{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:B3N32V6Z5AYCPMJGINLBMWGSEU","short_pith_number":"pith:B3N32V6Z","canonical_record":{"source":{"id":"1307.8187","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-07-31T01:49:50Z","cross_cats_sorted":[],"title_canon_sha256":"919e847df43b340c504aa85924bece0ee512588415ef67368d76f1097a8e8c99","abstract_canon_sha256":"5d197eec60b39a751b6fff0573f536b483f29697691733feac2d795e8b6274c8"},"schema_version":"1.0"},"canonical_sha256":"0edbbd57d9e83027b12643561658d225257fea43ffe650e4db06f23d17911370","source":{"kind":"arxiv","id":"1307.8187","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1307.8187","created_at":"2026-05-18T03:11:12Z"},{"alias_kind":"arxiv_version","alias_value":"1307.8187v2","created_at":"2026-05-18T03:11:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1307.8187","created_at":"2026-05-18T03:11:12Z"},{"alias_kind":"pith_short_12","alias_value":"B3N32V6Z5AYC","created_at":"2026-05-18T12:27:38Z"},{"alias_kind":"pith_short_16","alias_value":"B3N32V6Z5AYCPMJG","created_at":"2026-05-18T12:27:38Z"},{"alias_kind":"pith_short_8","alias_value":"B3N32V6Z","created_at":"2026-05-18T12:27:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:B3N32V6Z5AYCPMJGINLBMWGSEU","target":"record","payload":{"canonical_record":{"source":{"id":"1307.8187","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-07-31T01:49:50Z","cross_cats_sorted":[],"title_canon_sha256":"919e847df43b340c504aa85924bece0ee512588415ef67368d76f1097a8e8c99","abstract_canon_sha256":"5d197eec60b39a751b6fff0573f536b483f29697691733feac2d795e8b6274c8"},"schema_version":"1.0"},"canonical_sha256":"0edbbd57d9e83027b12643561658d225257fea43ffe650e4db06f23d17911370","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:11:12.682711Z","signature_b64":"8soF9icUTRHxt9lMBEADzlVeYJaHdjBLpF4n9Nkeu/tkdNlHDzu3tH/LqKb9ChaTT7iFRwDFqQxskQls7ijjCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0edbbd57d9e83027b12643561658d225257fea43ffe650e4db06f23d17911370","last_reissued_at":"2026-05-18T03:11:12.682176Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:11:12.682176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1307.8187","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":"2026-05-18T03:11:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bI9ftnFDNgd3OWSeNHmMFjnXN+FpQ6C47+ibOxnuHiZD5OAv2B+jqXFwqOa0CGbKZjUW46yfHiGz+QlA6GC+AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T14:54:53.783907Z"},"content_sha256":"d7e38fa1e7516ecddf2b08d0a266145952cd58f84354bc1b72ea027be33cf701","schema_version":"1.0","event_id":"sha256:d7e38fa1e7516ecddf2b08d0a266145952cd58f84354bc1b72ea027be33cf701"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:B3N32V6Z5AYCPMJGINLBMWGSEU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Minimax Online Learning with Unknown Time Horizon","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haipeng Luo, Robert E. Schapire","submitted_at":"2013-07-31T01:49:50Z","abstract_excerpt":"We consider online learning when the time horizon is unknown. We apply a minimax analysis, beginning with the fixed horizon case, and then moving on to two unknown-horizon settings, one that assumes the horizon is chosen randomly according to some known distribution, and the other which allows the adversary full control over the horizon. For the random horizon setting with restricted losses, we derive a fully optimal minimax algorithm. And for the adversarial horizon setting, we prove a nontrivial lower bound which shows that the adversary obtains strictly more power than when the horizon is f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1307.8187","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":""},"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":"2026-05-18T03:11:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4T8ipkKwRiq2nxJZXLiXD8HA0EFlqOmdNggnEg8hn3LZTKrFTTHuRepUSixfDnU5j5UlZnFMf9TJy57+Pb6kCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T14:54:53.784600Z"},"content_sha256":"e12712f46a05bd3376800a7bbd2732650e992990bd013eb5e33ca102be29c3da","schema_version":"1.0","event_id":"sha256:e12712f46a05bd3376800a7bbd2732650e992990bd013eb5e33ca102be29c3da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B3N32V6Z5AYCPMJGINLBMWGSEU/bundle.json","state_url":"https://pith.science/pith/B3N32V6Z5AYCPMJGINLBMWGSEU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B3N32V6Z5AYCPMJGINLBMWGSEU/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":"2026-06-10T14:54:53Z","links":{"resolver":"https://pith.science/pith/B3N32V6Z5AYCPMJGINLBMWGSEU","bundle":"https://pith.science/pith/B3N32V6Z5AYCPMJGINLBMWGSEU/bundle.json","state":"https://pith.science/pith/B3N32V6Z5AYCPMJGINLBMWGSEU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B3N32V6Z5AYCPMJGINLBMWGSEU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:B3N32V6Z5AYCPMJGINLBMWGSEU","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":"5d197eec60b39a751b6fff0573f536b483f29697691733feac2d795e8b6274c8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-07-31T01:49:50Z","title_canon_sha256":"919e847df43b340c504aa85924bece0ee512588415ef67368d76f1097a8e8c99"},"schema_version":"1.0","source":{"id":"1307.8187","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1307.8187","created_at":"2026-05-18T03:11:12Z"},{"alias_kind":"arxiv_version","alias_value":"1307.8187v2","created_at":"2026-05-18T03:11:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1307.8187","created_at":"2026-05-18T03:11:12Z"},{"alias_kind":"pith_short_12","alias_value":"B3N32V6Z5AYC","created_at":"2026-05-18T12:27:38Z"},{"alias_kind":"pith_short_16","alias_value":"B3N32V6Z5AYCPMJG","created_at":"2026-05-18T12:27:38Z"},{"alias_kind":"pith_short_8","alias_value":"B3N32V6Z","created_at":"2026-05-18T12:27:38Z"}],"graph_snapshots":[{"event_id":"sha256:e12712f46a05bd3376800a7bbd2732650e992990bd013eb5e33ca102be29c3da","target":"graph","created_at":"2026-05-18T03:11:12Z","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 consider online learning when the time horizon is unknown. We apply a minimax analysis, beginning with the fixed horizon case, and then moving on to two unknown-horizon settings, one that assumes the horizon is chosen randomly according to some known distribution, and the other which allows the adversary full control over the horizon. For the random horizon setting with restricted losses, we derive a fully optimal minimax algorithm. And for the adversarial horizon setting, we prove a nontrivial lower bound which shows that the adversary obtains strictly more power than when the horizon is f","authors_text":"Haipeng Luo, Robert E. Schapire","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-07-31T01:49:50Z","title":"Towards Minimax Online Learning with Unknown Time Horizon"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1307.8187","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:d7e38fa1e7516ecddf2b08d0a266145952cd58f84354bc1b72ea027be33cf701","target":"record","created_at":"2026-05-18T03:11:12Z","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":"5d197eec60b39a751b6fff0573f536b483f29697691733feac2d795e8b6274c8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-07-31T01:49:50Z","title_canon_sha256":"919e847df43b340c504aa85924bece0ee512588415ef67368d76f1097a8e8c99"},"schema_version":"1.0","source":{"id":"1307.8187","kind":"arxiv","version":2}},"canonical_sha256":"0edbbd57d9e83027b12643561658d225257fea43ffe650e4db06f23d17911370","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0edbbd57d9e83027b12643561658d225257fea43ffe650e4db06f23d17911370","first_computed_at":"2026-05-18T03:11:12.682176Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:11:12.682176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8soF9icUTRHxt9lMBEADzlVeYJaHdjBLpF4n9Nkeu/tkdNlHDzu3tH/LqKb9ChaTT7iFRwDFqQxskQls7ijjCA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:11:12.682711Z","signed_message":"canonical_sha256_bytes"},"source_id":"1307.8187","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7e38fa1e7516ecddf2b08d0a266145952cd58f84354bc1b72ea027be33cf701","sha256:e12712f46a05bd3376800a7bbd2732650e992990bd013eb5e33ca102be29c3da"],"state_sha256":"09287b2480a91b1d4fbac1b959f95a49836c29ab80b468ed6fdf0ef50b365432"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6rbgDJCy7fhrLLKoRoijkN3I+jea0rxJ1BEBvKpYZrQiK8Q41RI56dQspY+4UM1SngNoZgliKuVLA7qW1HATDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T14:54:53.788584Z","bundle_sha256":"c32cff30c3bd49763c2a5336ddcd8c9cc07469443f7dd376a7f1d8d0182f4176"}}