{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:F4L7FWJD5M35MZWMSZUWHC265E","short_pith_number":"pith:F4L7FWJD","canonical_record":{"source":{"id":"2505.13060","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T12:51:02Z","cross_cats_sorted":[],"title_canon_sha256":"a2102f99b8627b191277edd13f4798c6d65de2bdbc6aea6c032c1157b9a7e198","abstract_canon_sha256":"cb26ce047e3d541543837b16ce949d3bd8acb4be7f93888bba42aefd5deffa99"},"schema_version":"1.0"},"canonical_sha256":"2f17f2d923eb37d666cc9669638b5ee9224d9569eba8d7c83f5bbc60ebd6600c","source":{"kind":"arxiv","id":"2505.13060","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13060","created_at":"2026-07-05T11:05:14Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13060v1","created_at":"2026-07-05T11:05:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13060","created_at":"2026-07-05T11:05:14Z"},{"alias_kind":"pith_short_12","alias_value":"F4L7FWJD5M35","created_at":"2026-07-05T11:05:14Z"},{"alias_kind":"pith_short_16","alias_value":"F4L7FWJD5M35MZWM","created_at":"2026-07-05T11:05:14Z"},{"alias_kind":"pith_short_8","alias_value":"F4L7FWJD","created_at":"2026-07-05T11:05:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:F4L7FWJD5M35MZWMSZUWHC265E","target":"record","payload":{"canonical_record":{"source":{"id":"2505.13060","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T12:51:02Z","cross_cats_sorted":[],"title_canon_sha256":"a2102f99b8627b191277edd13f4798c6d65de2bdbc6aea6c032c1157b9a7e198","abstract_canon_sha256":"cb26ce047e3d541543837b16ce949d3bd8acb4be7f93888bba42aefd5deffa99"},"schema_version":"1.0"},"canonical_sha256":"2f17f2d923eb37d666cc9669638b5ee9224d9569eba8d7c83f5bbc60ebd6600c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:14.519144Z","signature_b64":"mcawERh/92ki65okXu9Z+JffrDqTd4cn9BJcHLbkTtM02trnuwZdeRozokWMAf8RSfcsnO9GKWXJTK/ZsKfDBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f17f2d923eb37d666cc9669638b5ee9224d9569eba8d7c83f5bbc60ebd6600c","last_reissued_at":"2026-07-05T11:05:14.518701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:14.518701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.13060","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:05:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VxYgchZC5tSbvFov68H65OFikcWYmjqejuUuKhTQB5IwhjBdhebU7cRFdR/d/+JLi4uzbov458+p7BYU3FcrCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:25:38.305562Z"},"content_sha256":"e6fd5b1699ee3fea9170cfdfe1ef23f2643a0a7254529e667d18f03d4048f929","schema_version":"1.0","event_id":"sha256:e6fd5b1699ee3fea9170cfdfe1ef23f2643a0a7254529e667d18f03d4048f929"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:F4L7FWJD5M35MZWMSZUWHC265E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automatic mixed precision for optimizing gained time with constrained loss mean-squared-error based on model partition to sequential sub-graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Ohayon, Itay Niv, Shmulik Markovich-Golan, Yair Hanani","submitted_at":"2025-05-19T12:51:02Z","abstract_excerpt":"Quantization is essential for Neural Network (NN) compression, reducing model size and computational demands by using lower bit-width data types, though aggressive reduction often hampers accuracy. Mixed Precision (MP) mitigates this tradeoff by varying the numerical precision across network layers. This study focuses on automatically selecting an optimal MP configuration within Post-Training Quantization (PTQ) for inference. The first key contribution is a novel sensitivity metric derived from a first-order Taylor series expansion of the loss function as a function of quantization errors in w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13060","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/2505.13060/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:05:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5X2GympxYHA40L8jNPSOLzooqDq9Vp6be6F61XsAaKF6QtJOLNlzPZvI9NMUCkT+ZUj8Pd+wzODAlbx5AIEjAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:25:38.305939Z"},"content_sha256":"1e49ba78a155296c6ded0cff1d75f7c5013ba2169625efae3a80cec702d9a14f","schema_version":"1.0","event_id":"sha256:1e49ba78a155296c6ded0cff1d75f7c5013ba2169625efae3a80cec702d9a14f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F4L7FWJD5M35MZWMSZUWHC265E/bundle.json","state_url":"https://pith.science/pith/F4L7FWJD5M35MZWMSZUWHC265E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F4L7FWJD5M35MZWMSZUWHC265E/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T23:25:38Z","links":{"resolver":"https://pith.science/pith/F4L7FWJD5M35MZWMSZUWHC265E","bundle":"https://pith.science/pith/F4L7FWJD5M35MZWMSZUWHC265E/bundle.json","state":"https://pith.science/pith/F4L7FWJD5M35MZWMSZUWHC265E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F4L7FWJD5M35MZWMSZUWHC265E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:F4L7FWJD5M35MZWMSZUWHC265E","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":"cb26ce047e3d541543837b16ce949d3bd8acb4be7f93888bba42aefd5deffa99","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T12:51:02Z","title_canon_sha256":"a2102f99b8627b191277edd13f4798c6d65de2bdbc6aea6c032c1157b9a7e198"},"schema_version":"1.0","source":{"id":"2505.13060","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13060","created_at":"2026-07-05T11:05:14Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13060v1","created_at":"2026-07-05T11:05:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13060","created_at":"2026-07-05T11:05:14Z"},{"alias_kind":"pith_short_12","alias_value":"F4L7FWJD5M35","created_at":"2026-07-05T11:05:14Z"},{"alias_kind":"pith_short_16","alias_value":"F4L7FWJD5M35MZWM","created_at":"2026-07-05T11:05:14Z"},{"alias_kind":"pith_short_8","alias_value":"F4L7FWJD","created_at":"2026-07-05T11:05:14Z"}],"graph_snapshots":[{"event_id":"sha256:1e49ba78a155296c6ded0cff1d75f7c5013ba2169625efae3a80cec702d9a14f","target":"graph","created_at":"2026-07-05T11:05:14Z","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/2505.13060/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Quantization is essential for Neural Network (NN) compression, reducing model size and computational demands by using lower bit-width data types, though aggressive reduction often hampers accuracy. Mixed Precision (MP) mitigates this tradeoff by varying the numerical precision across network layers. This study focuses on automatically selecting an optimal MP configuration within Post-Training Quantization (PTQ) for inference. The first key contribution is a novel sensitivity metric derived from a first-order Taylor series expansion of the loss function as a function of quantization errors in w","authors_text":"Daniel Ohayon, Itay Niv, Shmulik Markovich-Golan, Yair Hanani","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T12:51:02Z","title":"Automatic mixed precision for optimizing gained time with constrained loss mean-squared-error based on model partition to sequential sub-graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13060","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:e6fd5b1699ee3fea9170cfdfe1ef23f2643a0a7254529e667d18f03d4048f929","target":"record","created_at":"2026-07-05T11:05:14Z","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":"cb26ce047e3d541543837b16ce949d3bd8acb4be7f93888bba42aefd5deffa99","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T12:51:02Z","title_canon_sha256":"a2102f99b8627b191277edd13f4798c6d65de2bdbc6aea6c032c1157b9a7e198"},"schema_version":"1.0","source":{"id":"2505.13060","kind":"arxiv","version":1}},"canonical_sha256":"2f17f2d923eb37d666cc9669638b5ee9224d9569eba8d7c83f5bbc60ebd6600c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f17f2d923eb37d666cc9669638b5ee9224d9569eba8d7c83f5bbc60ebd6600c","first_computed_at":"2026-07-05T11:05:14.518701Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:14.518701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mcawERh/92ki65okXu9Z+JffrDqTd4cn9BJcHLbkTtM02trnuwZdeRozokWMAf8RSfcsnO9GKWXJTK/ZsKfDBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:14.519144Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13060","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e6fd5b1699ee3fea9170cfdfe1ef23f2643a0a7254529e667d18f03d4048f929","sha256:1e49ba78a155296c6ded0cff1d75f7c5013ba2169625efae3a80cec702d9a14f"],"state_sha256":"660e9b9206112e5ea2956978911ca11ffd1413d87edd1d1c1641f806d6c71a65"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IUV0IC5lZ4FRp6uQ4Jgi3yw5wCOtEUxhaQ6s2+qlT/y6Xt8fELd1g9nHFZ5HcRJv6IvvdtMj9olvUm0Z8XsPDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:25:38.307938Z","bundle_sha256":"b9c135f9ccf628fb8230a9a6fb8ef7650b31b824bbc60d4041a393333a18879f"}}