{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:P576AZCHFCJBAH6UHUE6J7PDJ4","short_pith_number":"pith:P576AZCH","schema_version":"1.0","canonical_sha256":"7f7fe064472892101fd43d09e4fde34f3ff795f6e4bbaa918201280839dc6bc2","source":{"kind":"arxiv","id":"2607.28589","version":1},"attestation_state":"computed","paper":{"title":"MixFrag: Fragility-Guided Mixed-Precision Post-Training Quantization for Vision Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Md. Mehrab Hossain Opi, Md. Umar Faruk, Robiul Islam Ryad","submitted_at":"2026-07-30T17:43:36Z","abstract_excerpt":"Post-training quantization (PTQ) has emerged as an effective solution for deploying Vision Transformers (ViTs) on resource-constrained devices. However, existing PTQ methods typically employ uniform bit-widths across transformer components, overlooking their heterogeneous sensitivity to quantization and leading to inefficient precision allocation. In this paper, we propose {MixFrag, a fragility-guided mixed-precision PTQ framework for Vision Transformers. MixFrag first estimates component-level quantization fragility by measuring the Kullback--Leibler (KL) divergence between full-precision and"},"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":"2607.28589","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T17:43:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bc90dadd04475fa26c92fff474883503eec70dd569947c6fed1a8758be14b5dd","abstract_canon_sha256":"c95e08282269e183d7db30e22340779da965ed2ebf3201ffbd7742ef8dd233d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f7fe064472892101fd43d09e4fde34f3ff795f6e4bbaa918201280839dc6bc2","last_reissued_at":"2026-07-31T01:38:47.553360Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:38:47.553360Z"},"graph_snapshot":{"paper":{"title":"MixFrag: Fragility-Guided Mixed-Precision Post-Training Quantization for Vision Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Md. Mehrab Hossain Opi, Md. Umar Faruk, Robiul Islam Ryad","submitted_at":"2026-07-30T17:43:36Z","abstract_excerpt":"Post-training quantization (PTQ) has emerged as an effective solution for deploying Vision Transformers (ViTs) on resource-constrained devices. However, existing PTQ methods typically employ uniform bit-widths across transformer components, overlooking their heterogeneous sensitivity to quantization and leading to inefficient precision allocation. In this paper, we propose {MixFrag, a fragility-guided mixed-precision PTQ framework for Vision Transformers. MixFrag first estimates component-level quantization fragility by measuring the Kullback--Leibler (KL) divergence between full-precision and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28589","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/2607.28589/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":"2607.28589","created_at":"2026-07-31T01:38:47.556644+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.28589v1","created_at":"2026-07-31T01:38:47.556644+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28589","created_at":"2026-07-31T01:38:47.556644+00:00"},{"alias_kind":"pith_short_12","alias_value":"P576AZCHFCJB","created_at":"2026-07-31T01:38:47.556644+00:00"},{"alias_kind":"pith_short_16","alias_value":"P576AZCHFCJBAH6U","created_at":"2026-07-31T01:38:47.556644+00:00"},{"alias_kind":"pith_short_8","alias_value":"P576AZCH","created_at":"2026-07-31T01:38:47.556644+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/P576AZCHFCJBAH6UHUE6J7PDJ4","json":"https://pith.science/pith/P576AZCHFCJBAH6UHUE6J7PDJ4.json","graph_json":"https://pith.science/api/pith-number/P576AZCHFCJBAH6UHUE6J7PDJ4/graph.json","events_json":"https://pith.science/api/pith-number/P576AZCHFCJBAH6UHUE6J7PDJ4/events.json","paper":"https://pith.science/paper/P576AZCH"},"agent_actions":{"view_html":"https://pith.science/pith/P576AZCHFCJBAH6UHUE6J7PDJ4","download_json":"https://pith.science/pith/P576AZCHFCJBAH6UHUE6J7PDJ4.json","view_paper":"https://pith.science/paper/P576AZCH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.28589&json=true","fetch_graph":"https://pith.science/api/pith-number/P576AZCHFCJBAH6UHUE6J7PDJ4/graph.json","fetch_events":"https://pith.science/api/pith-number/P576AZCHFCJBAH6UHUE6J7PDJ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P576AZCHFCJBAH6UHUE6J7PDJ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P576AZCHFCJBAH6UHUE6J7PDJ4/action/storage_attestation","attest_author":"https://pith.science/pith/P576AZCHFCJBAH6UHUE6J7PDJ4/action/author_attestation","sign_citation":"https://pith.science/pith/P576AZCHFCJBAH6UHUE6J7PDJ4/action/citation_signature","submit_replication":"https://pith.science/pith/P576AZCHFCJBAH6UHUE6J7PDJ4/action/replication_record"}},"created_at":"2026-07-31T01:38:47.556644+00:00","updated_at":"2026-07-31T01:38:47.556644+00:00"}