{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SUDKTVIPTJ7D7W5PPEOLEZOXPN","short_pith_number":"pith:SUDKTVIP","canonical_record":{"source":{"id":"2502.08259","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T10:05:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c389cdb376f6d6835b6eaab6bd44859244c6e890e1663329137dc42a5f030dec","abstract_canon_sha256":"3278fe94cf83bf6d157a9ff501ed31ff8a1efbd44f9a6661622ff48744db0b3c"},"schema_version":"1.0"},"canonical_sha256":"9506a9d50f9a7e3fdbaf791cb265d77b76e0c846f851980dc9d3d5b17c4931f5","source":{"kind":"arxiv","id":"2502.08259","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08259","created_at":"2026-07-05T10:27:25Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08259v2","created_at":"2026-07-05T10:27:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08259","created_at":"2026-07-05T10:27:25Z"},{"alias_kind":"pith_short_12","alias_value":"SUDKTVIPTJ7D","created_at":"2026-07-05T10:27:25Z"},{"alias_kind":"pith_short_16","alias_value":"SUDKTVIPTJ7D7W5P","created_at":"2026-07-05T10:27:25Z"},{"alias_kind":"pith_short_8","alias_value":"SUDKTVIP","created_at":"2026-07-05T10:27:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SUDKTVIPTJ7D7W5PPEOLEZOXPN","target":"record","payload":{"canonical_record":{"source":{"id":"2502.08259","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T10:05:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c389cdb376f6d6835b6eaab6bd44859244c6e890e1663329137dc42a5f030dec","abstract_canon_sha256":"3278fe94cf83bf6d157a9ff501ed31ff8a1efbd44f9a6661622ff48744db0b3c"},"schema_version":"1.0"},"canonical_sha256":"9506a9d50f9a7e3fdbaf791cb265d77b76e0c846f851980dc9d3d5b17c4931f5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:25.033328Z","signature_b64":"UlTHYQlIJ78sLAOjPG8iomUYb0nRj2g/w35L1rlmFgP6QHT44hiElTtKDFDWC0ZASjteO9IHTXV22a6CxIGFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9506a9d50f9a7e3fdbaf791cb265d77b76e0c846f851980dc9d3d5b17c4931f5","last_reissued_at":"2026-07-05T10:27:25.032313Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:25.032313Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.08259","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":"2026-07-05T10:27:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HEo0mHLqgLVkCLIQvUJTG3ncXROE4y8DbhvNKz537I6mTnqPuZusllDMtWDQdtD8EwYLqanKGLujZVX+hOVLAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:53:55.880553Z"},"content_sha256":"4dbbbe02865fa30e01eb008bcd78499d7cb30539306fd4a8cf28a0674882033c","schema_version":"1.0","event_id":"sha256:4dbbbe02865fa30e01eb008bcd78499d7cb30539306fd4a8cf28a0674882033c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SUDKTVIPTJ7D7W5PPEOLEZOXPN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Balancing optimism and pessimism in offline-to-online learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Csaba Szepesvari, Flore Sentenac, Ilbin Lee","submitted_at":"2025-02-12T10:05:25Z","abstract_excerpt":"We consider what we call the offline-to-online learning setting, focusing on stochastic finite-armed bandit problems. In offline-to-online learning, a learner starts with offline data collected from interactions with an unknown environment in a way that is not under the learner's control. Given this data, the learner begins interacting with the environment, gradually improving its initial strategy as it collects more data to maximize its total reward. The learner in this setting faces a fundamental dilemma: if the policy is deployed for only a short period, a suitable strategy (in a number of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08259","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/2502.08259/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":"2026-07-05T10:27:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1YfDe0Ti7efaFAqTQV/qTYcedCJUSSPwtx2Z4PlCNuSuuDbO9UMNz51iNORyQQZxQ7V0z0rTqZdtcP4tvH3TAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:53:55.881079Z"},"content_sha256":"899e66654cd60d74c8a6c85b6922aab9946a68e7194ffed4cad44625df9a6a79","schema_version":"1.0","event_id":"sha256:899e66654cd60d74c8a6c85b6922aab9946a68e7194ffed4cad44625df9a6a79"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SUDKTVIPTJ7D7W5PPEOLEZOXPN/bundle.json","state_url":"https://pith.science/pith/SUDKTVIPTJ7D7W5PPEOLEZOXPN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SUDKTVIPTJ7D7W5PPEOLEZOXPN/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":"2026-08-08T17:53:55Z","links":{"resolver":"https://pith.science/pith/SUDKTVIPTJ7D7W5PPEOLEZOXPN","bundle":"https://pith.science/pith/SUDKTVIPTJ7D7W5PPEOLEZOXPN/bundle.json","state":"https://pith.science/pith/SUDKTVIPTJ7D7W5PPEOLEZOXPN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SUDKTVIPTJ7D7W5PPEOLEZOXPN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SUDKTVIPTJ7D7W5PPEOLEZOXPN","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":"3278fe94cf83bf6d157a9ff501ed31ff8a1efbd44f9a6661622ff48744db0b3c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T10:05:25Z","title_canon_sha256":"c389cdb376f6d6835b6eaab6bd44859244c6e890e1663329137dc42a5f030dec"},"schema_version":"1.0","source":{"id":"2502.08259","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08259","created_at":"2026-07-05T10:27:25Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08259v2","created_at":"2026-07-05T10:27:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08259","created_at":"2026-07-05T10:27:25Z"},{"alias_kind":"pith_short_12","alias_value":"SUDKTVIPTJ7D","created_at":"2026-07-05T10:27:25Z"},{"alias_kind":"pith_short_16","alias_value":"SUDKTVIPTJ7D7W5P","created_at":"2026-07-05T10:27:25Z"},{"alias_kind":"pith_short_8","alias_value":"SUDKTVIP","created_at":"2026-07-05T10:27:25Z"}],"graph_snapshots":[{"event_id":"sha256:899e66654cd60d74c8a6c85b6922aab9946a68e7194ffed4cad44625df9a6a79","target":"graph","created_at":"2026-07-05T10:27:25Z","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/2502.08259/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider what we call the offline-to-online learning setting, focusing on stochastic finite-armed bandit problems. In offline-to-online learning, a learner starts with offline data collected from interactions with an unknown environment in a way that is not under the learner's control. Given this data, the learner begins interacting with the environment, gradually improving its initial strategy as it collects more data to maximize its total reward. The learner in this setting faces a fundamental dilemma: if the policy is deployed for only a short period, a suitable strategy (in a number of ","authors_text":"Csaba Szepesvari, Flore Sentenac, Ilbin Lee","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T10:05:25Z","title":"Balancing optimism and pessimism in offline-to-online learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08259","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":"sha256:4dbbbe02865fa30e01eb008bcd78499d7cb30539306fd4a8cf28a0674882033c","target":"record","created_at":"2026-07-05T10:27:25Z","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":"3278fe94cf83bf6d157a9ff501ed31ff8a1efbd44f9a6661622ff48744db0b3c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T10:05:25Z","title_canon_sha256":"c389cdb376f6d6835b6eaab6bd44859244c6e890e1663329137dc42a5f030dec"},"schema_version":"1.0","source":{"id":"2502.08259","kind":"arxiv","version":2}},"canonical_sha256":"9506a9d50f9a7e3fdbaf791cb265d77b76e0c846f851980dc9d3d5b17c4931f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9506a9d50f9a7e3fdbaf791cb265d77b76e0c846f851980dc9d3d5b17c4931f5","first_computed_at":"2026-07-05T10:27:25.032313Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:27:25.032313Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UlTHYQlIJ78sLAOjPG8iomUYb0nRj2g/w35L1rlmFgP6QHT44hiElTtKDFDWC0ZASjteO9IHTXV22a6CxIGFAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:27:25.033328Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.08259","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4dbbbe02865fa30e01eb008bcd78499d7cb30539306fd4a8cf28a0674882033c","sha256:899e66654cd60d74c8a6c85b6922aab9946a68e7194ffed4cad44625df9a6a79"],"state_sha256":"a7c56b58504fcc660e97a4aa2658b609c35fe18d8a47da7e76d492db8327a1b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7n0qotSM1hwGf2WOZCM8Om1JPok1HI1+fHdSORhbfrRaRKJWu4zP5KguD8Y6PFb8fLFMwa1oe76k/YCAE7g1BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T17:53:55.884322Z","bundle_sha256":"5338ffcf95500045d66d7060c3c347330420a5980b2f47e6bf1416758082dac2"}}