{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:CPIB64CBARGL3GRDWCXQTSR7OC","short_pith_number":"pith:CPIB64CB","canonical_record":{"source":{"id":"1901.08159","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-01-23T22:52:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9bc2090543a04f812241671728998fcf5dba73e0749f878c4812f644c3ea6758","abstract_canon_sha256":"79539704edf037399c317d65abb77615b9900ed3d665f4290b7b24b37eae26e3"},"schema_version":"1.0"},"canonical_sha256":"13d01f7041044cbd9a23b0af09ca3f70a9fd32bae2dee9c996fde4a556509d62","source":{"kind":"arxiv","id":"1901.08159","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08159","created_at":"2026-05-17T23:55:37Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08159v1","created_at":"2026-05-17T23:55:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08159","created_at":"2026-05-17T23:55:37Z"},{"alias_kind":"pith_short_12","alias_value":"CPIB64CBARGL","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"CPIB64CBARGL3GRD","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"CPIB64CB","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:CPIB64CBARGL3GRDWCXQTSR7OC","target":"record","payload":{"canonical_record":{"source":{"id":"1901.08159","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-01-23T22:52:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9bc2090543a04f812241671728998fcf5dba73e0749f878c4812f644c3ea6758","abstract_canon_sha256":"79539704edf037399c317d65abb77615b9900ed3d665f4290b7b24b37eae26e3"},"schema_version":"1.0"},"canonical_sha256":"13d01f7041044cbd9a23b0af09ca3f70a9fd32bae2dee9c996fde4a556509d62","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:37.793761Z","signature_b64":"dk7wVI6Ot0wA7jW1rS7EfsEmN3Br0xw5tzyQsTSbj85vGo1SY/hx2dtiJExWBO6vUYEtHKy1kGsIBXqh2RvcBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13d01f7041044cbd9a23b0af09ca3f70a9fd32bae2dee9c996fde4a556509d62","last_reissued_at":"2026-05-17T23:55:37.793261Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:37.793261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.08159","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":"2026-05-17T23:55:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3VUzlIpF+4tZLGI+XWoTshqMGsv2yvG0+vBud/KjUATx5quUPFI2Lueh37bBZKUZV7vrARn4LTmdeYsk+RutBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T08:41:54.337124Z"},"content_sha256":"97eb3161920940320b4081550b9f84f9cc512fcd3abd8203d56c81b5b4f516cb","schema_version":"1.0","event_id":"sha256:97eb3161920940320b4081550b9f84f9cc512fcd3abd8203d56c81b5b4f516cb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:CPIB64CBARGL3GRDWCXQTSR7OC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meta-Learning for Contextual Bandit Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Amr Sharaf, Hal Daum\\'e III","submitted_at":"2019-01-23T22:52:13Z","abstract_excerpt":"We describe MELEE, a meta-learning algorithm for learning a good exploration policy in the interactive contextual bandit setting. Here, an algorithm must take actions based on contexts, and learn based only on a reward signal from the action taken, thereby generating an exploration/exploitation trade-off. MELEE addresses this trade-off by learning a good exploration strategy for offline tasks based on synthetic data, on which it can simulate the contextual bandit setting. Based on these simulations, MELEE uses an imitation learning strategy to learn a good exploration policy that can then be a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08159","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":""},"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":"2026-05-17T23:55:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VF3gwEgFKqlRGw3wGIqRrD19ecKTuFzMNDR/QCQqYE+tMcMMO5R2TRMf1Li068QaAiriZtLxSA4VypWHYzGnAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T08:41:54.337493Z"},"content_sha256":"e99add5f4ad194ad8d1a86c1b43e73c264078cf8aacabf644c54eda6f3fd45be","schema_version":"1.0","event_id":"sha256:e99add5f4ad194ad8d1a86c1b43e73c264078cf8aacabf644c54eda6f3fd45be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CPIB64CBARGL3GRDWCXQTSR7OC/bundle.json","state_url":"https://pith.science/pith/CPIB64CBARGL3GRDWCXQTSR7OC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CPIB64CBARGL3GRDWCXQTSR7OC/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":"2026-06-07T08:41:54Z","links":{"resolver":"https://pith.science/pith/CPIB64CBARGL3GRDWCXQTSR7OC","bundle":"https://pith.science/pith/CPIB64CBARGL3GRDWCXQTSR7OC/bundle.json","state":"https://pith.science/pith/CPIB64CBARGL3GRDWCXQTSR7OC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CPIB64CBARGL3GRDWCXQTSR7OC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:CPIB64CBARGL3GRDWCXQTSR7OC","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":"79539704edf037399c317d65abb77615b9900ed3d665f4290b7b24b37eae26e3","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-01-23T22:52:13Z","title_canon_sha256":"9bc2090543a04f812241671728998fcf5dba73e0749f878c4812f644c3ea6758"},"schema_version":"1.0","source":{"id":"1901.08159","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08159","created_at":"2026-05-17T23:55:37Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08159v1","created_at":"2026-05-17T23:55:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08159","created_at":"2026-05-17T23:55:37Z"},{"alias_kind":"pith_short_12","alias_value":"CPIB64CBARGL","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"CPIB64CBARGL3GRD","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"CPIB64CB","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:e99add5f4ad194ad8d1a86c1b43e73c264078cf8aacabf644c54eda6f3fd45be","target":"graph","created_at":"2026-05-17T23:55:37Z","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"},"paper":{"abstract_excerpt":"We describe MELEE, a meta-learning algorithm for learning a good exploration policy in the interactive contextual bandit setting. Here, an algorithm must take actions based on contexts, and learn based only on a reward signal from the action taken, thereby generating an exploration/exploitation trade-off. MELEE addresses this trade-off by learning a good exploration strategy for offline tasks based on synthetic data, on which it can simulate the contextual bandit setting. Based on these simulations, MELEE uses an imitation learning strategy to learn a good exploration policy that can then be a","authors_text":"Amr Sharaf, Hal Daum\\'e III","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-01-23T22:52:13Z","title":"Meta-Learning for Contextual Bandit Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08159","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":"sha256:97eb3161920940320b4081550b9f84f9cc512fcd3abd8203d56c81b5b4f516cb","target":"record","created_at":"2026-05-17T23:55:37Z","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":"79539704edf037399c317d65abb77615b9900ed3d665f4290b7b24b37eae26e3","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-01-23T22:52:13Z","title_canon_sha256":"9bc2090543a04f812241671728998fcf5dba73e0749f878c4812f644c3ea6758"},"schema_version":"1.0","source":{"id":"1901.08159","kind":"arxiv","version":1}},"canonical_sha256":"13d01f7041044cbd9a23b0af09ca3f70a9fd32bae2dee9c996fde4a556509d62","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13d01f7041044cbd9a23b0af09ca3f70a9fd32bae2dee9c996fde4a556509d62","first_computed_at":"2026-05-17T23:55:37.793261Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:37.793261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dk7wVI6Ot0wA7jW1rS7EfsEmN3Br0xw5tzyQsTSbj85vGo1SY/hx2dtiJExWBO6vUYEtHKy1kGsIBXqh2RvcBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:37.793761Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.08159","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97eb3161920940320b4081550b9f84f9cc512fcd3abd8203d56c81b5b4f516cb","sha256:e99add5f4ad194ad8d1a86c1b43e73c264078cf8aacabf644c54eda6f3fd45be"],"state_sha256":"a0daa5ce808bea1b277ffcb06e2ff6c9ff8ae12a538c4cd9c82de7d335a55f88"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"brT7OqxPiptlQtc7+v97NS6hp8Nm9UgipW1X9kFfSgJ55aqSHkB2l9NAIKmedDeC0atlg0nwRkByrLoPAVqzDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T08:41:54.339570Z","bundle_sha256":"1da66994fafce6797bd6600d79dbf6076281666199a43e1eac734e4704c3cf3e"}}