{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:374RULZI5G4X2XF45LJP4WBX44","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"451337235e2a50a7d365f0936b6db40ac8219349be6e57521d4d2628804d5e99","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-08T01:20:24Z","title_canon_sha256":"d72ae7b70752853d323f591730b3ea4ce37062ad7ae149a93ef6cbfb527c405e"},"schema_version":"1.0","source":{"id":"2505.04877","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.04877","created_at":"2026-07-05T11:04:50Z"},{"alias_kind":"arxiv_version","alias_value":"2505.04877v1","created_at":"2026-07-05T11:04:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04877","created_at":"2026-07-05T11:04:50Z"},{"alias_kind":"pith_short_12","alias_value":"374RULZI5G4X","created_at":"2026-07-05T11:04:50Z"},{"alias_kind":"pith_short_16","alias_value":"374RULZI5G4X2XF4","created_at":"2026-07-05T11:04:50Z"},{"alias_kind":"pith_short_8","alias_value":"374RULZI","created_at":"2026-07-05T11:04:50Z"}],"graph_snapshots":[{"event_id":"sha256:f65dbfd3ae51bd7753c943cdf14d58b64771cee89fa41a073ed3be31c003cdc7","target":"graph","created_at":"2026-07-05T11:04:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.04877/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mixed Precision Quantization (MPQ) has become an essential technique for optimizing neural network by determining the optimal bitwidth per layer. Existing MPQ methods, however, face a major hurdle: they require a computationally expensive search for quantization policies on large-scale datasets. To resolve this issue, we introduce a novel approach that first searches for quantization policies on small datasets and then generalizes them to large-scale datasets. This approach simplifies the process, eliminating the need for large-scale quantization fine-tuning and only necessitating model weight","authors_text":"Guoyang Xie, Jianlun Ma, Lianbo Ma, Qiang He, Yuee Zhou, Zhichao Lu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-08T01:20:24Z","title":"Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04877","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:df626ecb760937d5f662083616752baf807692c565f75db698eaaa309d893ddf","target":"record","created_at":"2026-07-05T11:04:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"451337235e2a50a7d365f0936b6db40ac8219349be6e57521d4d2628804d5e99","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-08T01:20:24Z","title_canon_sha256":"d72ae7b70752853d323f591730b3ea4ce37062ad7ae149a93ef6cbfb527c405e"},"schema_version":"1.0","source":{"id":"2505.04877","kind":"arxiv","version":1}},"canonical_sha256":"dff91a2f28e9b97d5cbcead2fe5837e727b84b4bf38e49d2b6d1656f97c65b96","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dff91a2f28e9b97d5cbcead2fe5837e727b84b4bf38e49d2b6d1656f97c65b96","first_computed_at":"2026-07-05T11:04:50.599005Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:50.599005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kNtiYKvCllKL5QUOPdKFQQqszbEoatsABI/iI5CxPJxStpjqwlIIXswT9RBIUIVy23LhNWFMBnnrUc/CaP7RBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:50.599491Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.04877","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df626ecb760937d5f662083616752baf807692c565f75db698eaaa309d893ddf","sha256:f65dbfd3ae51bd7753c943cdf14d58b64771cee89fa41a073ed3be31c003cdc7"],"state_sha256":"2cccf1611e5de4104fa64800e81b6b437ffdfe7e71eaf45d6563d81e831eefab"}