{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:35KHF6ICZGU6FY7FM44APLTT7P","short_pith_number":"pith:35KHF6IC","schema_version":"1.0","canonical_sha256":"df5472f902c9a9e2e3e5673807ae73fbd04a9bdb76f75b4aa793c4befc1468eb","source":{"kind":"arxiv","id":"2203.04248","version":1},"attestation_state":"computed","paper":{"title":"Dual Lottery Ticket Hypothesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Huan Wang, Kunpeng Li, Yue Bai, Yun Fu, Zhiqiang Tao","submitted_at":"2022-03-08T18:06:26Z","abstract_excerpt":"Fully exploiting the learning capacity of neural networks requires overparameterized dense networks. On the other side, directly training sparse neural networks typically results in unsatisfactory performance. Lottery Ticket Hypothesis (LTH) provides a novel view to investigate sparse network training and maintain its capacity. Concretely, it claims there exist winning tickets from a randomly initialized network found by iterative magnitude pruning and preserving promising trainability (or we say being in trainable condition). In this work, we regard the winning ticket from LTH as the subnetwo"},"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":"2203.04248","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-08T18:06:26Z","cross_cats_sorted":[],"title_canon_sha256":"000e74423dcab8042c98988281d3929002559099fc4decd6c7ccf07ae7b09240","abstract_canon_sha256":"6cbb1ffbd7882668c26e9adfae6cecf06dbf3bf91806bda70c771a8884261549"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:03:07.466371Z","signature_b64":"c1nIAsI6wHxfvzuSM90ff1ocSwaKhtP8/b3730STWuAywPo+LGxMPyltZc0QvalFUmb5JQclholNbKyqL8JFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df5472f902c9a9e2e3e5673807ae73fbd04a9bdb76f75b4aa793c4befc1468eb","last_reissued_at":"2026-07-05T04:03:07.465933Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:03:07.465933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual Lottery Ticket Hypothesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Huan Wang, Kunpeng Li, Yue Bai, Yun Fu, Zhiqiang Tao","submitted_at":"2022-03-08T18:06:26Z","abstract_excerpt":"Fully exploiting the learning capacity of neural networks requires overparameterized dense networks. On the other side, directly training sparse neural networks typically results in unsatisfactory performance. Lottery Ticket Hypothesis (LTH) provides a novel view to investigate sparse network training and maintain its capacity. Concretely, it claims there exist winning tickets from a randomly initialized network found by iterative magnitude pruning and preserving promising trainability (or we say being in trainable condition). In this work, we regard the winning ticket from LTH as the subnetwo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.04248","kind":"arxiv","version":1},"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/2203.04248/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":"2203.04248","created_at":"2026-07-05T04:03:07.465994+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.04248v1","created_at":"2026-07-05T04:03:07.465994+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.04248","created_at":"2026-07-05T04:03:07.465994+00:00"},{"alias_kind":"pith_short_12","alias_value":"35KHF6ICZGU6","created_at":"2026-07-05T04:03:07.465994+00:00"},{"alias_kind":"pith_short_16","alias_value":"35KHF6ICZGU6FY7F","created_at":"2026-07-05T04:03:07.465994+00:00"},{"alias_kind":"pith_short_8","alias_value":"35KHF6IC","created_at":"2026-07-05T04:03:07.465994+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.17909","citing_title":"NeuroTrails: Training with Dynamic Sparse Heads as the Key to Effective Ensembling","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/35KHF6ICZGU6FY7FM44APLTT7P","json":"https://pith.science/pith/35KHF6ICZGU6FY7FM44APLTT7P.json","graph_json":"https://pith.science/api/pith-number/35KHF6ICZGU6FY7FM44APLTT7P/graph.json","events_json":"https://pith.science/api/pith-number/35KHF6ICZGU6FY7FM44APLTT7P/events.json","paper":"https://pith.science/paper/35KHF6IC"},"agent_actions":{"view_html":"https://pith.science/pith/35KHF6ICZGU6FY7FM44APLTT7P","download_json":"https://pith.science/pith/35KHF6ICZGU6FY7FM44APLTT7P.json","view_paper":"https://pith.science/paper/35KHF6IC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.04248&json=true","fetch_graph":"https://pith.science/api/pith-number/35KHF6ICZGU6FY7FM44APLTT7P/graph.json","fetch_events":"https://pith.science/api/pith-number/35KHF6ICZGU6FY7FM44APLTT7P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/35KHF6ICZGU6FY7FM44APLTT7P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/35KHF6ICZGU6FY7FM44APLTT7P/action/storage_attestation","attest_author":"https://pith.science/pith/35KHF6ICZGU6FY7FM44APLTT7P/action/author_attestation","sign_citation":"https://pith.science/pith/35KHF6ICZGU6FY7FM44APLTT7P/action/citation_signature","submit_replication":"https://pith.science/pith/35KHF6ICZGU6FY7FM44APLTT7P/action/replication_record"}},"created_at":"2026-07-05T04:03:07.465994+00:00","updated_at":"2026-07-05T04:03:07.465994+00:00"}