{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z2ZJD7LEASZBL6GQD7XWUJL5VC","short_pith_number":"pith:Z2ZJD7LE","schema_version":"1.0","canonical_sha256":"ceb291fd6404b215f8d01fef6a257da888d1c4a4ac26e6b9bc618bed8221707b","source":{"kind":"arxiv","id":"2412.05551","version":1},"attestation_state":"computed","paper":{"title":"GAQAT: gradient-adaptive quantization-aware training for domain generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Tang, Han Yu, Jiacheng Jiang, Qun Li, Wenwu Zhu, Yuan Meng, Zhi Wang","submitted_at":"2024-12-07T06:07:21Z","abstract_excerpt":"Research on loss surface geometry, such as Sharpness-Aware Minimization (SAM), shows that flatter minima improve generalization. Recent studies further reveal that flatter minima can also reduce the domain generalization (DG) gap. However, existing flatness-based DG techniques predominantly operate within a full-precision training process, which is impractical for deployment on resource-constrained edge devices that typically rely on lower bit-width representations (e.g., 4 bits, 3 bits). Consequently, low-precision quantization-aware training is critical for optimizing these techniques in rea"},"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":"2412.05551","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-07T06:07:21Z","cross_cats_sorted":[],"title_canon_sha256":"4b61bc9d6c3d73a15978442065e52b52bc80f4732af052cfa1570424d93734cf","abstract_canon_sha256":"be67def9d606783c6e13459e99c87e979dc74cc131c7bc986ceee42d07d4fa0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:05.180130Z","signature_b64":"KwEt3haMV+B64qtl8MDeW36ngS4FLCZDPfKJELwezOGhi8HjBJGZAHIdsL9Gwv6OVEEuyZrwARr0OooAyDAnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ceb291fd6404b215f8d01fef6a257da888d1c4a4ac26e6b9bc618bed8221707b","last_reissued_at":"2026-07-05T09:46:05.179754Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:05.179754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GAQAT: gradient-adaptive quantization-aware training for domain generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Tang, Han Yu, Jiacheng Jiang, Qun Li, Wenwu Zhu, Yuan Meng, Zhi Wang","submitted_at":"2024-12-07T06:07:21Z","abstract_excerpt":"Research on loss surface geometry, such as Sharpness-Aware Minimization (SAM), shows that flatter minima improve generalization. Recent studies further reveal that flatter minima can also reduce the domain generalization (DG) gap. However, existing flatness-based DG techniques predominantly operate within a full-precision training process, which is impractical for deployment on resource-constrained edge devices that typically rely on lower bit-width representations (e.g., 4 bits, 3 bits). Consequently, low-precision quantization-aware training is critical for optimizing these techniques in rea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05551","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/2412.05551/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":"2412.05551","created_at":"2026-07-05T09:46:05.179811+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05551v1","created_at":"2026-07-05T09:46:05.179811+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05551","created_at":"2026-07-05T09:46:05.179811+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z2ZJD7LEASZB","created_at":"2026-07-05T09:46:05.179811+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z2ZJD7LEASZBL6GQ","created_at":"2026-07-05T09:46:05.179811+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z2ZJD7LE","created_at":"2026-07-05T09:46:05.179811+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04920","citing_title":"Toward Multi-Domain and Long-Tailed Quantization via Feature Alignment and Scaling","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z2ZJD7LEASZBL6GQD7XWUJL5VC","json":"https://pith.science/pith/Z2ZJD7LEASZBL6GQD7XWUJL5VC.json","graph_json":"https://pith.science/api/pith-number/Z2ZJD7LEASZBL6GQD7XWUJL5VC/graph.json","events_json":"https://pith.science/api/pith-number/Z2ZJD7LEASZBL6GQD7XWUJL5VC/events.json","paper":"https://pith.science/paper/Z2ZJD7LE"},"agent_actions":{"view_html":"https://pith.science/pith/Z2ZJD7LEASZBL6GQD7XWUJL5VC","download_json":"https://pith.science/pith/Z2ZJD7LEASZBL6GQD7XWUJL5VC.json","view_paper":"https://pith.science/paper/Z2ZJD7LE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05551&json=true","fetch_graph":"https://pith.science/api/pith-number/Z2ZJD7LEASZBL6GQD7XWUJL5VC/graph.json","fetch_events":"https://pith.science/api/pith-number/Z2ZJD7LEASZBL6GQD7XWUJL5VC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z2ZJD7LEASZBL6GQD7XWUJL5VC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z2ZJD7LEASZBL6GQD7XWUJL5VC/action/storage_attestation","attest_author":"https://pith.science/pith/Z2ZJD7LEASZBL6GQD7XWUJL5VC/action/author_attestation","sign_citation":"https://pith.science/pith/Z2ZJD7LEASZBL6GQD7XWUJL5VC/action/citation_signature","submit_replication":"https://pith.science/pith/Z2ZJD7LEASZBL6GQD7XWUJL5VC/action/replication_record"}},"created_at":"2026-07-05T09:46:05.179811+00:00","updated_at":"2026-07-05T09:46:05.179811+00:00"}