{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:H2AEMYIXX3ZCQDFYHUIRTSD7BO","short_pith_number":"pith:H2AEMYIX","canonical_record":{"source":{"id":"2308.12573","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-24T05:26:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e30dfe7ae87577cf20017ec22d6e9cb1cd234fa18bed5ae4b07fb5fb24b7bedd","abstract_canon_sha256":"b3463308e92b782a98287beafbfe6182463b43fc372f506a5c2d64634a4993ad"},"schema_version":"1.0"},"canonical_sha256":"3e80466117bef2280cb83d1119c87f0b9d7d675dfc635d0d03d2bc2c37a914e7","source":{"kind":"arxiv","id":"2308.12573","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.12573","created_at":"2026-07-05T06:44:14Z"},{"alias_kind":"arxiv_version","alias_value":"2308.12573v1","created_at":"2026-07-05T06:44:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12573","created_at":"2026-07-05T06:44:14Z"},{"alias_kind":"pith_short_12","alias_value":"H2AEMYIXX3ZC","created_at":"2026-07-05T06:44:14Z"},{"alias_kind":"pith_short_16","alias_value":"H2AEMYIXX3ZCQDFY","created_at":"2026-07-05T06:44:14Z"},{"alias_kind":"pith_short_8","alias_value":"H2AEMYIX","created_at":"2026-07-05T06:44:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:H2AEMYIXX3ZCQDFYHUIRTSD7BO","target":"record","payload":{"canonical_record":{"source":{"id":"2308.12573","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-24T05:26:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e30dfe7ae87577cf20017ec22d6e9cb1cd234fa18bed5ae4b07fb5fb24b7bedd","abstract_canon_sha256":"b3463308e92b782a98287beafbfe6182463b43fc372f506a5c2d64634a4993ad"},"schema_version":"1.0"},"canonical_sha256":"3e80466117bef2280cb83d1119c87f0b9d7d675dfc635d0d03d2bc2c37a914e7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:44:14.616442Z","signature_b64":"DSV1rH9I82Q+zkDBrz4Us/yGHd0iTkoOWtDsbj+eyzBFWO6k3IFI24dq7bdQLArf2Nlml/zkcLX2N4IsLUdGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e80466117bef2280cb83d1119c87f0b9d7d675dfc635d0d03d2bc2c37a914e7","last_reissued_at":"2026-07-05T06:44:14.616050Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:44:14.616050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.12573","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":"2026-07-05T06:44:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Hhg9qUSbV0WpPabSKja9RbilQ/Mqi15s4bQg6PXp6gj7LhLQ4iEqyJJBpgGf7lFom+EdzG0PlrEHinHma4gBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T19:06:06.938585Z"},"content_sha256":"46deb67e3fe33ffdd92b7fe8b8ecc4a114e0cbc53415d1d0b906361bdc5db7e1","schema_version":"1.0","event_id":"sha256:46deb67e3fe33ffdd92b7fe8b8ecc4a114e0cbc53415d1d0b906361bdc5db7e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:H2AEMYIXX3ZCQDFYHUIRTSD7BO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Conditional Kernel Imitation Learning for Continuous State Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ashutosh Nayyar, Nathan Dahlin, Rahul Jain, Rishabh Agrawal","submitted_at":"2023-08-24T05:26:42Z","abstract_excerpt":"Imitation Learning (IL) is an important paradigm within the broader reinforcement learning (RL) methodology. Unlike most of RL, it does not assume availability of reward-feedback. Reward inference and shaping are known to be difficult and error-prone methods particularly when the demonstration data comes from human experts. Classical methods such as behavioral cloning and inverse reinforcement learning are highly sensitive to estimation errors, a problem that is particularly acute in continuous state space problems. Meanwhile, state-of-the-art IL algorithms convert behavioral policy learning p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12573","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/2308.12573/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":"2026-07-05T06:44:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IRBwm2Ep6ERT+dIWyjwiQ5DdjUxn4DzU8Zlk2Rs6mZdv+Tj5spgZ/UDFzXW71X8t3R7rpAVvjq1vqMYxSimMAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T19:06:06.939098Z"},"content_sha256":"9561d43fc7ecaf41d994aff55d75fdb89c472b9a1cb4ce3adc85ef694b3dc658","schema_version":"1.0","event_id":"sha256:9561d43fc7ecaf41d994aff55d75fdb89c472b9a1cb4ce3adc85ef694b3dc658"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H2AEMYIXX3ZCQDFYHUIRTSD7BO/bundle.json","state_url":"https://pith.science/pith/H2AEMYIXX3ZCQDFYHUIRTSD7BO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H2AEMYIXX3ZCQDFYHUIRTSD7BO/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":"2026-08-12T19:06:06Z","links":{"resolver":"https://pith.science/pith/H2AEMYIXX3ZCQDFYHUIRTSD7BO","bundle":"https://pith.science/pith/H2AEMYIXX3ZCQDFYHUIRTSD7BO/bundle.json","state":"https://pith.science/pith/H2AEMYIXX3ZCQDFYHUIRTSD7BO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H2AEMYIXX3ZCQDFYHUIRTSD7BO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:H2AEMYIXX3ZCQDFYHUIRTSD7BO","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":"b3463308e92b782a98287beafbfe6182463b43fc372f506a5c2d64634a4993ad","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-24T05:26:42Z","title_canon_sha256":"e30dfe7ae87577cf20017ec22d6e9cb1cd234fa18bed5ae4b07fb5fb24b7bedd"},"schema_version":"1.0","source":{"id":"2308.12573","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.12573","created_at":"2026-07-05T06:44:14Z"},{"alias_kind":"arxiv_version","alias_value":"2308.12573v1","created_at":"2026-07-05T06:44:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12573","created_at":"2026-07-05T06:44:14Z"},{"alias_kind":"pith_short_12","alias_value":"H2AEMYIXX3ZC","created_at":"2026-07-05T06:44:14Z"},{"alias_kind":"pith_short_16","alias_value":"H2AEMYIXX3ZCQDFY","created_at":"2026-07-05T06:44:14Z"},{"alias_kind":"pith_short_8","alias_value":"H2AEMYIX","created_at":"2026-07-05T06:44:14Z"}],"graph_snapshots":[{"event_id":"sha256:9561d43fc7ecaf41d994aff55d75fdb89c472b9a1cb4ce3adc85ef694b3dc658","target":"graph","created_at":"2026-07-05T06:44:14Z","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/2308.12573/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Imitation Learning (IL) is an important paradigm within the broader reinforcement learning (RL) methodology. Unlike most of RL, it does not assume availability of reward-feedback. Reward inference and shaping are known to be difficult and error-prone methods particularly when the demonstration data comes from human experts. Classical methods such as behavioral cloning and inverse reinforcement learning are highly sensitive to estimation errors, a problem that is particularly acute in continuous state space problems. Meanwhile, state-of-the-art IL algorithms convert behavioral policy learning p","authors_text":"Ashutosh Nayyar, Nathan Dahlin, Rahul Jain, Rishabh Agrawal","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-24T05:26:42Z","title":"Conditional Kernel Imitation Learning for Continuous State Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12573","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":"sha256:46deb67e3fe33ffdd92b7fe8b8ecc4a114e0cbc53415d1d0b906361bdc5db7e1","target":"record","created_at":"2026-07-05T06:44:14Z","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":"b3463308e92b782a98287beafbfe6182463b43fc372f506a5c2d64634a4993ad","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-24T05:26:42Z","title_canon_sha256":"e30dfe7ae87577cf20017ec22d6e9cb1cd234fa18bed5ae4b07fb5fb24b7bedd"},"schema_version":"1.0","source":{"id":"2308.12573","kind":"arxiv","version":1}},"canonical_sha256":"3e80466117bef2280cb83d1119c87f0b9d7d675dfc635d0d03d2bc2c37a914e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e80466117bef2280cb83d1119c87f0b9d7d675dfc635d0d03d2bc2c37a914e7","first_computed_at":"2026-07-05T06:44:14.616050Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:44:14.616050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DSV1rH9I82Q+zkDBrz4Us/yGHd0iTkoOWtDsbj+eyzBFWO6k3IFI24dq7bdQLArf2Nlml/zkcLX2N4IsLUdGBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:44:14.616442Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.12573","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:46deb67e3fe33ffdd92b7fe8b8ecc4a114e0cbc53415d1d0b906361bdc5db7e1","sha256:9561d43fc7ecaf41d994aff55d75fdb89c472b9a1cb4ce3adc85ef694b3dc658"],"state_sha256":"6e45dc3e7ba08db99a64e457a426de45e32a0229f9c6d04b0cb93f5d7bfa778f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tQyUoz//8Y4mSvmoQ57YhW+H6KWDBd1mQhFewbnzx42veUUWYikqjTljxkRB/eMW8xf7b/H8ve808AM4UwI1BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T19:06:06.943946Z","bundle_sha256":"fcb1f372c88d93a8d000f19c673c03c7db6449c7a08ade914652fa42bb8306b9"}}