{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HQ2KQGRD5XCB26F7IFTYIS2A4U","short_pith_number":"pith:HQ2KQGRD","schema_version":"1.0","canonical_sha256":"3c34a81a23edc41d78bf4167844b40e5302f5d089fa8f4476bfc74d78c575723","source":{"kind":"arxiv","id":"2301.13741","version":3},"attestation_state":"computed","paper":{"title":"UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chaofan Tao, Chun Yuan, Dachuan Shi, Jiaqi Wang, Ying Jin, Zhendong Yang","submitted_at":"2023-01-31T16:18:52Z","abstract_excerpt":"Real-world data contains a vast amount of multimodal information, among which vision and language are the two most representative modalities. Moreover, increasingly heavier models, \\textit{e}.\\textit{g}., Transformers, have attracted the attention of researchers to model compression. However, how to compress multimodal models, especially vison-language Transformers, is still under-explored. This paper proposes the \\textbf{U}nified and \\textbf{P}r\\textbf{o}gressive \\textbf{P}runing (\\textbf{\\emph{UPop}}) as a universal vison-language Transformer compression framework, which incorporates 1) unif"},"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":"2301.13741","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-31T16:18:52Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"e6459fcfb680147f7691caf11164d4cfaf1579df1313bb6ab912013e20a2bb51","abstract_canon_sha256":"161dc281137313a2d81afc7d87b7bc2fbccf6ef5f05ebf27c5cbce1eff689aff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:18.093724Z","signature_b64":"ev7R4C3X7UHYI814DDdycqiR/GFwXlUqXqP+hC0xu4xHrEPlWOopzoZoccCnmm5yZ0e/Mp2V8Jbcxl9npxFCDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c34a81a23edc41d78bf4167844b40e5302f5d089fa8f4476bfc74d78c575723","last_reissued_at":"2026-07-05T06:26:18.093095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:18.093095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chaofan Tao, Chun Yuan, Dachuan Shi, Jiaqi Wang, Ying Jin, Zhendong Yang","submitted_at":"2023-01-31T16:18:52Z","abstract_excerpt":"Real-world data contains a vast amount of multimodal information, among which vision and language are the two most representative modalities. Moreover, increasingly heavier models, \\textit{e}.\\textit{g}., Transformers, have attracted the attention of researchers to model compression. However, how to compress multimodal models, especially vison-language Transformers, is still under-explored. This paper proposes the \\textbf{U}nified and \\textbf{P}r\\textbf{o}gressive \\textbf{P}runing (\\textbf{\\emph{UPop}}) as a universal vison-language Transformer compression framework, which incorporates 1) unif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13741","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/2301.13741/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":"2301.13741","created_at":"2026-07-05T06:26:18.093157+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.13741v3","created_at":"2026-07-05T06:26:18.093157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13741","created_at":"2026-07-05T06:26:18.093157+00:00"},{"alias_kind":"pith_short_12","alias_value":"HQ2KQGRD5XCB","created_at":"2026-07-05T06:26:18.093157+00:00"},{"alias_kind":"pith_short_16","alias_value":"HQ2KQGRD5XCB26F7","created_at":"2026-07-05T06:26:18.093157+00:00"},{"alias_kind":"pith_short_8","alias_value":"HQ2KQGRD","created_at":"2026-07-05T06:26:18.093157+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.21723","citing_title":"Detection Transformers Under the Knife: A Neuroscience-Inspired Approach to Ablations","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HQ2KQGRD5XCB26F7IFTYIS2A4U","json":"https://pith.science/pith/HQ2KQGRD5XCB26F7IFTYIS2A4U.json","graph_json":"https://pith.science/api/pith-number/HQ2KQGRD5XCB26F7IFTYIS2A4U/graph.json","events_json":"https://pith.science/api/pith-number/HQ2KQGRD5XCB26F7IFTYIS2A4U/events.json","paper":"https://pith.science/paper/HQ2KQGRD"},"agent_actions":{"view_html":"https://pith.science/pith/HQ2KQGRD5XCB26F7IFTYIS2A4U","download_json":"https://pith.science/pith/HQ2KQGRD5XCB26F7IFTYIS2A4U.json","view_paper":"https://pith.science/paper/HQ2KQGRD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.13741&json=true","fetch_graph":"https://pith.science/api/pith-number/HQ2KQGRD5XCB26F7IFTYIS2A4U/graph.json","fetch_events":"https://pith.science/api/pith-number/HQ2KQGRD5XCB26F7IFTYIS2A4U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HQ2KQGRD5XCB26F7IFTYIS2A4U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HQ2KQGRD5XCB26F7IFTYIS2A4U/action/storage_attestation","attest_author":"https://pith.science/pith/HQ2KQGRD5XCB26F7IFTYIS2A4U/action/author_attestation","sign_citation":"https://pith.science/pith/HQ2KQGRD5XCB26F7IFTYIS2A4U/action/citation_signature","submit_replication":"https://pith.science/pith/HQ2KQGRD5XCB26F7IFTYIS2A4U/action/replication_record"}},"created_at":"2026-07-05T06:26:18.093157+00:00","updated_at":"2026-07-05T06:26:18.093157+00:00"}