{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KOC63DKESCJ2FWWKXUJPLV4EMJ","short_pith_number":"pith:KOC63DKE","schema_version":"1.0","canonical_sha256":"5385ed8d449093a2dacabd12f5d78462795ec02c3169a4689276b0f850595438","source":{"kind":"arxiv","id":"1802.03796","version":4},"attestation_state":"computed","paper":{"title":"Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dan Amir, Daphna Weinshall, Gad Cohen","submitted_at":"2018-02-11T19:24:47Z","abstract_excerpt":"We provide theoretical investigation of curriculum learning in the context of stochastic gradient descent when optimizing the convex linear regression loss. We prove that the rate of convergence of an ideal curriculum learning method is monotonically increasing with the difficulty of the examples. Moreover, among all equally difficult points, convergence is faster when using points which incur higher loss with respect to the current hypothesis. We then analyze curriculum learning in the context of training a CNN. We describe a method which infers the curriculum by way of transfer learning from"},"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":"1802.03796","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-11T19:24:47Z","cross_cats_sorted":[],"title_canon_sha256":"f183ab8550b28553581ec3267881b568c3081dcacf1f3c67e5d55181319b8d78","abstract_canon_sha256":"1094a3db2e4a2a842ca09b03abdca73f6be343ee223464da2451fe242bdf054f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:24.302474Z","signature_b64":"3ppfFLNk/s+avjiaSl108Gw3yy505/e6tYQMAOG6ST6r4ZOBuCRL11yUMprs6Oigdt0OtdDUZzB3RIwrXKPZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5385ed8d449093a2dacabd12f5d78462795ec02c3169a4689276b0f850595438","last_reissued_at":"2026-07-05T07:28:24.301993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:24.301993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dan Amir, Daphna Weinshall, Gad Cohen","submitted_at":"2018-02-11T19:24:47Z","abstract_excerpt":"We provide theoretical investigation of curriculum learning in the context of stochastic gradient descent when optimizing the convex linear regression loss. We prove that the rate of convergence of an ideal curriculum learning method is monotonically increasing with the difficulty of the examples. Moreover, among all equally difficult points, convergence is faster when using points which incur higher loss with respect to the current hypothesis. We then analyze curriculum learning in the context of training a CNN. We describe a method which infers the curriculum by way of transfer learning from"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03796","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1802.03796/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":"1802.03796","created_at":"2026-07-05T07:28:24.302059+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.03796v4","created_at":"2026-07-05T07:28:24.302059+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03796","created_at":"2026-07-05T07:28:24.302059+00:00"},{"alias_kind":"pith_short_12","alias_value":"KOC63DKESCJ2","created_at":"2026-07-05T07:28:24.302059+00:00"},{"alias_kind":"pith_short_16","alias_value":"KOC63DKESCJ2FWWK","created_at":"2026-07-05T07:28:24.302059+00:00"},{"alias_kind":"pith_short_8","alias_value":"KOC63DKE","created_at":"2026-07-05T07:28:24.302059+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31636","citing_title":"LiteMatch: Lightweight Zero-Shot Stereo Matching via Cost Volume Stabilization","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2502.12272","citing_title":"Learning to Reason at the Frontier of Learnability","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KOC63DKESCJ2FWWKXUJPLV4EMJ","json":"https://pith.science/pith/KOC63DKESCJ2FWWKXUJPLV4EMJ.json","graph_json":"https://pith.science/api/pith-number/KOC63DKESCJ2FWWKXUJPLV4EMJ/graph.json","events_json":"https://pith.science/api/pith-number/KOC63DKESCJ2FWWKXUJPLV4EMJ/events.json","paper":"https://pith.science/paper/KOC63DKE"},"agent_actions":{"view_html":"https://pith.science/pith/KOC63DKESCJ2FWWKXUJPLV4EMJ","download_json":"https://pith.science/pith/KOC63DKESCJ2FWWKXUJPLV4EMJ.json","view_paper":"https://pith.science/paper/KOC63DKE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.03796&json=true","fetch_graph":"https://pith.science/api/pith-number/KOC63DKESCJ2FWWKXUJPLV4EMJ/graph.json","fetch_events":"https://pith.science/api/pith-number/KOC63DKESCJ2FWWKXUJPLV4EMJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KOC63DKESCJ2FWWKXUJPLV4EMJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KOC63DKESCJ2FWWKXUJPLV4EMJ/action/storage_attestation","attest_author":"https://pith.science/pith/KOC63DKESCJ2FWWKXUJPLV4EMJ/action/author_attestation","sign_citation":"https://pith.science/pith/KOC63DKESCJ2FWWKXUJPLV4EMJ/action/citation_signature","submit_replication":"https://pith.science/pith/KOC63DKESCJ2FWWKXUJPLV4EMJ/action/replication_record"}},"created_at":"2026-07-05T07:28:24.302059+00:00","updated_at":"2026-07-05T07:28:24.302059+00:00"}