{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:SERSJ3VV7EXGB7DJRQDSDMNA32","short_pith_number":"pith:SERSJ3VV","canonical_record":{"source":{"id":"1703.08595","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-24T20:59:50Z","cross_cats_sorted":[],"title_canon_sha256":"bcd0a8a9585394e4d44df56b0bdbe5422b88962198e313ee26f9c9ca1353e8e6","abstract_canon_sha256":"49a4dd6807a50cc76696d0a0f153980e6c9d13c564ae1633655ae22a64b4d34d"},"schema_version":"1.0"},"canonical_sha256":"912324eeb5f92e60fc698c0721b1a0de9f7cf61d1468798ca41c5bf73bf8393e","source":{"kind":"arxiv","id":"1703.08595","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.08595","created_at":"2026-05-18T00:47:56Z"},{"alias_kind":"arxiv_version","alias_value":"1703.08595v1","created_at":"2026-05-18T00:47:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.08595","created_at":"2026-05-18T00:47:56Z"},{"alias_kind":"pith_short_12","alias_value":"SERSJ3VV7EXG","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"SERSJ3VV7EXGB7DJ","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"SERSJ3VV","created_at":"2026-05-18T12:31:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:SERSJ3VV7EXGB7DJRQDSDMNA32","target":"record","payload":{"canonical_record":{"source":{"id":"1703.08595","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-24T20:59:50Z","cross_cats_sorted":[],"title_canon_sha256":"bcd0a8a9585394e4d44df56b0bdbe5422b88962198e313ee26f9c9ca1353e8e6","abstract_canon_sha256":"49a4dd6807a50cc76696d0a0f153980e6c9d13c564ae1633655ae22a64b4d34d"},"schema_version":"1.0"},"canonical_sha256":"912324eeb5f92e60fc698c0721b1a0de9f7cf61d1468798ca41c5bf73bf8393e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:47:56.071530Z","signature_b64":"wX1udJRWZ2s3W+l1dH6e6nM5EgvjZMnmHMKH0uEfMRo89buryxLCL3AHwyD7POdSGhk/V0OkF96nKK0joQtSBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"912324eeb5f92e60fc698c0721b1a0de9f7cf61d1468798ca41c5bf73bf8393e","last_reissued_at":"2026-05-18T00:47:56.070990Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:47:56.070990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.08595","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":"2026-05-18T00:47:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lqtmVBeuVLu6B8CHnfhlmqjbYzkPuV7Us8prcKGGNXvA6xvYcF7xQFQsOXtL/KiDC2jPc0d+UYLPZh9WNZRdCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T08:04:02.865599Z"},"content_sha256":"d30ff8961b85998cf3d2ab7fb13a1038392a993739537e88ef2407057a5c64d9","schema_version":"1.0","event_id":"sha256:d30ff8961b85998cf3d2ab7fb13a1038392a993739537e88ef2407057a5c64d9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:SERSJ3VV7EXGB7DJRQDSDMNA32","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Low Precision Neural Networks using Subband Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aswin Raghavan, David Zhang, Mohamed Amer, Sek Chai, Tim Shields","submitted_at":"2017-03-24T20:59:50Z","abstract_excerpt":"Large-scale deep neural networks (DNN) have been successfully used in a number of tasks from image recognition to natural language processing. They are trained using large training sets on large models, making them computationally and memory intensive. As such, there is much interest in research development for faster training and test time. In this paper, we present a unique approach using lower precision weights for more efficient and faster training phase. We separate imagery into different frequency bands (e.g. with different information content) such that the neural net can better learn u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.08595","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":"2026-05-18T00:47:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MKEq81ZwExe1xEFUreKQcwwOcCX0LHsB6qnGGBUAGxUz+S5kVXbHcuWMyXyE98SHQk5NdX0vUhawfMrIHNsSAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T08:04:02.865948Z"},"content_sha256":"0e33261cba7cbc7f07b3b32e44290fd213cd137040ba583a08733ca6ac4752ec","schema_version":"1.0","event_id":"sha256:0e33261cba7cbc7f07b3b32e44290fd213cd137040ba583a08733ca6ac4752ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SERSJ3VV7EXGB7DJRQDSDMNA32/bundle.json","state_url":"https://pith.science/pith/SERSJ3VV7EXGB7DJRQDSDMNA32/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SERSJ3VV7EXGB7DJRQDSDMNA32/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":"2026-06-03T08:04:02Z","links":{"resolver":"https://pith.science/pith/SERSJ3VV7EXGB7DJRQDSDMNA32","bundle":"https://pith.science/pith/SERSJ3VV7EXGB7DJRQDSDMNA32/bundle.json","state":"https://pith.science/pith/SERSJ3VV7EXGB7DJRQDSDMNA32/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SERSJ3VV7EXGB7DJRQDSDMNA32/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:SERSJ3VV7EXGB7DJRQDSDMNA32","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":"49a4dd6807a50cc76696d0a0f153980e6c9d13c564ae1633655ae22a64b4d34d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-24T20:59:50Z","title_canon_sha256":"bcd0a8a9585394e4d44df56b0bdbe5422b88962198e313ee26f9c9ca1353e8e6"},"schema_version":"1.0","source":{"id":"1703.08595","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.08595","created_at":"2026-05-18T00:47:56Z"},{"alias_kind":"arxiv_version","alias_value":"1703.08595v1","created_at":"2026-05-18T00:47:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.08595","created_at":"2026-05-18T00:47:56Z"},{"alias_kind":"pith_short_12","alias_value":"SERSJ3VV7EXG","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"SERSJ3VV7EXGB7DJ","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"SERSJ3VV","created_at":"2026-05-18T12:31:43Z"}],"graph_snapshots":[{"event_id":"sha256:0e33261cba7cbc7f07b3b32e44290fd213cd137040ba583a08733ca6ac4752ec","target":"graph","created_at":"2026-05-18T00:47:56Z","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":"Large-scale deep neural networks (DNN) have been successfully used in a number of tasks from image recognition to natural language processing. They are trained using large training sets on large models, making them computationally and memory intensive. As such, there is much interest in research development for faster training and test time. In this paper, we present a unique approach using lower precision weights for more efficient and faster training phase. We separate imagery into different frequency bands (e.g. with different information content) such that the neural net can better learn u","authors_text":"Aswin Raghavan, David Zhang, Mohamed Amer, Sek Chai, Tim Shields","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-24T20:59:50Z","title":"Low Precision Neural Networks using Subband Decomposition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.08595","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:d30ff8961b85998cf3d2ab7fb13a1038392a993739537e88ef2407057a5c64d9","target":"record","created_at":"2026-05-18T00:47:56Z","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":"49a4dd6807a50cc76696d0a0f153980e6c9d13c564ae1633655ae22a64b4d34d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-24T20:59:50Z","title_canon_sha256":"bcd0a8a9585394e4d44df56b0bdbe5422b88962198e313ee26f9c9ca1353e8e6"},"schema_version":"1.0","source":{"id":"1703.08595","kind":"arxiv","version":1}},"canonical_sha256":"912324eeb5f92e60fc698c0721b1a0de9f7cf61d1468798ca41c5bf73bf8393e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"912324eeb5f92e60fc698c0721b1a0de9f7cf61d1468798ca41c5bf73bf8393e","first_computed_at":"2026-05-18T00:47:56.070990Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:47:56.070990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wX1udJRWZ2s3W+l1dH6e6nM5EgvjZMnmHMKH0uEfMRo89buryxLCL3AHwyD7POdSGhk/V0OkF96nKK0joQtSBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:47:56.071530Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.08595","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d30ff8961b85998cf3d2ab7fb13a1038392a993739537e88ef2407057a5c64d9","sha256:0e33261cba7cbc7f07b3b32e44290fd213cd137040ba583a08733ca6ac4752ec"],"state_sha256":"3289377e6b49d09fc829507346f9b973cdd364ea9d42019521af720359e2c410"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yZYjaqlgxyTNuEignXf0IMvZUutqMQ2q0TQuY0KHmrihlniJlhU6HbL8WpY6ka60GATAjXDj5hl0i06h3bCcBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T08:04:02.867898Z","bundle_sha256":"173f5859f8928a10e6282df291f152b874f1f6282b0bf97e6e2d4138aa98f41a"}}