{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FP3XCKLVSL7X7NUWWOQKW5OCK4","short_pith_number":"pith:FP3XCKLV","schema_version":"1.0","canonical_sha256":"2bf771297592ff7fb696b3a0ab75c25726f1b0809b59cfad9cf32168540a2659","source":{"kind":"arxiv","id":"2212.08254","version":2},"attestation_state":"computed","paper":{"title":"RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Junrui Xiao, Lianwei Yang, Qingyi Gu, Zhikai Li","submitted_at":"2022-12-16T02:52:37Z","abstract_excerpt":"Post-training quantization (PTQ), which only requires a tiny dataset for calibration without end-to-end retraining, is a light and practical model compression technique. Recently, several PTQ schemes for vision transformers (ViTs) have been presented; unfortunately, they typically suffer from non-trivial accuracy degradation, especially in low-bit cases. In this paper, we propose RepQ-ViT, a novel PTQ framework for ViTs based on quantization scale reparameterization, to address the above issues. RepQ-ViT decouples the quantization and inference processes, where the former employs complex quant"},"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":"2212.08254","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-16T02:52:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"775232001180699544ad12823d44842a87a304b4aaf76acea62099cb13f20d0e","abstract_canon_sha256":"77438288da92fe1f2c11b3ef244e652daf431a159f5af4b9ebba2e4c93dcd180"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:37:53.368800Z","signature_b64":"MOwZYgooxy1L/++JV8B0UteabvYh8dCj0pYaVvxzrYXI77UCrDqjSewVfV6lOeRNnggFUn8mHaQ7wFnQdGFzDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bf771297592ff7fb696b3a0ab75c25726f1b0809b59cfad9cf32168540a2659","last_reissued_at":"2026-07-05T06:37:53.367922Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:37:53.367922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Junrui Xiao, Lianwei Yang, Qingyi Gu, Zhikai Li","submitted_at":"2022-12-16T02:52:37Z","abstract_excerpt":"Post-training quantization (PTQ), which only requires a tiny dataset for calibration without end-to-end retraining, is a light and practical model compression technique. Recently, several PTQ schemes for vision transformers (ViTs) have been presented; unfortunately, they typically suffer from non-trivial accuracy degradation, especially in low-bit cases. In this paper, we propose RepQ-ViT, a novel PTQ framework for ViTs based on quantization scale reparameterization, to address the above issues. RepQ-ViT decouples the quantization and inference processes, where the former employs complex quant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08254","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/2212.08254/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":"2212.08254","created_at":"2026-07-05T06:37:53.367978+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.08254v2","created_at":"2026-07-05T06:37:53.367978+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08254","created_at":"2026-07-05T06:37:53.367978+00:00"},{"alias_kind":"pith_short_12","alias_value":"FP3XCKLVSL7X","created_at":"2026-07-05T06:37:53.367978+00:00"},{"alias_kind":"pith_short_16","alias_value":"FP3XCKLVSL7X7NUW","created_at":"2026-07-05T06:37:53.367978+00:00"},{"alias_kind":"pith_short_8","alias_value":"FP3XCKLV","created_at":"2026-07-05T06:37:53.367978+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/FP3XCKLVSL7X7NUWWOQKW5OCK4","json":"https://pith.science/pith/FP3XCKLVSL7X7NUWWOQKW5OCK4.json","graph_json":"https://pith.science/api/pith-number/FP3XCKLVSL7X7NUWWOQKW5OCK4/graph.json","events_json":"https://pith.science/api/pith-number/FP3XCKLVSL7X7NUWWOQKW5OCK4/events.json","paper":"https://pith.science/paper/FP3XCKLV"},"agent_actions":{"view_html":"https://pith.science/pith/FP3XCKLVSL7X7NUWWOQKW5OCK4","download_json":"https://pith.science/pith/FP3XCKLVSL7X7NUWWOQKW5OCK4.json","view_paper":"https://pith.science/paper/FP3XCKLV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.08254&json=true","fetch_graph":"https://pith.science/api/pith-number/FP3XCKLVSL7X7NUWWOQKW5OCK4/graph.json","fetch_events":"https://pith.science/api/pith-number/FP3XCKLVSL7X7NUWWOQKW5OCK4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FP3XCKLVSL7X7NUWWOQKW5OCK4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FP3XCKLVSL7X7NUWWOQKW5OCK4/action/storage_attestation","attest_author":"https://pith.science/pith/FP3XCKLVSL7X7NUWWOQKW5OCK4/action/author_attestation","sign_citation":"https://pith.science/pith/FP3XCKLVSL7X7NUWWOQKW5OCK4/action/citation_signature","submit_replication":"https://pith.science/pith/FP3XCKLVSL7X7NUWWOQKW5OCK4/action/replication_record"}},"created_at":"2026-07-05T06:37:53.367978+00:00","updated_at":"2026-07-05T06:37:53.367978+00:00"}