{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DTUJ423PIJW3K5QJEWNVAFJV6P","short_pith_number":"pith:DTUJ423P","schema_version":"1.0","canonical_sha256":"1ce89e6b6f426db57609259b501535f3f6a6064218015a5775f3ab49a7fc069e","source":{"kind":"arxiv","id":"2104.11832","version":2},"attestation_state":"computed","paper":{"title":"Playing Lottery Tickets with Vision and Language","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jingjing Liu, Lijuan Wang, Linjie Li, Shuohang Wang, Tianlong Chen, Yen-Chun Chen, Yu Cheng, Zhe Gan, Zicheng Liu","submitted_at":"2021-04-23T22:24:33Z","abstract_excerpt":"Large-scale pre-training has recently revolutionized vision-and-language (VL) research. Models such as LXMERT and UNITER have significantly lifted the state of the art over a wide range of VL tasks. However, the large number of parameters in such models hinders their application in practice. In parallel, work on the lottery ticket hypothesis (LTH) has shown that deep neural networks contain small matching subnetworks that can achieve on par or even better performance than the dense networks when trained in isolation. In this work, we perform the first empirical study to assess whether such tra"},"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":"2104.11832","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-23T22:24:33Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"3a7b3a3e0336a82bd0343ead8f0f19613223cd7cb5577c389e18f69079440b49","abstract_canon_sha256":"93683ebb866313b32dc73804d1533523c594ed1f9cf3547dcce1d51f9c88ce26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:41:02.713263Z","signature_b64":"Bn7xPOJZ8Ui1C2YzWJ5OkClbaAaksLP6riTsVCcLiINKDixEa1UiqLNmjqTRtkfYXENcHSK1AaXOI0ZIbvcbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ce89e6b6f426db57609259b501535f3f6a6064218015a5775f3ab49a7fc069e","last_reissued_at":"2026-07-05T03:41:02.712771Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:41:02.712771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Playing Lottery Tickets with Vision and Language","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jingjing Liu, Lijuan Wang, Linjie Li, Shuohang Wang, Tianlong Chen, Yen-Chun Chen, Yu Cheng, Zhe Gan, Zicheng Liu","submitted_at":"2021-04-23T22:24:33Z","abstract_excerpt":"Large-scale pre-training has recently revolutionized vision-and-language (VL) research. Models such as LXMERT and UNITER have significantly lifted the state of the art over a wide range of VL tasks. However, the large number of parameters in such models hinders their application in practice. In parallel, work on the lottery ticket hypothesis (LTH) has shown that deep neural networks contain small matching subnetworks that can achieve on par or even better performance than the dense networks when trained in isolation. In this work, we perform the first empirical study to assess whether such tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.11832","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/2104.11832/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":"2104.11832","created_at":"2026-07-05T03:41:02.712830+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.11832v2","created_at":"2026-07-05T03:41:02.712830+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.11832","created_at":"2026-07-05T03:41:02.712830+00:00"},{"alias_kind":"pith_short_12","alias_value":"DTUJ423PIJW3","created_at":"2026-07-05T03:41:02.712830+00:00"},{"alias_kind":"pith_short_16","alias_value":"DTUJ423PIJW3K5QJ","created_at":"2026-07-05T03:41:02.712830+00:00"},{"alias_kind":"pith_short_8","alias_value":"DTUJ423P","created_at":"2026-07-05T03:41:02.712830+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/DTUJ423PIJW3K5QJEWNVAFJV6P","json":"https://pith.science/pith/DTUJ423PIJW3K5QJEWNVAFJV6P.json","graph_json":"https://pith.science/api/pith-number/DTUJ423PIJW3K5QJEWNVAFJV6P/graph.json","events_json":"https://pith.science/api/pith-number/DTUJ423PIJW3K5QJEWNVAFJV6P/events.json","paper":"https://pith.science/paper/DTUJ423P"},"agent_actions":{"view_html":"https://pith.science/pith/DTUJ423PIJW3K5QJEWNVAFJV6P","download_json":"https://pith.science/pith/DTUJ423PIJW3K5QJEWNVAFJV6P.json","view_paper":"https://pith.science/paper/DTUJ423P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.11832&json=true","fetch_graph":"https://pith.science/api/pith-number/DTUJ423PIJW3K5QJEWNVAFJV6P/graph.json","fetch_events":"https://pith.science/api/pith-number/DTUJ423PIJW3K5QJEWNVAFJV6P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DTUJ423PIJW3K5QJEWNVAFJV6P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DTUJ423PIJW3K5QJEWNVAFJV6P/action/storage_attestation","attest_author":"https://pith.science/pith/DTUJ423PIJW3K5QJEWNVAFJV6P/action/author_attestation","sign_citation":"https://pith.science/pith/DTUJ423PIJW3K5QJEWNVAFJV6P/action/citation_signature","submit_replication":"https://pith.science/pith/DTUJ423PIJW3K5QJEWNVAFJV6P/action/replication_record"}},"created_at":"2026-07-05T03:41:02.712830+00:00","updated_at":"2026-07-05T03:41:02.712830+00:00"}