{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2MMOMXV7XOK3ZYGJSPFJ7U6QUP","short_pith_number":"pith:2MMOMXV7","canonical_record":{"source":{"id":"2605.23650","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-22T14:00:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b38529485c556c672486cbebdb1d3ab5cfaea5dac2a490932390262bd5e6896a","abstract_canon_sha256":"8309046bac009f64967d38b95115b4e890dae72eb14e3c398b0d6bad4181e1d3"},"schema_version":"1.0"},"canonical_sha256":"d318e65ebfbb95bce0c993ca9fd3d0a3c26df71dd7c4e1291b6127d37ee685af","source":{"kind":"arxiv","id":"2605.23650","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23650","created_at":"2026-05-25T02:02:23Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23650v1","created_at":"2026-05-25T02:02:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23650","created_at":"2026-05-25T02:02:23Z"},{"alias_kind":"pith_short_12","alias_value":"2MMOMXV7XOK3","created_at":"2026-05-25T02:02:23Z"},{"alias_kind":"pith_short_16","alias_value":"2MMOMXV7XOK3ZYGJ","created_at":"2026-05-25T02:02:23Z"},{"alias_kind":"pith_short_8","alias_value":"2MMOMXV7","created_at":"2026-05-25T02:02:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2MMOMXV7XOK3ZYGJSPFJ7U6QUP","target":"record","payload":{"canonical_record":{"source":{"id":"2605.23650","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-22T14:00:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b38529485c556c672486cbebdb1d3ab5cfaea5dac2a490932390262bd5e6896a","abstract_canon_sha256":"8309046bac009f64967d38b95115b4e890dae72eb14e3c398b0d6bad4181e1d3"},"schema_version":"1.0"},"canonical_sha256":"d318e65ebfbb95bce0c993ca9fd3d0a3c26df71dd7c4e1291b6127d37ee685af","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:23.952634Z","signature_b64":"624AxNk6bwoGiv3MkjTY8OvSd3rNmwgUU/766Rb3PFenVJZssbVR1WjtdHhTWEfRqTUVp+COLC+rIcGQe7eDAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d318e65ebfbb95bce0c993ca9fd3d0a3c26df71dd7c4e1291b6127d37ee685af","last_reissued_at":"2026-05-25T02:02:23.951669Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:23.951669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.23650","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":"2026-05-25T02:02:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mzJlgEUIyAiLWL800lQ6S1WxQz9vKizEe+pFjdjE+egOTrfP7Q9oWkyUFOsqJEpKEzz6zF1M73FlcpiPidJIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:16:48.761922Z"},"content_sha256":"ca5c9223cec63044485898bff0b52b80fcf2fbe707d743a1cda16bb5db2a6908","schema_version":"1.0","event_id":"sha256:ca5c9223cec63044485898bff0b52b80fcf2fbe707d743a1cda16bb5db2a6908"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2MMOMXV7XOK3ZYGJSPFJ7U6QUP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Kernel-Based MDPs from Episodic Preferential Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Nikola Pavlovic, Qing Zhao, Sattar Vakili","submitted_at":"2026-05-22T14:00:37Z","abstract_excerpt":"Human feedback often arrives as preferences rather than calibrated numeric rewards, motivating reinforcement learning from preferential feedback, also referred to as reinforcement learning from human feedback (RLHF). We present a rigorous theoretical study of preference-only learning in episodic kernel MDPs. In each episode, the learner deploys two policies from a common start state and receives a single binary label indicating which trajectory is preferred, modeled by a Bradley--Terry--Luce link on the difference of cumulative (unobserved) rewards. Under kernel-based assumptions on the reward"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23650","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/2605.23650/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":"2026-05-25T02:02:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/ZVGhbVjTAoUDyy5/7ugqYj75BqeOE+QK5VWQ/SRJXVswy3Ky/syE3VT+JLyWK0OoHVZXjEGRXJASe9OSwSgBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:16:48.762802Z"},"content_sha256":"7e6d6db075dd7f6a16c8d364e208ead0797c0f8d0ac649e853047924d073ac34","schema_version":"1.0","event_id":"sha256:7e6d6db075dd7f6a16c8d364e208ead0797c0f8d0ac649e853047924d073ac34"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2MMOMXV7XOK3ZYGJSPFJ7U6QUP/bundle.json","state_url":"https://pith.science/pith/2MMOMXV7XOK3ZYGJSPFJ7U6QUP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2MMOMXV7XOK3ZYGJSPFJ7U6QUP/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":"2026-05-30T13:16:48Z","links":{"resolver":"https://pith.science/pith/2MMOMXV7XOK3ZYGJSPFJ7U6QUP","bundle":"https://pith.science/pith/2MMOMXV7XOK3ZYGJSPFJ7U6QUP/bundle.json","state":"https://pith.science/pith/2MMOMXV7XOK3ZYGJSPFJ7U6QUP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2MMOMXV7XOK3ZYGJSPFJ7U6QUP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2MMOMXV7XOK3ZYGJSPFJ7U6QUP","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":"8309046bac009f64967d38b95115b4e890dae72eb14e3c398b0d6bad4181e1d3","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-22T14:00:37Z","title_canon_sha256":"b38529485c556c672486cbebdb1d3ab5cfaea5dac2a490932390262bd5e6896a"},"schema_version":"1.0","source":{"id":"2605.23650","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23650","created_at":"2026-05-25T02:02:23Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23650v1","created_at":"2026-05-25T02:02:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23650","created_at":"2026-05-25T02:02:23Z"},{"alias_kind":"pith_short_12","alias_value":"2MMOMXV7XOK3","created_at":"2026-05-25T02:02:23Z"},{"alias_kind":"pith_short_16","alias_value":"2MMOMXV7XOK3ZYGJ","created_at":"2026-05-25T02:02:23Z"},{"alias_kind":"pith_short_8","alias_value":"2MMOMXV7","created_at":"2026-05-25T02:02:23Z"}],"graph_snapshots":[{"event_id":"sha256:7e6d6db075dd7f6a16c8d364e208ead0797c0f8d0ac649e853047924d073ac34","target":"graph","created_at":"2026-05-25T02:02:23Z","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/2605.23650/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human feedback often arrives as preferences rather than calibrated numeric rewards, motivating reinforcement learning from preferential feedback, also referred to as reinforcement learning from human feedback (RLHF). We present a rigorous theoretical study of preference-only learning in episodic kernel MDPs. In each episode, the learner deploys two policies from a common start state and receives a single binary label indicating which trajectory is preferred, modeled by a Bradley--Terry--Luce link on the difference of cumulative (unobserved) rewards. Under kernel-based assumptions on the reward","authors_text":"Nikola Pavlovic, Qing Zhao, Sattar Vakili","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-22T14:00:37Z","title":"Learning Kernel-Based MDPs from Episodic Preferential Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23650","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:ca5c9223cec63044485898bff0b52b80fcf2fbe707d743a1cda16bb5db2a6908","target":"record","created_at":"2026-05-25T02:02:23Z","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":"8309046bac009f64967d38b95115b4e890dae72eb14e3c398b0d6bad4181e1d3","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-22T14:00:37Z","title_canon_sha256":"b38529485c556c672486cbebdb1d3ab5cfaea5dac2a490932390262bd5e6896a"},"schema_version":"1.0","source":{"id":"2605.23650","kind":"arxiv","version":1}},"canonical_sha256":"d318e65ebfbb95bce0c993ca9fd3d0a3c26df71dd7c4e1291b6127d37ee685af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d318e65ebfbb95bce0c993ca9fd3d0a3c26df71dd7c4e1291b6127d37ee685af","first_computed_at":"2026-05-25T02:02:23.951669Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:02:23.951669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"624AxNk6bwoGiv3MkjTY8OvSd3rNmwgUU/766Rb3PFenVJZssbVR1WjtdHhTWEfRqTUVp+COLC+rIcGQe7eDAA==","signature_status":"signed_v1","signed_at":"2026-05-25T02:02:23.952634Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.23650","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca5c9223cec63044485898bff0b52b80fcf2fbe707d743a1cda16bb5db2a6908","sha256:7e6d6db075dd7f6a16c8d364e208ead0797c0f8d0ac649e853047924d073ac34"],"state_sha256":"28aa7c0d8ad14dcb251dcd7e2d6f28c2d5d89bfd9180e1b76d7365c8966ce462"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5KErYHL9xLYxthR7FuKIiW4BfaBgiy5MWbLYfNouXbynuR6CHYgtP5kPHIoUyLrL0n3PY2hj0jBFEK1eUraICQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T13:16:48.766873Z","bundle_sha256":"898ca11a07bc6ad63d527609932055dc6badbc68db158948c2e4829241654a8a"}}