{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:BIWDMW7YMJBYBM6G7TXFZ6CVOX","short_pith_number":"pith:BIWDMW7Y","schema_version":"1.0","canonical_sha256":"0a2c365bf8624380b3c6fcee5cf85575cf1e46ef2038bd00803602dd65879592","source":{"kind":"arxiv","id":"1809.02869","version":3},"attestation_state":"computed","paper":{"title":"Machine Teaching of Active Sequential Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mustafa Mert \\c{C}elikok, Pedram Daee, Samuel Kaski, Tomi Peltola","submitted_at":"2018-09-08T20:39:31Z","abstract_excerpt":"Machine teaching addresses the problem of finding the best training data that can guide a learning algorithm to a target model with minimal effort. In conventional settings, a teacher provides data that are consistent with the true data distribution. However, for sequential learners which actively choose their queries, such as multi-armed bandits and active learners, the teacher can only provide responses to the learner's queries, not design the full data. In this setting, consistent teachers can be sub-optimal for finite horizons. We formulate this sequential teaching problem, which current t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1809.02869","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-08T20:39:31Z","cross_cats_sorted":["cs.AI","cs.HC","stat.ML"],"title_canon_sha256":"5558feabf4e42a3ed0bd8876ed8969b663a718e17efc35054aea7fc2bf5342b6","abstract_canon_sha256":"e55f0118e415927448bad7d42e9c19e6c2b5340da036a584e89a0d654b0eb619"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:16:18.649502Z","signature_b64":"R1pVNj8BUc6XYyjAwMANBoVBTNcQpAcxhJb40R8jGEnxSgTYE2R2iug9Io4s8DxjIC9ri3NP4C67NzoepjWGAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a2c365bf8624380b3c6fcee5cf85575cf1e46ef2038bd00803602dd65879592","last_reissued_at":"2026-07-05T00:16:18.649053Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:16:18.649053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Machine Teaching of Active Sequential Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mustafa Mert \\c{C}elikok, Pedram Daee, Samuel Kaski, Tomi Peltola","submitted_at":"2018-09-08T20:39:31Z","abstract_excerpt":"Machine teaching addresses the problem of finding the best training data that can guide a learning algorithm to a target model with minimal effort. In conventional settings, a teacher provides data that are consistent with the true data distribution. However, for sequential learners which actively choose their queries, such as multi-armed bandits and active learners, the teacher can only provide responses to the learner's queries, not design the full data. In this setting, consistent teachers can be sub-optimal for finite horizons. We formulate this sequential teaching problem, which current t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.02869","kind":"arxiv","version":3},"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/1809.02869/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1809.02869","created_at":"2026-07-05T00:16:18.649111+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.02869v3","created_at":"2026-07-05T00:16:18.649111+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.02869","created_at":"2026-07-05T00:16:18.649111+00:00"},{"alias_kind":"pith_short_12","alias_value":"BIWDMW7YMJBY","created_at":"2026-07-05T00:16:18.649111+00:00"},{"alias_kind":"pith_short_16","alias_value":"BIWDMW7YMJBYBM6G","created_at":"2026-07-05T00:16:18.649111+00:00"},{"alias_kind":"pith_short_8","alias_value":"BIWDMW7Y","created_at":"2026-07-05T00:16:18.649111+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BIWDMW7YMJBYBM6G7TXFZ6CVOX","json":"https://pith.science/pith/BIWDMW7YMJBYBM6G7TXFZ6CVOX.json","graph_json":"https://pith.science/api/pith-number/BIWDMW7YMJBYBM6G7TXFZ6CVOX/graph.json","events_json":"https://pith.science/api/pith-number/BIWDMW7YMJBYBM6G7TXFZ6CVOX/events.json","paper":"https://pith.science/paper/BIWDMW7Y"},"agent_actions":{"view_html":"https://pith.science/pith/BIWDMW7YMJBYBM6G7TXFZ6CVOX","download_json":"https://pith.science/pith/BIWDMW7YMJBYBM6G7TXFZ6CVOX.json","view_paper":"https://pith.science/paper/BIWDMW7Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.02869&json=true","fetch_graph":"https://pith.science/api/pith-number/BIWDMW7YMJBYBM6G7TXFZ6CVOX/graph.json","fetch_events":"https://pith.science/api/pith-number/BIWDMW7YMJBYBM6G7TXFZ6CVOX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BIWDMW7YMJBYBM6G7TXFZ6CVOX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BIWDMW7YMJBYBM6G7TXFZ6CVOX/action/storage_attestation","attest_author":"https://pith.science/pith/BIWDMW7YMJBYBM6G7TXFZ6CVOX/action/author_attestation","sign_citation":"https://pith.science/pith/BIWDMW7YMJBYBM6G7TXFZ6CVOX/action/citation_signature","submit_replication":"https://pith.science/pith/BIWDMW7YMJBYBM6G7TXFZ6CVOX/action/replication_record"}},"created_at":"2026-07-05T00:16:18.649111+00:00","updated_at":"2026-07-05T00:16:18.649111+00:00"}