6da7f57eb5b78373b5a0c3b2efe3c40617e","last_reissued_at":"2026-07-05T08:27:24.679584Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:24.679584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.08848","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:27:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ybMUoWmRfQu1SCddWknl/OTJnkDHqAarxFtXqxSRaJwKQOWGcv/P2AlSDo8JMSbyfUO9muhA1/f7R/LojK0TCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:01:42.548621Z"},"content_sha256":"8280bb402a85e196c8cd43dfffa49ecfaf564836b1f60f651888f9b84bf310a1","schema_version":"1.0","event_id":"sha256:8280bb402a85e196c8cd43dfffa49ecfaf564836b1f60f651888f9b84bf310a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DUD6NJPAC4BOQDQNPMEVS4HW3J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hybrid Inverse Reinforcement Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gokul Swamy, J. Andrew Bagnell, Juntao Ren, Sanjiban Choudhury, Zhiwei Steven Wu","submitted_at":"2024-02-13T23:29:09Z","abstract_excerpt":"The inverse reinforcement learning approach to imitation learning is a double-edged sword. On the one hand, it can enable learning from a smaller number of expert demonstrations with more robustness to error compounding than behavioral cloning approaches. On the other hand, it requires that the learner repeatedly solve a computationally expensive reinforcement learning (RL) problem. Often, much of this computation is wasted searching over policies very dissimilar to the expert's. In this work, we propose using hybrid RL -- training on a mixture of online and expert data -- to curtail unnecessa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08848","kind":"arxiv","version":2},"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/2402.08848/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":"2026-07-05T08:27:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y8/Pd5CUydoH+9KRpnhrUsRleXKRBDsgeM9XUBvby3tL2Xnqd52pwcOMyU/6oTrDeXHkuvHrKGqEXY4Oz3pbBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:01:42.549118Z"},"content_sha256":"b1dd8e09042f53ebbbc3779e03210431f4a0f1a0c5ecf22cfa81e8469801bb02","schema_version":"1.0","event_id":"sha256:b1dd8e09042f53ebbbc3779e03210431f4a0f1a0c5ecf22cfa81e8469801bb02"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DUD6NJPAC4BOQDQNPMEVS4HW3J/bundle.json","state_url":"https://pith.science/pith/DUD6NJPAC4BOQDQNPMEVS4HW3J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DUD6NJPAC4BOQDQNPMEVS4HW3J/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":"2026-08-04T16:01:42Z","links":{"resolver":"https://pith.science/pith/DUD6NJPAC4BOQDQNPMEVS4HW3J","bundle":"https://pith.science/pith/DUD6NJPAC4BOQDQNPMEVS4HW3J/bundle.json","state":"https://pith.science/pith/DUD6NJPAC4BOQDQNPMEVS4HW3J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DUD6NJPAC4BOQDQNPMEVS4HW3J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DUD6NJPAC4BOQDQNPMEVS4HW3J","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":"dba7f182f5c21223d0f1c9c5234f2ab02232ef2e84a1990fd3c9f05b46d73299","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-13T23:29:09Z","title_canon_sha256":"72ee7ae4d094aea124d0d5b29330751eead2f61995f545a2871b8a52888541b5"},"schema_version":"1.0","source":{"id":"2402.08848","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.08848","created_at":"2026-07-05T08:27:24Z"},{"alias_kind":"arxiv_version","alias_value":"2402.08848v2","created_at":"2026-07-05T08:27:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08848","created_at":"2026-07-05T08:27:24Z"},{"alias_kind":"pith_short_12","alias_value":"DUD6NJPAC4BO","created_at":"2026-07-05T08:27:24Z"},{"alias_kind":"pith_short_16","alias_value":"DUD6NJPAC4BOQDQN","created_at":"2026-07-05T08:27:24Z"},{"alias_kind":"pith_short_8","alias_value":"DUD6NJPA","created_at":"2026-07-05T08:27:24Z"}],"graph_snapshots":[{"event_id":"sha256:b1dd8e09042f53ebbbc3779e03210431f4a0f1a0c5ecf22cfa81e8469801bb02","target":"graph","created_at":"2026-07-05T08:27:24Z","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/2402.08848/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The inverse reinforcement learning approach to imitation learning is a double-edged sword. On the one hand, it can enable learning from a smaller number of expert demonstrations with more robustness to error compounding than behavioral cloning approaches. On the other hand, it requires that the learner repeatedly solve a computationally expensive reinforcement learning (RL) problem. Often, much of this computation is wasted searching over policies very dissimilar to the expert's. In this work, we propose using hybrid RL -- training on a mixture of online and expert data -- to curtail unnecessa","authors_text":"Gokul Swamy, J. Andrew Bagnell, Juntao Ren, Sanjiban Choudhury, Zhiwei Steven Wu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-13T23:29:09Z","title":"Hybrid Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08848","kind":"arxiv","version":2},"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":"sha256:8280bb402a85e196c8cd43dfffa49ecfaf564836b1f60f651888f9b84bf310a1","target":"record","created_at":"2026-07-05T08:27:24Z","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":"dba7f182f5c21223d0f1c9c5234f2ab02232ef2e84a1990fd3c9f05b46d73299","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-13T23:29:09Z","title_canon_sha256":"72ee7ae4d094aea124d0d5b29330751eead2f61995f545a2871b8a52888541b5"},"schema_version":"1.0","source":{"id":"2402.08848","kind":"arxiv","version":2}},"canonical_sha256":"1d07e6a5e01702e80e0d7b095970f6da7f57eb5b78373b5a0c3b2efe3c40617e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d07e6a5e01702e80e0d7b095970f6da7f57eb5b78373b5a0c3b2efe3c40617e","first_computed_at":"2026-07-05T08:27:24.679584Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:24.679584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u3hfm+MZ0N3AAxgM3q1Xn10Jvy8AYHJFP4saiZyyZy+479gdOKJstnnbZ4jvk6VnmrYkUQYLyjgrwNkvTQDVDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:24.679991Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.08848","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8280bb402a85e196c8cd43dfffa49ecfaf564836b1f60f651888f9b84bf310a1","sha256:b1dd8e09042f53ebbbc3779e03210431f4a0f1a0c5ecf22cfa81e8469801bb02"],"state_sha256":"4737b1d30ef8cb09720ea7bbc65dd665bc86e7152dc5d2558b693daf0963def5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K2+ypLyFPZSyex34uhR8izK1xnuiVYyVYzKdhcNos2p7mxNE2v3uNugyjbMuQwMrgxZeT9Tm0qc/ufjC5cv2Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T16:01:42.584142Z","bundle_sha256":"dd2eee846ac3f76b0dfa965ebee8401520cd9ebdd26dfbbd6f2b850cdb5132e3"}}