{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JRI5U2YBZPV4Q43DTJ3GSVLUWS","short_pith_number":"pith:JRI5U2YB","schema_version":"1.0","canonical_sha256":"4c51da6b01cbebc873639a76695574b4821d7c1a054c3547fecc57b2b5cf4d9d","source":{"kind":"arxiv","id":"1905.07785","version":2},"attestation_state":"computed","paper":{"title":"Sparse Transfer Learning via Winning Lottery Tickets","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Rahul Mehta","submitted_at":"2019-05-19T17:48:29Z","abstract_excerpt":"The recently proposed Lottery Ticket Hypothesis of Frankle and Carbin (2019) suggests that the performance of over-parameterized deep networks is due to the random initialization seeding the network with a small fraction of favorable weights. These weights retain their dominant status throughout training -- in a very real sense, this sub-network \"won the lottery\" during initialization. The authors find sub-networks via unstructured magnitude pruning with 85-95% of parameters removed that train to the same accuracy as the original network at a similar speed, which they call winning tickets. In "},"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":"1905.07785","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-05-19T17:48:29Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"797e30075b1e9b2aec71b0b370263732085d4c913d82c83ac8fb608377823d37","abstract_canon_sha256":"b226c4f9fcc0004425e4977c966cd4539429948e5441f34379d16683d5ca4074"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:26:23.677209Z","signature_b64":"TDgAhsPGvS4jpwohjKg0+PzBAYsWiqCEHmfacyp1hUftKO/8l6x9gCC9MYf6AQuhaZeXNQ4+b2N4eLgocbSgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c51da6b01cbebc873639a76695574b4821d7c1a054c3547fecc57b2b5cf4d9d","last_reissued_at":"2026-07-05T00:26:23.676641Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:26:23.676641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparse Transfer Learning via Winning Lottery Tickets","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Rahul Mehta","submitted_at":"2019-05-19T17:48:29Z","abstract_excerpt":"The recently proposed Lottery Ticket Hypothesis of Frankle and Carbin (2019) suggests that the performance of over-parameterized deep networks is due to the random initialization seeding the network with a small fraction of favorable weights. These weights retain their dominant status throughout training -- in a very real sense, this sub-network \"won the lottery\" during initialization. The authors find sub-networks via unstructured magnitude pruning with 85-95% of parameters removed that train to the same accuracy as the original network at a similar speed, which they call winning tickets. In "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07785","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1905.07785/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":"1905.07785","created_at":"2026-07-05T00:26:23.676704+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.07785v2","created_at":"2026-07-05T00:26:23.676704+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07785","created_at":"2026-07-05T00:26:23.676704+00:00"},{"alias_kind":"pith_short_12","alias_value":"JRI5U2YBZPV4","created_at":"2026-07-05T00:26:23.676704+00:00"},{"alias_kind":"pith_short_16","alias_value":"JRI5U2YBZPV4Q43D","created_at":"2026-07-05T00:26:23.676704+00:00"},{"alias_kind":"pith_short_8","alias_value":"JRI5U2YB","created_at":"2026-07-05T00:26:23.676704+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.27052","citing_title":"Man, Machine, and Mathematics","ref_index":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JRI5U2YBZPV4Q43DTJ3GSVLUWS","json":"https://pith.science/pith/JRI5U2YBZPV4Q43DTJ3GSVLUWS.json","graph_json":"https://pith.science/api/pith-number/JRI5U2YBZPV4Q43DTJ3GSVLUWS/graph.json","events_json":"https://pith.science/api/pith-number/JRI5U2YBZPV4Q43DTJ3GSVLUWS/events.json","paper":"https://pith.science/paper/JRI5U2YB"},"agent_actions":{"view_html":"https://pith.science/pith/JRI5U2YBZPV4Q43DTJ3GSVLUWS","download_json":"https://pith.science/pith/JRI5U2YBZPV4Q43DTJ3GSVLUWS.json","view_paper":"https://pith.science/paper/JRI5U2YB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.07785&json=true","fetch_graph":"https://pith.science/api/pith-number/JRI5U2YBZPV4Q43DTJ3GSVLUWS/graph.json","fetch_events":"https://pith.science/api/pith-number/JRI5U2YBZPV4Q43DTJ3GSVLUWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JRI5U2YBZPV4Q43DTJ3GSVLUWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JRI5U2YBZPV4Q43DTJ3GSVLUWS/action/storage_attestation","attest_author":"https://pith.science/pith/JRI5U2YBZPV4Q43DTJ3GSVLUWS/action/author_attestation","sign_citation":"https://pith.science/pith/JRI5U2YBZPV4Q43DTJ3GSVLUWS/action/citation_signature","submit_replication":"https://pith.science/pith/JRI5U2YBZPV4Q43DTJ3GSVLUWS/action/replication_record"}},"created_at":"2026-07-05T00:26:23.676704+00:00","updated_at":"2026-07-05T00:26:23.676704+00:00"}