{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:U7ZFHMP2T2BQY2NE7FPOES74GU","short_pith_number":"pith:U7ZFHMP2","schema_version":"1.0","canonical_sha256":"a7f253b1fa9e830c69a4f95ee24bfc35110f98ce06f84a10dcef5d090a4b527f","source":{"kind":"arxiv","id":"2311.05317","version":1},"attestation_state":"computed","paper":{"title":"RepQ: Generalizing Quantization-Aware Training for Re-Parametrized Architectures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexey Zaytsev, Anastasiia Prutianova, Chung-Kuei Lee, Fengyu Sun, Ivan Koryakovskiy","submitted_at":"2023-11-09T12:25:39Z","abstract_excerpt":"Existing neural networks are memory-consuming and computationally intensive, making deploying them challenging in resource-constrained environments. However, there are various methods to improve their efficiency. Two such methods are quantization, a well-known approach for network compression, and re-parametrization, an emerging technique designed to improve model performance. Although both techniques have been studied individually, there has been limited research on their simultaneous application. To address this gap, we propose a novel approach called RepQ, which applies quantization to re-p"},"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":"2311.05317","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-09T12:25:39Z","cross_cats_sorted":[],"title_canon_sha256":"a7c03c71927e1acf3f40f8add42eebf6f6c7a0682b310be55005f480a373caff","abstract_canon_sha256":"0cfb2341933ddaa276d26f70a8b33f8c1353cec8985ec91c91e1a7d993425c1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:57.666428Z","signature_b64":"OSM/owSo8ue0onJGyDGJB5aGSINOLQzeXe6u2WdOxmgvjrG7LCTCihxwK4jhIK/DlZn8EzyvE5HP4gU/uZj6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7f253b1fa9e830c69a4f95ee24bfc35110f98ce06f84a10dcef5d090a4b527f","last_reissued_at":"2026-07-05T07:10:57.665979Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:57.665979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RepQ: Generalizing Quantization-Aware Training for Re-Parametrized Architectures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexey Zaytsev, Anastasiia Prutianova, Chung-Kuei Lee, Fengyu Sun, Ivan Koryakovskiy","submitted_at":"2023-11-09T12:25:39Z","abstract_excerpt":"Existing neural networks are memory-consuming and computationally intensive, making deploying them challenging in resource-constrained environments. However, there are various methods to improve their efficiency. Two such methods are quantization, a well-known approach for network compression, and re-parametrization, an emerging technique designed to improve model performance. Although both techniques have been studied individually, there has been limited research on their simultaneous application. To address this gap, we propose a novel approach called RepQ, which applies quantization to re-p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05317","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/2311.05317/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":"2311.05317","created_at":"2026-07-05T07:10:57.666044+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.05317v1","created_at":"2026-07-05T07:10:57.666044+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05317","created_at":"2026-07-05T07:10:57.666044+00:00"},{"alias_kind":"pith_short_12","alias_value":"U7ZFHMP2T2BQ","created_at":"2026-07-05T07:10:57.666044+00:00"},{"alias_kind":"pith_short_16","alias_value":"U7ZFHMP2T2BQY2NE","created_at":"2026-07-05T07:10:57.666044+00:00"},{"alias_kind":"pith_short_8","alias_value":"U7ZFHMP2","created_at":"2026-07-05T07:10:57.666044+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/U7ZFHMP2T2BQY2NE7FPOES74GU","json":"https://pith.science/pith/U7ZFHMP2T2BQY2NE7FPOES74GU.json","graph_json":"https://pith.science/api/pith-number/U7ZFHMP2T2BQY2NE7FPOES74GU/graph.json","events_json":"https://pith.science/api/pith-number/U7ZFHMP2T2BQY2NE7FPOES74GU/events.json","paper":"https://pith.science/paper/U7ZFHMP2"},"agent_actions":{"view_html":"https://pith.science/pith/U7ZFHMP2T2BQY2NE7FPOES74GU","download_json":"https://pith.science/pith/U7ZFHMP2T2BQY2NE7FPOES74GU.json","view_paper":"https://pith.science/paper/U7ZFHMP2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.05317&json=true","fetch_graph":"https://pith.science/api/pith-number/U7ZFHMP2T2BQY2NE7FPOES74GU/graph.json","fetch_events":"https://pith.science/api/pith-number/U7ZFHMP2T2BQY2NE7FPOES74GU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U7ZFHMP2T2BQY2NE7FPOES74GU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U7ZFHMP2T2BQY2NE7FPOES74GU/action/storage_attestation","attest_author":"https://pith.science/pith/U7ZFHMP2T2BQY2NE7FPOES74GU/action/author_attestation","sign_citation":"https://pith.science/pith/U7ZFHMP2T2BQY2NE7FPOES74GU/action/citation_signature","submit_replication":"https://pith.science/pith/U7ZFHMP2T2BQY2NE7FPOES74GU/action/replication_record"}},"created_at":"2026-07-05T07:10:57.666044+00:00","updated_at":"2026-07-05T07:10:57.666044+00:00"}