{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KA5WNAORT6RCXWVEP6Q4XF23K6","short_pith_number":"pith:KA5WNAOR","schema_version":"1.0","canonical_sha256":"503b6681d19fa22bdaa47fa1cb975b57aa340313dec5530cb3579b64106ae2a7","source":{"kind":"arxiv","id":"2409.17634","version":1},"attestation_state":"computed","paper":{"title":"P4Q: Learning to Prompt for Quantization in Visual-language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Baochang Zhang, Huixin Sun, Runqi Wang, Xianbin Cao, Xiaolong Jiang, Yanjing Li, Yao Hu","submitted_at":"2024-09-26T08:31:27Z","abstract_excerpt":"Large-scale pre-trained Vision-Language Models (VLMs) have gained prominence in various visual and multimodal tasks, yet the deployment of VLMs on downstream application platforms remains challenging due to their prohibitive requirements of training samples and computing resources. Fine-tuning and quantization of VLMs can substantially reduce the sample and computation costs, which are in urgent need. There are two prevailing paradigms in quantization, Quantization-Aware Training (QAT) can effectively quantize large-scale VLMs but incur a huge training cost, while low-bit Post-Training Quantiz"},"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":"2409.17634","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-26T08:31:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b8b45440f03de40372ea062ed08f8fd08b27ba783bfaa71bfe97122126d7fb0a","abstract_canon_sha256":"f2654ea6ef4af0b8432d6f51716973c5cde1ebabc4a25ba211961f740e8ab4af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:13.185065Z","signature_b64":"xDALSBOIfRLllPbj5RFwvynqnzmxb7W5rBOuEW1hsWltEFOHQZDUuIbYgusYBv5BdY0dIqr9NwyzCcstPy7WDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"503b6681d19fa22bdaa47fa1cb975b57aa340313dec5530cb3579b64106ae2a7","last_reissued_at":"2026-07-05T09:12:13.184577Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:13.184577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"P4Q: Learning to Prompt for Quantization in Visual-language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Baochang Zhang, Huixin Sun, Runqi Wang, Xianbin Cao, Xiaolong Jiang, Yanjing Li, Yao Hu","submitted_at":"2024-09-26T08:31:27Z","abstract_excerpt":"Large-scale pre-trained Vision-Language Models (VLMs) have gained prominence in various visual and multimodal tasks, yet the deployment of VLMs on downstream application platforms remains challenging due to their prohibitive requirements of training samples and computing resources. Fine-tuning and quantization of VLMs can substantially reduce the sample and computation costs, which are in urgent need. There are two prevailing paradigms in quantization, Quantization-Aware Training (QAT) can effectively quantize large-scale VLMs but incur a huge training cost, while low-bit Post-Training Quantiz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17634","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/2409.17634/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":"2409.17634","created_at":"2026-07-05T09:12:13.184643+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.17634v1","created_at":"2026-07-05T09:12:13.184643+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17634","created_at":"2026-07-05T09:12:13.184643+00:00"},{"alias_kind":"pith_short_12","alias_value":"KA5WNAORT6RC","created_at":"2026-07-05T09:12:13.184643+00:00"},{"alias_kind":"pith_short_16","alias_value":"KA5WNAORT6RCXWVE","created_at":"2026-07-05T09:12:13.184643+00:00"},{"alias_kind":"pith_short_8","alias_value":"KA5WNAOR","created_at":"2026-07-05T09:12:13.184643+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.09262","citing_title":"Harnessing Input-Adaptive Inference for Efficient VLN","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KA5WNAORT6RCXWVEP6Q4XF23K6","json":"https://pith.science/pith/KA5WNAORT6RCXWVEP6Q4XF23K6.json","graph_json":"https://pith.science/api/pith-number/KA5WNAORT6RCXWVEP6Q4XF23K6/graph.json","events_json":"https://pith.science/api/pith-number/KA5WNAORT6RCXWVEP6Q4XF23K6/events.json","paper":"https://pith.science/paper/KA5WNAOR"},"agent_actions":{"view_html":"https://pith.science/pith/KA5WNAORT6RCXWVEP6Q4XF23K6","download_json":"https://pith.science/pith/KA5WNAORT6RCXWVEP6Q4XF23K6.json","view_paper":"https://pith.science/paper/KA5WNAOR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.17634&json=true","fetch_graph":"https://pith.science/api/pith-number/KA5WNAORT6RCXWVEP6Q4XF23K6/graph.json","fetch_events":"https://pith.science/api/pith-number/KA5WNAORT6RCXWVEP6Q4XF23K6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KA5WNAORT6RCXWVEP6Q4XF23K6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KA5WNAORT6RCXWVEP6Q4XF23K6/action/storage_attestation","attest_author":"https://pith.science/pith/KA5WNAORT6RCXWVEP6Q4XF23K6/action/author_attestation","sign_citation":"https://pith.science/pith/KA5WNAORT6RCXWVEP6Q4XF23K6/action/citation_signature","submit_replication":"https://pith.science/pith/KA5WNAORT6RCXWVEP6Q4XF23K6/action/replication_record"}},"created_at":"2026-07-05T09:12:13.184643+00:00","updated_at":"2026-07-05T09:12:13.184643+00:00"}