{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5CNVK3A55OIQTMMZ3OUNSMMCQ7","short_pith_number":"pith:5CNVK3A5","schema_version":"1.0","canonical_sha256":"e89b556c1deb9109b199dba8d9318287ebac67b4502262805177ddd896ea094f","source":{"kind":"arxiv","id":"2211.01484","version":3},"attestation_state":"computed","paper":{"title":"Data Level Lottery Ticket Hypothesis for Vision Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Geng Yuan, Hao Tang, Minghai Qin, Peiyan Dong, Xiaolong Ma, Xin Meng, Xuan Shen, Yanzhi Wang, Zhenglun Kong","submitted_at":"2022-11-02T21:12:37Z","abstract_excerpt":"The conventional lottery ticket hypothesis (LTH) claims that there exists a sparse subnetwork within a dense neural network and a proper random initialization method called the winning ticket, such that it can be trained from scratch to almost as good as the dense counterpart. Meanwhile, the research of LTH in vision transformers (ViTs) is scarcely evaluated. In this paper, we first show that the conventional winning ticket is hard to find at the weight level of ViTs by existing methods. Then, we generalize the LTH for ViTs to input data consisting of image patches inspired by the input depend"},"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":"2211.01484","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-02T21:12:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"261d47e6d705a04e43f158c5055f8c477f73ab71423c0933188a2c03676781f7","abstract_canon_sha256":"c212fe357dd5eab3827dab0ef7a027f4c62b26f26d56fa2bd5413ec04c5e09b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:56.677921Z","signature_b64":"TnN0AFkhv+9PMgfLCDhD5qOEjXkidwq/PButKTY38QHEKKVPys2gligP3GztjSdLgr6tXLcOt2VXTQFybXlVCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e89b556c1deb9109b199dba8d9318287ebac67b4502262805177ddd896ea094f","last_reissued_at":"2026-07-05T06:14:56.677393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:56.677393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Level Lottery Ticket Hypothesis for Vision Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Geng Yuan, Hao Tang, Minghai Qin, Peiyan Dong, Xiaolong Ma, Xin Meng, Xuan Shen, Yanzhi Wang, Zhenglun Kong","submitted_at":"2022-11-02T21:12:37Z","abstract_excerpt":"The conventional lottery ticket hypothesis (LTH) claims that there exists a sparse subnetwork within a dense neural network and a proper random initialization method called the winning ticket, such that it can be trained from scratch to almost as good as the dense counterpart. Meanwhile, the research of LTH in vision transformers (ViTs) is scarcely evaluated. In this paper, we first show that the conventional winning ticket is hard to find at the weight level of ViTs by existing methods. Then, we generalize the LTH for ViTs to input data consisting of image patches inspired by the input depend"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.01484","kind":"arxiv","version":3},"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/2211.01484/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":"2211.01484","created_at":"2026-07-05T06:14:56.677450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.01484v3","created_at":"2026-07-05T06:14:56.677450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.01484","created_at":"2026-07-05T06:14:56.677450+00:00"},{"alias_kind":"pith_short_12","alias_value":"5CNVK3A55OIQ","created_at":"2026-07-05T06:14:56.677450+00:00"},{"alias_kind":"pith_short_16","alias_value":"5CNVK3A55OIQTMMZ","created_at":"2026-07-05T06:14:56.677450+00:00"},{"alias_kind":"pith_short_8","alias_value":"5CNVK3A5","created_at":"2026-07-05T06:14:56.677450+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/5CNVK3A55OIQTMMZ3OUNSMMCQ7","json":"https://pith.science/pith/5CNVK3A55OIQTMMZ3OUNSMMCQ7.json","graph_json":"https://pith.science/api/pith-number/5CNVK3A55OIQTMMZ3OUNSMMCQ7/graph.json","events_json":"https://pith.science/api/pith-number/5CNVK3A55OIQTMMZ3OUNSMMCQ7/events.json","paper":"https://pith.science/paper/5CNVK3A5"},"agent_actions":{"view_html":"https://pith.science/pith/5CNVK3A55OIQTMMZ3OUNSMMCQ7","download_json":"https://pith.science/pith/5CNVK3A55OIQTMMZ3OUNSMMCQ7.json","view_paper":"https://pith.science/paper/5CNVK3A5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.01484&json=true","fetch_graph":"https://pith.science/api/pith-number/5CNVK3A55OIQTMMZ3OUNSMMCQ7/graph.json","fetch_events":"https://pith.science/api/pith-number/5CNVK3A55OIQTMMZ3OUNSMMCQ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5CNVK3A55OIQTMMZ3OUNSMMCQ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5CNVK3A55OIQTMMZ3OUNSMMCQ7/action/storage_attestation","attest_author":"https://pith.science/pith/5CNVK3A55OIQTMMZ3OUNSMMCQ7/action/author_attestation","sign_citation":"https://pith.science/pith/5CNVK3A55OIQTMMZ3OUNSMMCQ7/action/citation_signature","submit_replication":"https://pith.science/pith/5CNVK3A55OIQTMMZ3OUNSMMCQ7/action/replication_record"}},"created_at":"2026-07-05T06:14:56.677450+00:00","updated_at":"2026-07-05T06:14:56.677450+00:00"}