{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FBAO75FPWXQCOAXTYAPINWYMZY","short_pith_number":"pith:FBAO75FP","canonical_record":{"source":{"id":"2303.11369","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-20T18:16:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6c3ad5fedc9e2f6749cb7b0ba293f082b72bcab756d79bc8a0e20bb35599736e","abstract_canon_sha256":"ae7c61e9ba8508937734127712720902a8e37f079cc22d37948cd2694a8abaed"},"schema_version":"1.0"},"canonical_sha256":"2840eff4afb5e02702f3c01e86db0cce10a9aa85f3a5bf7ca9ba9c1db08c9e42","source":{"kind":"arxiv","id":"2303.11369","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.11369","created_at":"2026-07-05T06:31:10Z"},{"alias_kind":"arxiv_version","alias_value":"2303.11369v2","created_at":"2026-07-05T06:31:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11369","created_at":"2026-07-05T06:31:10Z"},{"alias_kind":"pith_short_12","alias_value":"FBAO75FPWXQC","created_at":"2026-07-05T06:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"FBAO75FPWXQCOAXT","created_at":"2026-07-05T06:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"FBAO75FP","created_at":"2026-07-05T06:31:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FBAO75FPWXQCOAXTYAPINWYMZY","target":"record","payload":{"canonical_record":{"source":{"id":"2303.11369","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-20T18:16:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6c3ad5fedc9e2f6749cb7b0ba293f082b72bcab756d79bc8a0e20bb35599736e","abstract_canon_sha256":"ae7c61e9ba8508937734127712720902a8e37f079cc22d37948cd2694a8abaed"},"schema_version":"1.0"},"canonical_sha256":"2840eff4afb5e02702f3c01e86db0cce10a9aa85f3a5bf7ca9ba9c1db08c9e42","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:31:10.402561Z","signature_b64":"Z/wM42BTyaSUg1/+cJwEF3VjsuvoZ2mtJ3Q+TiB3g5/jnfRmsGThsMGvhC45VFrA7RU7UUWlLAPoRmNG4iHkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2840eff4afb5e02702f3c01e86db0cce10a9aa85f3a5bf7ca9ba9c1db08c9e42","last_reissued_at":"2026-07-05T06:31:10.401961Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:31:10.401961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.11369","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":"2026-07-05T06:31:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W9J1eDtyGcxyFd7b/MuW/fR+fOw2hrdJrrpv8s00ztr9qyvGRdTvD9T2KDw3EyMlbeCXpHEFJ+NpiYuJahN8Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T16:45:36.365538Z"},"content_sha256":"163e31eecf30c1e60133b6a45d4ce6e70f35ae50ab2a0893df69da19a28b6768","schema_version":"1.0","event_id":"sha256:163e31eecf30c1e60133b6a45d4ce6e70f35ae50ab2a0893df69da19a28b6768"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FBAO75FPWXQCOAXTYAPINWYMZY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bridging Imitation and Online Reinforcement Learning: An Optimistic Tale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Botao Hao, Dengwang Tang, Rahul Jain, Zheng Wen","submitted_at":"2023-03-20T18:16:25Z","abstract_excerpt":"In this paper, we address the following problem: Given an offline demonstration dataset from an imperfect expert, what is the best way to leverage it to bootstrap online learning performance in MDPs. We first propose an Informed Posterior Sampling-based RL (iPSRL) algorithm that uses the offline dataset, and information about the expert's behavioral policy used to generate the offline dataset. Its cumulative Bayesian regret goes down to zero exponentially fast in N, the offline dataset size if the expert is competent enough. Since this algorithm is computationally impractical, we then propose "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.11369","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/2303.11369/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":"2026-07-05T06:31:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G5TqPP1vKO94McT6ILRItui+gL6IGb6cWj7GFe7AYGpL91U3ouvrrDhJMb+WeRgdHzNksSGHhaS5IIfwXforDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T16:45:36.366057Z"},"content_sha256":"6d13dcabad32bb9012afc8ddd40c22c545c7dd83f3e42269479c78c8e8247e0b","schema_version":"1.0","event_id":"sha256:6d13dcabad32bb9012afc8ddd40c22c545c7dd83f3e42269479c78c8e8247e0b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FBAO75FPWXQCOAXTYAPINWYMZY/bundle.json","state_url":"https://pith.science/pith/FBAO75FPWXQCOAXTYAPINWYMZY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FBAO75FPWXQCOAXTYAPINWYMZY/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":"2026-08-12T16:45:36Z","links":{"resolver":"https://pith.science/pith/FBAO75FPWXQCOAXTYAPINWYMZY","bundle":"https://pith.science/pith/FBAO75FPWXQCOAXTYAPINWYMZY/bundle.json","state":"https://pith.science/pith/FBAO75FPWXQCOAXTYAPINWYMZY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FBAO75FPWXQCOAXTYAPINWYMZY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FBAO75FPWXQCOAXTYAPINWYMZY","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":"ae7c61e9ba8508937734127712720902a8e37f079cc22d37948cd2694a8abaed","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-20T18:16:25Z","title_canon_sha256":"6c3ad5fedc9e2f6749cb7b0ba293f082b72bcab756d79bc8a0e20bb35599736e"},"schema_version":"1.0","source":{"id":"2303.11369","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.11369","created_at":"2026-07-05T06:31:10Z"},{"alias_kind":"arxiv_version","alias_value":"2303.11369v2","created_at":"2026-07-05T06:31:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11369","created_at":"2026-07-05T06:31:10Z"},{"alias_kind":"pith_short_12","alias_value":"FBAO75FPWXQC","created_at":"2026-07-05T06:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"FBAO75FPWXQCOAXT","created_at":"2026-07-05T06:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"FBAO75FP","created_at":"2026-07-05T06:31:10Z"}],"graph_snapshots":[{"event_id":"sha256:6d13dcabad32bb9012afc8ddd40c22c545c7dd83f3e42269479c78c8e8247e0b","target":"graph","created_at":"2026-07-05T06:31:10Z","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/2303.11369/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we address the following problem: Given an offline demonstration dataset from an imperfect expert, what is the best way to leverage it to bootstrap online learning performance in MDPs. We first propose an Informed Posterior Sampling-based RL (iPSRL) algorithm that uses the offline dataset, and information about the expert's behavioral policy used to generate the offline dataset. Its cumulative Bayesian regret goes down to zero exponentially fast in N, the offline dataset size if the expert is competent enough. Since this algorithm is computationally impractical, we then propose ","authors_text":"Botao Hao, Dengwang Tang, Rahul Jain, Zheng Wen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-20T18:16:25Z","title":"Bridging Imitation and Online Reinforcement Learning: An Optimistic Tale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.11369","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":"sha256:163e31eecf30c1e60133b6a45d4ce6e70f35ae50ab2a0893df69da19a28b6768","target":"record","created_at":"2026-07-05T06:31:10Z","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":"ae7c61e9ba8508937734127712720902a8e37f079cc22d37948cd2694a8abaed","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-20T18:16:25Z","title_canon_sha256":"6c3ad5fedc9e2f6749cb7b0ba293f082b72bcab756d79bc8a0e20bb35599736e"},"schema_version":"1.0","source":{"id":"2303.11369","kind":"arxiv","version":2}},"canonical_sha256":"2840eff4afb5e02702f3c01e86db0cce10a9aa85f3a5bf7ca9ba9c1db08c9e42","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2840eff4afb5e02702f3c01e86db0cce10a9aa85f3a5bf7ca9ba9c1db08c9e42","first_computed_at":"2026-07-05T06:31:10.401961Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:31:10.401961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z/wM42BTyaSUg1/+cJwEF3VjsuvoZ2mtJ3Q+TiB3g5/jnfRmsGThsMGvhC45VFrA7RU7UUWlLAPoRmNG4iHkAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:31:10.402561Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.11369","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:163e31eecf30c1e60133b6a45d4ce6e70f35ae50ab2a0893df69da19a28b6768","sha256:6d13dcabad32bb9012afc8ddd40c22c545c7dd83f3e42269479c78c8e8247e0b"],"state_sha256":"e3230435f62d2cdfead984966a1d55cbda5fbc846c225f7bb788ba1a588eb244"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1RY1Sy0I3A3Zk/kHSKnE/AknCpbkA3pIuZ9VvSU4NoHGbGevb2e29f6c/mM7sm0chJDJPJmy6y4tJaCGsFJ6DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T16:45:36.371273Z","bundle_sha256":"86db5b5d7611a84373df51d9097a81b6a90e62fb7eec23f546a7942d8034c997"}}