{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:N4V4Z45K3QC34FHXDSAW3RYNSP","short_pith_number":"pith:N4V4Z45K","canonical_record":{"source":{"id":"1802.08530","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-23T13:54:23Z","cross_cats_sorted":["cs.CV","cs.NE","stat.ML"],"title_canon_sha256":"372717172f3da79bd0e4c75204cb76bf0d4817182b06f82ac0fe6353e9f5c7ff","abstract_canon_sha256":"75ef439722809b182a249be24cb511677074e187a2e2d3f20f665fdb9c849e38"},"schema_version":"1.0"},"canonical_sha256":"6f2bccf3aadc05be14f71c816dc70d93ea1d68b2b26d8547f3e2a3680e53185b","source":{"kind":"arxiv","id":"1802.08530","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.08530","created_at":"2026-05-18T00:22:36Z"},{"alias_kind":"arxiv_version","alias_value":"1802.08530v1","created_at":"2026-05-18T00:22:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.08530","created_at":"2026-05-18T00:22:36Z"},{"alias_kind":"pith_short_12","alias_value":"N4V4Z45K3QC3","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"N4V4Z45K3QC34FHX","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"N4V4Z45K","created_at":"2026-05-18T12:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:N4V4Z45K3QC34FHXDSAW3RYNSP","target":"record","payload":{"canonical_record":{"source":{"id":"1802.08530","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-23T13:54:23Z","cross_cats_sorted":["cs.CV","cs.NE","stat.ML"],"title_canon_sha256":"372717172f3da79bd0e4c75204cb76bf0d4817182b06f82ac0fe6353e9f5c7ff","abstract_canon_sha256":"75ef439722809b182a249be24cb511677074e187a2e2d3f20f665fdb9c849e38"},"schema_version":"1.0"},"canonical_sha256":"6f2bccf3aadc05be14f71c816dc70d93ea1d68b2b26d8547f3e2a3680e53185b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:36.753713Z","signature_b64":"7pWzMFC7M2D4yfpnTFiH1Im2eRlyk2K9oHWzWcEPRHcz+9bctmnikT+bUAlHzAf8ToEbNU2f2h3TVtZFdOmvCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f2bccf3aadc05be14f71c816dc70d93ea1d68b2b26d8547f3e2a3680e53185b","last_reissued_at":"2026-05-18T00:22:36.753129Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:36.753129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.08530","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":"2026-05-18T00:22:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vQ8mMggmoxwpt1+RdvbsJaklQsNyZKsMNFfN4B33kzLHqHmfxrNP1YNN1qAXj5NcP4DbUK18vmSwN/hd6MLbCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T09:07:17.054052Z"},"content_sha256":"614801938ef12a634a63fca0fced9936fbf7d602e39293f03b2eafcc7fc81ec8","schema_version":"1.0","event_id":"sha256:614801938ef12a634a63fca0fced9936fbf7d602e39293f03b2eafcc7fc81ec8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:N4V4Z45K3QC34FHXDSAW3RYNSP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training wide residual networks for deployment using a single bit for each weight","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mark D. McDonnell","submitted_at":"2018-02-23T13:54:23Z","abstract_excerpt":"For fast and energy-efficient deployment of trained deep neural networks on resource-constrained embedded hardware, each learned weight parameter should ideally be represented and stored using a single bit. Error-rates usually increase when this requirement is imposed. Here, we report large improvements in error rates on multiple datasets, for deep convolutional neural networks deployed with 1-bit-per-weight. Using wide residual networks as our main baseline, our approach simplifies existing methods that binarize weights by applying the sign function in training; we apply scaling factors for e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.08530","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":"2026-05-18T00:22:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GL0JiGtpvDZhvKl1oY/tzUOK285wc+gi0us2QgiczOVkX7vRGWRz8zUzohrfYpU+YxnRw2mLn7N66XVYzOaYAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T09:07:17.054444Z"},"content_sha256":"5f25fa67ec34ed2279bc27cf2071f0004ac546605ac75f29a62a4b739684aaef","schema_version":"1.0","event_id":"sha256:5f25fa67ec34ed2279bc27cf2071f0004ac546605ac75f29a62a4b739684aaef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N4V4Z45K3QC34FHXDSAW3RYNSP/bundle.json","state_url":"https://pith.science/pith/N4V4Z45K3QC34FHXDSAW3RYNSP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N4V4Z45K3QC34FHXDSAW3RYNSP/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":"2026-05-28T09:07:17Z","links":{"resolver":"https://pith.science/pith/N4V4Z45K3QC34FHXDSAW3RYNSP","bundle":"https://pith.science/pith/N4V4Z45K3QC34FHXDSAW3RYNSP/bundle.json","state":"https://pith.science/pith/N4V4Z45K3QC34FHXDSAW3RYNSP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N4V4Z45K3QC34FHXDSAW3RYNSP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:N4V4Z45K3QC34FHXDSAW3RYNSP","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":"75ef439722809b182a249be24cb511677074e187a2e2d3f20f665fdb9c849e38","cross_cats_sorted":["cs.CV","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-23T13:54:23Z","title_canon_sha256":"372717172f3da79bd0e4c75204cb76bf0d4817182b06f82ac0fe6353e9f5c7ff"},"schema_version":"1.0","source":{"id":"1802.08530","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.08530","created_at":"2026-05-18T00:22:36Z"},{"alias_kind":"arxiv_version","alias_value":"1802.08530v1","created_at":"2026-05-18T00:22:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.08530","created_at":"2026-05-18T00:22:36Z"},{"alias_kind":"pith_short_12","alias_value":"N4V4Z45K3QC3","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"N4V4Z45K3QC34FHX","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"N4V4Z45K","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:5f25fa67ec34ed2279bc27cf2071f0004ac546605ac75f29a62a4b739684aaef","target":"graph","created_at":"2026-05-18T00:22:36Z","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":"For fast and energy-efficient deployment of trained deep neural networks on resource-constrained embedded hardware, each learned weight parameter should ideally be represented and stored using a single bit. Error-rates usually increase when this requirement is imposed. Here, we report large improvements in error rates on multiple datasets, for deep convolutional neural networks deployed with 1-bit-per-weight. Using wide residual networks as our main baseline, our approach simplifies existing methods that binarize weights by applying the sign function in training; we apply scaling factors for e","authors_text":"Mark D. McDonnell","cross_cats":["cs.CV","cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-23T13:54:23Z","title":"Training wide residual networks for deployment using a single bit for each weight"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.08530","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":"sha256:614801938ef12a634a63fca0fced9936fbf7d602e39293f03b2eafcc7fc81ec8","target":"record","created_at":"2026-05-18T00:22:36Z","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":"75ef439722809b182a249be24cb511677074e187a2e2d3f20f665fdb9c849e38","cross_cats_sorted":["cs.CV","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-23T13:54:23Z","title_canon_sha256":"372717172f3da79bd0e4c75204cb76bf0d4817182b06f82ac0fe6353e9f5c7ff"},"schema_version":"1.0","source":{"id":"1802.08530","kind":"arxiv","version":1}},"canonical_sha256":"6f2bccf3aadc05be14f71c816dc70d93ea1d68b2b26d8547f3e2a3680e53185b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f2bccf3aadc05be14f71c816dc70d93ea1d68b2b26d8547f3e2a3680e53185b","first_computed_at":"2026-05-18T00:22:36.753129Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:36.753129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7pWzMFC7M2D4yfpnTFiH1Im2eRlyk2K9oHWzWcEPRHcz+9bctmnikT+bUAlHzAf8ToEbNU2f2h3TVtZFdOmvCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:36.753713Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.08530","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:614801938ef12a634a63fca0fced9936fbf7d602e39293f03b2eafcc7fc81ec8","sha256:5f25fa67ec34ed2279bc27cf2071f0004ac546605ac75f29a62a4b739684aaef"],"state_sha256":"ee69008a5919dbf451cba006e01de9b0d1e180e5b6ca2a89bb2f3333113ce3ef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AdKJ8x5UTKwBkaH/WTYN57Kw7Bv4+EzwaxHxfFoBowdC2lESX6Qykfg1IJnbmSjbi5omNqEMl7hh7tTrupKyDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T09:07:17.056584Z","bundle_sha256":"fd319d014fd8a7b2102fb8e5f05d794c83d70cd36c41f0bfab6e19ed8c0cb152"}}