{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SCKZ2TKU7R5RXVZCWPLVTA645T","short_pith_number":"pith:SCKZ2TKU","schema_version":"1.0","canonical_sha256":"90959d4d54fc7b1bd722b3d75983dcecc550c732931eedeef759a807c0dbb2f6","source":{"kind":"arxiv","id":"2605.09503","version":2},"attestation_state":"computed","paper":{"title":"PermuQuant: Lowering Per-Group Quantization Error by Reordering Channels for Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Reordering channels to group similar statistics reduces per-group quantization error in diffusion models.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junxian Li, Kai Liu, Kaiwen Tao, Renjing Pei, Yongsen Cheng, Yulun Zhang, Zhikai Chen, Zhixin Wang","submitted_at":"2026-05-10T12:26:50Z","abstract_excerpt":"Large-scale visual generative models have achieved remarkable performance. However, their high computational and memory costs make deployment challenging in resource-constrained scenarios, such as interactive applications and personal single-GPU usage. Post-training quantization (PTQ) offers a practical solution by compressing pretrained models without expensive retraining. However, existing PTQ methods still suffer from severe quality degradation under extremely low-bit settings. In this paper, we identify channel ordering as an important but underexplored factor in per-group quantization. In"},"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":"2605.09503","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-10T12:26:50Z","cross_cats_sorted":[],"title_canon_sha256":"cfdfec046d9e408ceb2326dacfe0e3d66d76b14d219b49053b4cf07042f68767","abstract_canon_sha256":"89dd5604c2002a67a55cb5083eb65736dcd9dbddfb035fcb21d6ef526dbfe745"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:18.800007Z","signature_b64":"vz+qit7hdHzI1OfxpwI+QoQ0A3r6TyXUOtC9twMEQvH9tU3KTJV4jFGIpCIcDVSt7p/rHoCNfFdEh9GWtBMJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90959d4d54fc7b1bd722b3d75983dcecc550c732931eedeef759a807c0dbb2f6","last_reissued_at":"2026-06-02T02:04:18.799441Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:18.799441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PermuQuant: Lowering Per-Group Quantization Error by Reordering Channels for Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Reordering channels to group similar statistics reduces per-group quantization error in diffusion models.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junxian Li, Kai Liu, Kaiwen Tao, Renjing Pei, Yongsen Cheng, Yulun Zhang, Zhikai Chen, Zhixin Wang","submitted_at":"2026-05-10T12:26:50Z","abstract_excerpt":"Large-scale visual generative models have achieved remarkable performance. However, their high computational and memory costs make deployment challenging in resource-constrained scenarios, such as interactive applications and personal single-GPU usage. Post-training quantization (PTQ) offers a practical solution by compressing pretrained models without expensive retraining. However, existing PTQ methods still suffer from severe quality degradation under extremely low-bit settings. In this paper, we identify channel ordering as an important but underexplored factor in per-group quantization. In"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"PermuQuant consistently reduces quantization error and outperforms existing PTQ baselines. On FLUX.1-dev with an RTX 5090, PermuQuant achieves up to a 1.8× single step speedup and reduces the DiT memory footprint by 3.5× under W4A4 NVFP4 quantization.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a permutation chosen on calibration data via the joint second-moment criterion will generalize to the full input distribution at inference time and will not introduce new artifacts in the generated outputs.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PermuQuant reduces per-group quantization error in diffusion models by sorting channels with similar activation and weight statistics into the same groups using a calibration-checked permutation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Reordering channels to group similar statistics reduces per-group quantization error in diffusion models.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"f4943accd8ed586b19be0e6617004ba1b2428ada61acfacd21b03dbdbf95d9b8"},"source":{"id":"2605.09503","kind":"arxiv","version":2},"verdict":{"id":"8c63ad3d-c07e-4742-b55a-a0c4e3a52aa5","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T04:17:00.312464Z","strongest_claim":"PermuQuant consistently reduces quantization error and outperforms existing PTQ baselines. On FLUX.1-dev with an RTX 5090, PermuQuant achieves up to a 1.8× single step speedup and reduces the DiT memory footprint by 3.5× under W4A4 NVFP4 quantization.","one_line_summary":"PermuQuant reduces per-group quantization error in diffusion models by sorting channels with similar activation and weight statistics into the same groups using a calibration-checked permutation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a permutation chosen on calibration data via the joint second-moment criterion will generalize to the full input distribution at inference time and will not introduce new artifacts in the generated outputs.","pith_extraction_headline":"Reordering channels to group similar statistics reduces per-group quantization error in diffusion models."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.09503/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T07:42:01.380920Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T16:41:37.255516Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T13:01:17.787173Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T10:10:27.411584Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"7f6d5d5810d9779f60c7b85a0866222517c7ca8056bd740c810b98e5e21dce8d"},"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":"2605.09503","created_at":"2026-06-02T02:04:18.799508+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.09503v2","created_at":"2026-06-02T02:04:18.799508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.09503","created_at":"2026-06-02T02:04:18.799508+00:00"},{"alias_kind":"pith_short_12","alias_value":"SCKZ2TKU7R5R","created_at":"2026-06-02T02:04:18.799508+00:00"},{"alias_kind":"pith_short_16","alias_value":"SCKZ2TKU7R5RXVZC","created_at":"2026-06-02T02:04:18.799508+00:00"},{"alias_kind":"pith_short_8","alias_value":"SCKZ2TKU","created_at":"2026-06-02T02:04:18.799508+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.02461","citing_title":"OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SCKZ2TKU7R5RXVZCWPLVTA645T","json":"https://pith.science/pith/SCKZ2TKU7R5RXVZCWPLVTA645T.json","graph_json":"https://pith.science/api/pith-number/SCKZ2TKU7R5RXVZCWPLVTA645T/graph.json","events_json":"https://pith.science/api/pith-number/SCKZ2TKU7R5RXVZCWPLVTA645T/events.json","paper":"https://pith.science/paper/SCKZ2TKU"},"agent_actions":{"view_html":"https://pith.science/pith/SCKZ2TKU7R5RXVZCWPLVTA645T","download_json":"https://pith.science/pith/SCKZ2TKU7R5RXVZCWPLVTA645T.json","view_paper":"https://pith.science/paper/SCKZ2TKU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.09503&json=true","fetch_graph":"https://pith.science/api/pith-number/SCKZ2TKU7R5RXVZCWPLVTA645T/graph.json","fetch_events":"https://pith.science/api/pith-number/SCKZ2TKU7R5RXVZCWPLVTA645T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SCKZ2TKU7R5RXVZCWPLVTA645T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SCKZ2TKU7R5RXVZCWPLVTA645T/action/storage_attestation","attest_author":"https://pith.science/pith/SCKZ2TKU7R5RXVZCWPLVTA645T/action/author_attestation","sign_citation":"https://pith.science/pith/SCKZ2TKU7R5RXVZCWPLVTA645T/action/citation_signature","submit_replication":"https://pith.science/pith/SCKZ2TKU7R5RXVZCWPLVTA645T/action/replication_record"}},"created_at":"2026-06-02T02:04:18.799508+00:00","updated_at":"2026-06-02T02:04:18.799508+00:00"}