{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:FDLZTBC52UHZZIJQ75ZDFTUOFI","short_pith_number":"pith:FDLZTBC5","canonical_record":{"source":{"id":"1804.05267","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-04-14T19:10:07Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"525d968fef67999df3449bf5a79f800199324a1d56a54b4711cd3af87ffb4bfc","abstract_canon_sha256":"3266e66765f64355f5b615b4035bee8d9be4dffda10b2cd14bceb091b7cb9216"},"schema_version":"1.0"},"canonical_sha256":"28d799845dd50f9ca130ff7232ce8e2a311ab65c318e0ffe26bab0b4ba8f5633","source":{"kind":"arxiv","id":"1804.05267","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.05267","created_at":"2026-05-18T00:18:28Z"},{"alias_kind":"arxiv_version","alias_value":"1804.05267v1","created_at":"2026-05-18T00:18:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.05267","created_at":"2026-05-18T00:18:28Z"},{"alias_kind":"pith_short_12","alias_value":"FDLZTBC52UHZ","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"FDLZTBC52UHZZIJQ","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"FDLZTBC5","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:FDLZTBC52UHZZIJQ75ZDFTUOFI","target":"record","payload":{"canonical_record":{"source":{"id":"1804.05267","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-04-14T19:10:07Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"525d968fef67999df3449bf5a79f800199324a1d56a54b4711cd3af87ffb4bfc","abstract_canon_sha256":"3266e66765f64355f5b615b4035bee8d9be4dffda10b2cd14bceb091b7cb9216"},"schema_version":"1.0"},"canonical_sha256":"28d799845dd50f9ca130ff7232ce8e2a311ab65c318e0ffe26bab0b4ba8f5633","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:28.457788Z","signature_b64":"ZWooFoyoqBHLKuZKeVPyIkpQJ7kiHWRt3qpbOd8eMupq34e8MKJcdhjHCx0YaJwhbJbLHdm2H+wsSXa9nEZIDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28d799845dd50f9ca130ff7232ce8e2a311ab65c318e0ffe26bab0b4ba8f5633","last_reissued_at":"2026-05-18T00:18:28.457428Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:28.457428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.05267","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":"2026-05-18T00:18:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A4P18/jfAtKkFnRELOcRlG8tMS4jp0ZH0ieG06siQGScpPIA6j83e8Z+tI90IMf1/jU9XSE6JSupMSWAgyxXCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T11:00:25.395369Z"},"content_sha256":"13704454f5e1d2057001bd48bc4574a05885296adc127e21b1d56c73164005f0","schema_version":"1.0","event_id":"sha256:13704454f5e1d2057001bd48bc4574a05885296adc127e21b1d56c73164005f0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:FDLZTBC52UHZZIJQ75ZDFTUOFI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Low-Precision Floating-Point Schemes for Neural Network Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adri\\'an Cristal, Eduard Ayguad\\'e, Marc Casas, Marc Ortiz","submitted_at":"2018-04-14T19:10:07Z","abstract_excerpt":"The use of low-precision fixed-point arithmetic along with stochastic rounding has been proposed as a promising alternative to the commonly used 32-bit floating point arithmetic to enhance training neural networks training in terms of performance and energy efficiency. In the first part of this paper, the behaviour of the 12-bit fixed-point arithmetic when training a convolutional neural network with the CIFAR-10 dataset is analysed, showing that such arithmetic is not the most appropriate for the training phase. After that, the paper presents and evaluates, under the same conditions, alternat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.05267","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":""},"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":"2026-05-18T00:18:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yMzyn0a2Z8nTUnWMudf8Iq8ED5V6luPVSVyjVWPl0dDbHE/B/mZie4PxQxgUzeycY16+diUYN7bnMyptJK0CBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T11:00:25.395735Z"},"content_sha256":"af96b96fcb90b5f730692e901b3be4b42b6f0db87a84d7e6846d4e7a730bead1","schema_version":"1.0","event_id":"sha256:af96b96fcb90b5f730692e901b3be4b42b6f0db87a84d7e6846d4e7a730bead1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FDLZTBC52UHZZIJQ75ZDFTUOFI/bundle.json","state_url":"https://pith.science/pith/FDLZTBC52UHZZIJQ75ZDFTUOFI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FDLZTBC52UHZZIJQ75ZDFTUOFI/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":"2026-05-30T11:00:25Z","links":{"resolver":"https://pith.science/pith/FDLZTBC52UHZZIJQ75ZDFTUOFI","bundle":"https://pith.science/pith/FDLZTBC52UHZZIJQ75ZDFTUOFI/bundle.json","state":"https://pith.science/pith/FDLZTBC52UHZZIJQ75ZDFTUOFI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FDLZTBC52UHZZIJQ75ZDFTUOFI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:FDLZTBC52UHZZIJQ75ZDFTUOFI","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":"3266e66765f64355f5b615b4035bee8d9be4dffda10b2cd14bceb091b7cb9216","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-04-14T19:10:07Z","title_canon_sha256":"525d968fef67999df3449bf5a79f800199324a1d56a54b4711cd3af87ffb4bfc"},"schema_version":"1.0","source":{"id":"1804.05267","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.05267","created_at":"2026-05-18T00:18:28Z"},{"alias_kind":"arxiv_version","alias_value":"1804.05267v1","created_at":"2026-05-18T00:18:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.05267","created_at":"2026-05-18T00:18:28Z"},{"alias_kind":"pith_short_12","alias_value":"FDLZTBC52UHZ","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"FDLZTBC52UHZZIJQ","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"FDLZTBC5","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:af96b96fcb90b5f730692e901b3be4b42b6f0db87a84d7e6846d4e7a730bead1","target":"graph","created_at":"2026-05-18T00:18:28Z","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"},"paper":{"abstract_excerpt":"The use of low-precision fixed-point arithmetic along with stochastic rounding has been proposed as a promising alternative to the commonly used 32-bit floating point arithmetic to enhance training neural networks training in terms of performance and energy efficiency. In the first part of this paper, the behaviour of the 12-bit fixed-point arithmetic when training a convolutional neural network with the CIFAR-10 dataset is analysed, showing that such arithmetic is not the most appropriate for the training phase. After that, the paper presents and evaluates, under the same conditions, alternat","authors_text":"Adri\\'an Cristal, Eduard Ayguad\\'e, Marc Casas, Marc Ortiz","cross_cats":["cs.NE","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-04-14T19:10:07Z","title":"Low-Precision Floating-Point Schemes for Neural Network Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.05267","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":"sha256:13704454f5e1d2057001bd48bc4574a05885296adc127e21b1d56c73164005f0","target":"record","created_at":"2026-05-18T00:18:28Z","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":"3266e66765f64355f5b615b4035bee8d9be4dffda10b2cd14bceb091b7cb9216","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-04-14T19:10:07Z","title_canon_sha256":"525d968fef67999df3449bf5a79f800199324a1d56a54b4711cd3af87ffb4bfc"},"schema_version":"1.0","source":{"id":"1804.05267","kind":"arxiv","version":1}},"canonical_sha256":"28d799845dd50f9ca130ff7232ce8e2a311ab65c318e0ffe26bab0b4ba8f5633","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28d799845dd50f9ca130ff7232ce8e2a311ab65c318e0ffe26bab0b4ba8f5633","first_computed_at":"2026-05-18T00:18:28.457428Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:18:28.457428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZWooFoyoqBHLKuZKeVPyIkpQJ7kiHWRt3qpbOd8eMupq34e8MKJcdhjHCx0YaJwhbJbLHdm2H+wsSXa9nEZIDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:18:28.457788Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.05267","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13704454f5e1d2057001bd48bc4574a05885296adc127e21b1d56c73164005f0","sha256:af96b96fcb90b5f730692e901b3be4b42b6f0db87a84d7e6846d4e7a730bead1"],"state_sha256":"c41a06035233482e97816c53c4059bd3b819d7a7ec2d442683d4d0489f7fd9c3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KHDrLiGuz8tsysUY9iTyAhSYfhItUO6wbF0M1BJ3QD/luttAexctklvx7G1jTlVy4dcE4RZREF3CDbOZdlmmCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T11:00:25.398079Z","bundle_sha256":"ff90163907b0f8d6b2e9253905b5c6beb973fa0833d85a28e3b6583a466026e2"}}