{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:NWHGUQAUTQI5IZORZJ4AA3X37W","short_pith_number":"pith:NWHGUQAU","schema_version":"1.0","canonical_sha256":"6d8e6a40149c11d465d1ca78006efbfd906636766b497b3a0425503ad987b659","source":{"kind":"arxiv","id":"1707.00183","version":2},"attestation_state":"computed","paper":{"title":"Teacher-Student Curriculum Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Avital Oliver, John Schulman, Taco Cohen, Tambet Matiisen","submitted_at":"2017-07-01T18:13:17Z","abstract_excerpt":"We propose Teacher-Student Curriculum Learning (TSCL), a framework for automatic curriculum learning, where the Student tries to learn a complex task and the Teacher automatically chooses subtasks from a given set for the Student to train on. We describe a family of Teacher algorithms that rely on the intuition that the Student should practice more those tasks on which it makes the fastest progress, i.e. where the slope of the learning curve is highest. In addition, the Teacher algorithms address the problem of forgetting by also choosing tasks where the Student's performance is getting worse."},"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":"1707.00183","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-01T18:13:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bb0bb2df2dc773e9902d9a738b92e9b35558cdeb37056952dcd594883b765135","abstract_canon_sha256":"921a2c2b7a4e3c43d0a21ca7c919185f827354b13ee1b034163ad89a80dacf9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:13.202089Z","signature_b64":"SU6iiMrkjBB4ayX3T+QP1iUqdlN6y7Y+WPHefkcSwRE+bIZ6d94bASLpcVHmG1hmzn/v52sBPmAR4p8QPGjhCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d8e6a40149c11d465d1ca78006efbfd906636766b497b3a0425503ad987b659","last_reissued_at":"2026-05-18T00:29:13.201728Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:13.201728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Teacher-Student Curriculum Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Avital Oliver, John Schulman, Taco Cohen, Tambet Matiisen","submitted_at":"2017-07-01T18:13:17Z","abstract_excerpt":"We propose Teacher-Student Curriculum Learning (TSCL), a framework for automatic curriculum learning, where the Student tries to learn a complex task and the Teacher automatically chooses subtasks from a given set for the Student to train on. We describe a family of Teacher algorithms that rely on the intuition that the Student should practice more those tasks on which it makes the fastest progress, i.e. where the slope of the learning curve is highest. In addition, the Teacher algorithms address the problem of forgetting by also choosing tasks where the Student's performance is getting worse."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.00183","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1707.00183","created_at":"2026-05-18T00:29:13.201787+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.00183v2","created_at":"2026-05-18T00:29:13.201787+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.00183","created_at":"2026-05-18T00:29:13.201787+00:00"},{"alias_kind":"pith_short_12","alias_value":"NWHGUQAUTQI5","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"NWHGUQAUTQI5IZOR","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"NWHGUQAU","created_at":"2026-05-18T12:31:34.259226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1907.00274","citing_title":"NetTailor: Tuning the Architecture, Not Just the Weights","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2502.12272","citing_title":"Learning to Reason at the Frontier of Learnability","ref_index":60,"is_internal_anchor":true},{"citing_arxiv_id":"1910.07113","citing_title":"Solving Rubik's Cube with a Robot Hand","ref_index":67,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NWHGUQAUTQI5IZORZJ4AA3X37W","json":"https://pith.science/pith/NWHGUQAUTQI5IZORZJ4AA3X37W.json","graph_json":"https://pith.science/api/pith-number/NWHGUQAUTQI5IZORZJ4AA3X37W/graph.json","events_json":"https://pith.science/api/pith-number/NWHGUQAUTQI5IZORZJ4AA3X37W/events.json","paper":"https://pith.science/paper/NWHGUQAU"},"agent_actions":{"view_html":"https://pith.science/pith/NWHGUQAUTQI5IZORZJ4AA3X37W","download_json":"https://pith.science/pith/NWHGUQAUTQI5IZORZJ4AA3X37W.json","view_paper":"https://pith.science/paper/NWHGUQAU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.00183&json=true","fetch_graph":"https://pith.science/api/pith-number/NWHGUQAUTQI5IZORZJ4AA3X37W/graph.json","fetch_events":"https://pith.science/api/pith-number/NWHGUQAUTQI5IZORZJ4AA3X37W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NWHGUQAUTQI5IZORZJ4AA3X37W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NWHGUQAUTQI5IZORZJ4AA3X37W/action/storage_attestation","attest_author":"https://pith.science/pith/NWHGUQAUTQI5IZORZJ4AA3X37W/action/author_attestation","sign_citation":"https://pith.science/pith/NWHGUQAUTQI5IZORZJ4AA3X37W/action/citation_signature","submit_replication":"https://pith.science/pith/NWHGUQAUTQI5IZORZJ4AA3X37W/action/replication_record"}},"created_at":"2026-05-18T00:29:13.201787+00:00","updated_at":"2026-05-18T00:29:13.201787+00:00"}