{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:PMPL7EUQBZJGNFVR643X647XXW","short_pith_number":"pith:PMPL7EUQ","schema_version":"1.0","canonical_sha256":"7b1ebf92900e526696b1f7377f73f7bdb78b6be671a807e44e4025ef43753c17","source":{"kind":"arxiv","id":"1705.08076","version":4},"attestation_state":"computed","paper":{"title":"Learning from partial correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Michael Luby, Sanjoy Dasgupta","submitted_at":"2017-05-23T05:07:52Z","abstract_excerpt":"We introduce a new model of interactive learning in which an expert examines the predictions of a learner and partially fixes them if they are wrong. Although this kind of feedback is not i.i.d., we show statistical generalization bounds on the quality of the learned model."},"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":"1705.08076","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-23T05:07:52Z","cross_cats_sorted":[],"title_canon_sha256":"539bad692370ce542721486ed628f29b0cfcda1e0c6e14b813c36019882c6816","abstract_canon_sha256":"9ece6d43b711eb789c1cd6698fa4709e5d934e78c3e2519a4318a50b2ed75514"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:57.099651Z","signature_b64":"UH74bOftQfmwqJNXLpN5XrSHHd4yT2DB84UsU4probPWGtI2bepctrRafrDtfFGO5N9ufyzaDEIXQ/2cWampAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b1ebf92900e526696b1f7377f73f7bdb78b6be671a807e44e4025ef43753c17","last_reissued_at":"2026-05-18T00:18:57.099166Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:57.099166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning from partial correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Michael Luby, Sanjoy Dasgupta","submitted_at":"2017-05-23T05:07:52Z","abstract_excerpt":"We introduce a new model of interactive learning in which an expert examines the predictions of a learner and partially fixes them if they are wrong. Although this kind of feedback is not i.i.d., we show statistical generalization bounds on the quality of the learned model."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08076","kind":"arxiv","version":4},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1705.08076","created_at":"2026-05-18T00:18:57.099252+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.08076v4","created_at":"2026-05-18T00:18:57.099252+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08076","created_at":"2026-05-18T00:18:57.099252+00:00"},{"alias_kind":"pith_short_12","alias_value":"PMPL7EUQBZJG","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"PMPL7EUQBZJGNFVR","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"PMPL7EUQ","created_at":"2026-05-18T12:31:37.085036+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/PMPL7EUQBZJGNFVR643X647XXW","json":"https://pith.science/pith/PMPL7EUQBZJGNFVR643X647XXW.json","graph_json":"https://pith.science/api/pith-number/PMPL7EUQBZJGNFVR643X647XXW/graph.json","events_json":"https://pith.science/api/pith-number/PMPL7EUQBZJGNFVR643X647XXW/events.json","paper":"https://pith.science/paper/PMPL7EUQ"},"agent_actions":{"view_html":"https://pith.science/pith/PMPL7EUQBZJGNFVR643X647XXW","download_json":"https://pith.science/pith/PMPL7EUQBZJGNFVR643X647XXW.json","view_paper":"https://pith.science/paper/PMPL7EUQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.08076&json=true","fetch_graph":"https://pith.science/api/pith-number/PMPL7EUQBZJGNFVR643X647XXW/graph.json","fetch_events":"https://pith.science/api/pith-number/PMPL7EUQBZJGNFVR643X647XXW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PMPL7EUQBZJGNFVR643X647XXW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PMPL7EUQBZJGNFVR643X647XXW/action/storage_attestation","attest_author":"https://pith.science/pith/PMPL7EUQBZJGNFVR643X647XXW/action/author_attestation","sign_citation":"https://pith.science/pith/PMPL7EUQBZJGNFVR643X647XXW/action/citation_signature","submit_replication":"https://pith.science/pith/PMPL7EUQBZJGNFVR643X647XXW/action/replication_record"}},"created_at":"2026-05-18T00:18:57.099252+00:00","updated_at":"2026-05-18T00:18:57.099252+00:00"}