{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:SFZIALG52DJDDVPO5I3IAI2VHR","short_pith_number":"pith:SFZIALG5","canonical_record":{"source":{"id":"1807.11398","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-30T15:40:54Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c7ac0dccd1fcc737c6564d1473f26eda7321bdbae78cb1ae5cea17b51277a209","abstract_canon_sha256":"cf3af9ad5efb7f2f1a99b424fafc31f09ae1bc8186d33f938b1a0ab325117dba"},"schema_version":"1.0"},"canonical_sha256":"9172802cddd0d231d5eeea368023553c43b76c513dc29aa2ed8ea9b18b627606","source":{"kind":"arxiv","id":"1807.11398","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.11398","created_at":"2026-07-05T02:56:52Z"},{"alias_kind":"arxiv_version","alias_value":"1807.11398v2","created_at":"2026-07-05T02:56:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.11398","created_at":"2026-07-05T02:56:52Z"},{"alias_kind":"pith_short_12","alias_value":"SFZIALG52DJD","created_at":"2026-07-05T02:56:52Z"},{"alias_kind":"pith_short_16","alias_value":"SFZIALG52DJDDVPO","created_at":"2026-07-05T02:56:52Z"},{"alias_kind":"pith_short_8","alias_value":"SFZIALG5","created_at":"2026-07-05T02:56:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:SFZIALG52DJDDVPO5I3IAI2VHR","target":"record","payload":{"canonical_record":{"source":{"id":"1807.11398","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-30T15:40:54Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c7ac0dccd1fcc737c6564d1473f26eda7321bdbae78cb1ae5cea17b51277a209","abstract_canon_sha256":"cf3af9ad5efb7f2f1a99b424fafc31f09ae1bc8186d33f938b1a0ab325117dba"},"schema_version":"1.0"},"canonical_sha256":"9172802cddd0d231d5eeea368023553c43b76c513dc29aa2ed8ea9b18b627606","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:56:52.091904Z","signature_b64":"9EXs0I+aOYsSksoFqcULCLdqwq/5P+H4sbBXGzwuqr9wD6ZePfFGcFSxRAQAcF1B4N+4QcMC5rGCVpxVZsbEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9172802cddd0d231d5eeea368023553c43b76c513dc29aa2ed8ea9b18b627606","last_reissued_at":"2026-07-05T02:56:52.091463Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:56:52.091463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.11398","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":"2026-07-05T02:56:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"THag/sPeofbq3+SjNPpVChc0fySWtoqfF/fKlL2iDv4JuNB2kMBnJ7XUq6S82TF/GjGZma8rAHdeUkWB8i5WCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T09:35:41.647053Z"},"content_sha256":"e2d02318fb96e1dd33a17e337aa8b455415bf03c33535c020a04f43a917879e5","schema_version":"1.0","event_id":"sha256:e2d02318fb96e1dd33a17e337aa8b455415bf03c33535c020a04f43a917879e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:SFZIALG52DJDDVPO5I3IAI2VHR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Preference-based Online Learning with Dueling Bandits: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adil El Mesaoudi-Paul, Eyke H\\\"ullermeier, Robert Busa-Fekete, Viktor Bengs","submitted_at":"2018-07-30T15:40:54Z","abstract_excerpt":"In machine learning, the notion of multi-armed bandits refers to a class of online learning problems, in which an agent is supposed to simultaneously explore and exploit a given set of choice alternatives in the course of a sequential decision process. In the standard setting, the agent learns from stochastic feedback in the form of real-valued rewards. In many applications, however, numerical reward signals are not readily available -- instead, only weaker information is provided, in particular relative preferences in the form of qualitative comparisons between pairs of alternatives. This obs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.11398","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/1807.11398/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":"2026-07-05T02:56:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P7dy1K4d9LGnb1edoiSoBjbPhov17mDwQphND+LZfIMbg9isuxcwJ+TQWueNxhbskojVki8hlwinsJzyD3g9AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T09:35:41.647492Z"},"content_sha256":"e3ab4c860c2d8ef58e38a9569501a3ca5a9317388cf4614a2a0986d246fb6703","schema_version":"1.0","event_id":"sha256:e3ab4c860c2d8ef58e38a9569501a3ca5a9317388cf4614a2a0986d246fb6703"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SFZIALG52DJDDVPO5I3IAI2VHR/bundle.json","state_url":"https://pith.science/pith/SFZIALG52DJDDVPO5I3IAI2VHR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SFZIALG52DJDDVPO5I3IAI2VHR/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":"2026-08-19T09:35:41Z","links":{"resolver":"https://pith.science/pith/SFZIALG52DJDDVPO5I3IAI2VHR","bundle":"https://pith.science/pith/SFZIALG52DJDDVPO5I3IAI2VHR/bundle.json","state":"https://pith.science/pith/SFZIALG52DJDDVPO5I3IAI2VHR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SFZIALG52DJDDVPO5I3IAI2VHR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:SFZIALG52DJDDVPO5I3IAI2VHR","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":"cf3af9ad5efb7f2f1a99b424fafc31f09ae1bc8186d33f938b1a0ab325117dba","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-30T15:40:54Z","title_canon_sha256":"c7ac0dccd1fcc737c6564d1473f26eda7321bdbae78cb1ae5cea17b51277a209"},"schema_version":"1.0","source":{"id":"1807.11398","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.11398","created_at":"2026-07-05T02:56:52Z"},{"alias_kind":"arxiv_version","alias_value":"1807.11398v2","created_at":"2026-07-05T02:56:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.11398","created_at":"2026-07-05T02:56:52Z"},{"alias_kind":"pith_short_12","alias_value":"SFZIALG52DJD","created_at":"2026-07-05T02:56:52Z"},{"alias_kind":"pith_short_16","alias_value":"SFZIALG52DJDDVPO","created_at":"2026-07-05T02:56:52Z"},{"alias_kind":"pith_short_8","alias_value":"SFZIALG5","created_at":"2026-07-05T02:56:52Z"}],"graph_snapshots":[{"event_id":"sha256:e3ab4c860c2d8ef58e38a9569501a3ca5a9317388cf4614a2a0986d246fb6703","target":"graph","created_at":"2026-07-05T02:56:52Z","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/1807.11398/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In machine learning, the notion of multi-armed bandits refers to a class of online learning problems, in which an agent is supposed to simultaneously explore and exploit a given set of choice alternatives in the course of a sequential decision process. In the standard setting, the agent learns from stochastic feedback in the form of real-valued rewards. In many applications, however, numerical reward signals are not readily available -- instead, only weaker information is provided, in particular relative preferences in the form of qualitative comparisons between pairs of alternatives. This obs","authors_text":"Adil El Mesaoudi-Paul, Eyke H\\\"ullermeier, Robert Busa-Fekete, Viktor Bengs","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-30T15:40:54Z","title":"Preference-based Online Learning with Dueling Bandits: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.11398","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:e2d02318fb96e1dd33a17e337aa8b455415bf03c33535c020a04f43a917879e5","target":"record","created_at":"2026-07-05T02:56:52Z","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":"cf3af9ad5efb7f2f1a99b424fafc31f09ae1bc8186d33f938b1a0ab325117dba","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-30T15:40:54Z","title_canon_sha256":"c7ac0dccd1fcc737c6564d1473f26eda7321bdbae78cb1ae5cea17b51277a209"},"schema_version":"1.0","source":{"id":"1807.11398","kind":"arxiv","version":2}},"canonical_sha256":"9172802cddd0d231d5eeea368023553c43b76c513dc29aa2ed8ea9b18b627606","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9172802cddd0d231d5eeea368023553c43b76c513dc29aa2ed8ea9b18b627606","first_computed_at":"2026-07-05T02:56:52.091463Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:56:52.091463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9EXs0I+aOYsSksoFqcULCLdqwq/5P+H4sbBXGzwuqr9wD6ZePfFGcFSxRAQAcF1B4N+4QcMC5rGCVpxVZsbEBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:56:52.091904Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.11398","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2d02318fb96e1dd33a17e337aa8b455415bf03c33535c020a04f43a917879e5","sha256:e3ab4c860c2d8ef58e38a9569501a3ca5a9317388cf4614a2a0986d246fb6703"],"state_sha256":"227693b0017ea199d84b4b0821dbdd0f15677e36676352bf52d23bc8b20f0c1a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AZwZvdhecw0q6DWipDD0BYiBFDr2JOo8JK5rKnixCIeY2Pi9tqJmCl/v/RQxT64HV6zUJ62lnq8O3sibiiHtAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T09:35:41.650436Z","bundle_sha256":"399ee0c165eea8747cab8d2726742ed296a71c223d165bb89c25b792dc99126d"}}