{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:CUZ74N6TLZ7XVEWJ4U4VWYQDUJ","short_pith_number":"pith:CUZ74N6T","canonical_record":{"source":{"id":"2006.05094","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-09T07:45:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fcae71b3130344c72d8562b0b3743baf103472bff5ee71143625dae754c8956d","abstract_canon_sha256":"091a525d5803f748a84c6ac7b9e0bab396db83f9cfbf20cc8256e9eae36a2f1e"},"schema_version":"1.0"},"canonical_sha256":"1533fe37d35e7f7a92c9e5395b6203a24cc335f38f1d9004d1eaef34507c5246","source":{"kind":"arxiv","id":"2006.05094","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.05094","created_at":"2026-07-05T02:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"2006.05094v2","created_at":"2026-07-05T02:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.05094","created_at":"2026-07-05T02:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"CUZ74N6TLZ7X","created_at":"2026-07-05T02:04:57Z"},{"alias_kind":"pith_short_16","alias_value":"CUZ74N6TLZ7XVEWJ","created_at":"2026-07-05T02:04:57Z"},{"alias_kind":"pith_short_8","alias_value":"CUZ74N6T","created_at":"2026-07-05T02:04:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:CUZ74N6TLZ7XVEWJ4U4VWYQDUJ","target":"record","payload":{"canonical_record":{"source":{"id":"2006.05094","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-09T07:45:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fcae71b3130344c72d8562b0b3743baf103472bff5ee71143625dae754c8956d","abstract_canon_sha256":"091a525d5803f748a84c6ac7b9e0bab396db83f9cfbf20cc8256e9eae36a2f1e"},"schema_version":"1.0"},"canonical_sha256":"1533fe37d35e7f7a92c9e5395b6203a24cc335f38f1d9004d1eaef34507c5246","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:04:57.239083Z","signature_b64":"DWB1LiTnPpJV8fsAIb+w6z1xJoooK54vFRd4iCqHabK7YtSp2yXVpFa4y3nfLpwoqjG9lctl6SeoaErbmwoPAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1533fe37d35e7f7a92c9e5395b6203a24cc335f38f1d9004d1eaef34507c5246","last_reissued_at":"2026-07-05T02:04:57.238716Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:04:57.238716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.05094","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":"2026-07-05T02:04:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qqBp+YhDajC5qd5e8NzYnYf02gWX+EVWA1VqrHvevVveT/1dGYReHN/IsdumTpts63pn6O++LjGy3JwQgJS1Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:41:39.549975Z"},"content_sha256":"e831a613ddf0874b4451a40073c889494aa263b8e7adeddd244734a782e00ad8","schema_version":"1.0","event_id":"sha256:e831a613ddf0874b4451a40073c889494aa263b8e7adeddd244734a782e00ad8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:CUZ74N6TLZ7XVEWJ4U4VWYQDUJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meta-Learning Bandit Policies by Gradient Ascent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Branislav Kveton, Chih-wei Hsu, Craig Boutilier, Csaba Szepesvari, Manzil Zaheer, Martin Mladenov","submitted_at":"2020-06-09T07:45:41Z","abstract_excerpt":"Most bandit policies are designed to either minimize regret in any problem instance, making very few assumptions about the underlying environment, or in a Bayesian sense, assuming a prior distribution over environment parameters. The former are often too conservative in practical settings, while the latter require assumptions that are hard to verify in practice. We study bandit problems that fall between these two extremes, where the learning agent has access to sampled bandit instances from an unknown prior distribution $\\mathcal{P}$ and aims to achieve high reward on average over the bandit "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.05094","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/2006.05094/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":"2026-07-05T02:04:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3muan5QzOv2Jzy4G1aKxKNwzgXBenM2fBNxNjvbjzlLisT0n1B3btGSKnxjyOdtN55unYmOu5I6S3FO28hwsAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:41:39.550484Z"},"content_sha256":"dd070f3d27746050d5113c931bd8875a98a20b729f2cb74ce6a6056aea0f8db5","schema_version":"1.0","event_id":"sha256:dd070f3d27746050d5113c931bd8875a98a20b729f2cb74ce6a6056aea0f8db5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CUZ74N6TLZ7XVEWJ4U4VWYQDUJ/bundle.json","state_url":"https://pith.science/pith/CUZ74N6TLZ7XVEWJ4U4VWYQDUJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CUZ74N6TLZ7XVEWJ4U4VWYQDUJ/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":"2026-08-05T16:41:39Z","links":{"resolver":"https://pith.science/pith/CUZ74N6TLZ7XVEWJ4U4VWYQDUJ","bundle":"https://pith.science/pith/CUZ74N6TLZ7XVEWJ4U4VWYQDUJ/bundle.json","state":"https://pith.science/pith/CUZ74N6TLZ7XVEWJ4U4VWYQDUJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CUZ74N6TLZ7XVEWJ4U4VWYQDUJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:CUZ74N6TLZ7XVEWJ4U4VWYQDUJ","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":"091a525d5803f748a84c6ac7b9e0bab396db83f9cfbf20cc8256e9eae36a2f1e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-09T07:45:41Z","title_canon_sha256":"fcae71b3130344c72d8562b0b3743baf103472bff5ee71143625dae754c8956d"},"schema_version":"1.0","source":{"id":"2006.05094","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.05094","created_at":"2026-07-05T02:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"2006.05094v2","created_at":"2026-07-05T02:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.05094","created_at":"2026-07-05T02:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"CUZ74N6TLZ7X","created_at":"2026-07-05T02:04:57Z"},{"alias_kind":"pith_short_16","alias_value":"CUZ74N6TLZ7XVEWJ","created_at":"2026-07-05T02:04:57Z"},{"alias_kind":"pith_short_8","alias_value":"CUZ74N6T","created_at":"2026-07-05T02:04:57Z"}],"graph_snapshots":[{"event_id":"sha256:dd070f3d27746050d5113c931bd8875a98a20b729f2cb74ce6a6056aea0f8db5","target":"graph","created_at":"2026-07-05T02:04:57Z","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/2006.05094/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most bandit policies are designed to either minimize regret in any problem instance, making very few assumptions about the underlying environment, or in a Bayesian sense, assuming a prior distribution over environment parameters. The former are often too conservative in practical settings, while the latter require assumptions that are hard to verify in practice. We study bandit problems that fall between these two extremes, where the learning agent has access to sampled bandit instances from an unknown prior distribution $\\mathcal{P}$ and aims to achieve high reward on average over the bandit ","authors_text":"Branislav Kveton, Chih-wei Hsu, Craig Boutilier, Csaba Szepesvari, Manzil Zaheer, Martin Mladenov","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-09T07:45:41Z","title":"Meta-Learning Bandit Policies by Gradient Ascent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.05094","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:e831a613ddf0874b4451a40073c889494aa263b8e7adeddd244734a782e00ad8","target":"record","created_at":"2026-07-05T02:04:57Z","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":"091a525d5803f748a84c6ac7b9e0bab396db83f9cfbf20cc8256e9eae36a2f1e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-09T07:45:41Z","title_canon_sha256":"fcae71b3130344c72d8562b0b3743baf103472bff5ee71143625dae754c8956d"},"schema_version":"1.0","source":{"id":"2006.05094","kind":"arxiv","version":2}},"canonical_sha256":"1533fe37d35e7f7a92c9e5395b6203a24cc335f38f1d9004d1eaef34507c5246","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1533fe37d35e7f7a92c9e5395b6203a24cc335f38f1d9004d1eaef34507c5246","first_computed_at":"2026-07-05T02:04:57.238716Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:04:57.238716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DWB1LiTnPpJV8fsAIb+w6z1xJoooK54vFRd4iCqHabK7YtSp2yXVpFa4y3nfLpwoqjG9lctl6SeoaErbmwoPAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:04:57.239083Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.05094","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e831a613ddf0874b4451a40073c889494aa263b8e7adeddd244734a782e00ad8","sha256:dd070f3d27746050d5113c931bd8875a98a20b729f2cb74ce6a6056aea0f8db5"],"state_sha256":"9421591c09a216e7fe22b92953ef1306d0c3364dafa035e963cc5a9dcd7f4379"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dr1XDGv47Y+YgOkXxDDgiSBz5z/cqc7+GDarPdncCWXem5A3k2PHyLpbKnVQmBET4vulXo2be0pyTAZbw5BUCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T16:41:39.556409Z","bundle_sha256":"38df0e30a4b9b47e9e7ff8fa3f60dab276d6e1bb57693db495093cb9a809c437"}}