{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:PAXZXUXY7EQMFNCV4LTZ3R4WX2","short_pith_number":"pith:PAXZXUXY","canonical_record":{"source":{"id":"1807.07948","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-20T17:36:05Z","cross_cats_sorted":[],"title_canon_sha256":"2e1af0e95d520a43f52344d7fff87f9a2b36b005e6925431ae1666b280a0e748","abstract_canon_sha256":"5dfe9710bb92a890b23bbfa1125e7628b9e2ee76ed2a0e993f41f8db2b629774"},"schema_version":"1.0"},"canonical_sha256":"782f9bd2f8f920c2b455e2e79dc796be977b37549837821b12f4c97fdd99e981","source":{"kind":"arxiv","id":"1807.07948","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.07948","created_at":"2026-05-18T00:10:14Z"},{"alias_kind":"arxiv_version","alias_value":"1807.07948v1","created_at":"2026-05-18T00:10:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.07948","created_at":"2026-05-18T00:10:14Z"},{"alias_kind":"pith_short_12","alias_value":"PAXZXUXY7EQM","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"PAXZXUXY7EQMFNCV","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"PAXZXUXY","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:PAXZXUXY7EQMFNCV4LTZ3R4WX2","target":"record","payload":{"canonical_record":{"source":{"id":"1807.07948","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-20T17:36:05Z","cross_cats_sorted":[],"title_canon_sha256":"2e1af0e95d520a43f52344d7fff87f9a2b36b005e6925431ae1666b280a0e748","abstract_canon_sha256":"5dfe9710bb92a890b23bbfa1125e7628b9e2ee76ed2a0e993f41f8db2b629774"},"schema_version":"1.0"},"canonical_sha256":"782f9bd2f8f920c2b455e2e79dc796be977b37549837821b12f4c97fdd99e981","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:14.868519Z","signature_b64":"nk3iuYCmrunyHRfaK3gnBaMtdGNjLA1zVYwW27U5wKlLrL2IF39mpENHUR28EGvVt30KZL2zWzoZcbofEleEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"782f9bd2f8f920c2b455e2e79dc796be977b37549837821b12f4c97fdd99e981","last_reissued_at":"2026-05-18T00:10:14.867643Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:14.867643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.07948","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":"2026-05-18T00:10:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zUCN3D+r20RUbIj2Gu/HA3qn9osYzULkbaGhp419CUN7qqaRJ6SoNYVUrBXvnn4ysprAu8hnePBhCDgzOUOsAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:01:57.750084Z"},"content_sha256":"cca57663e7f1714ec25691f1c898e72d7e4e2075ad7a268de22dbcd55c8233f4","schema_version":"1.0","event_id":"sha256:cca57663e7f1714ec25691f1c898e72d7e4e2075ad7a268de22dbcd55c8233f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:PAXZXUXY7EQMFNCV4LTZ3R4WX2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimize Deep Convolutional Neural Network with Ternarized Weights and High Accuracy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boqing Gong, Deliang Fan, Zhezhi He","submitted_at":"2018-07-20T17:36:05Z","abstract_excerpt":"Deep convolution neural network has achieved great success in many artificial intelligence applications. However, its enormous model size and massive computation cost have become the main obstacle for deployment of such powerful algorithm in the low power and resource-limited embedded systems. As the countermeasure to this problem, in this work, we propose statistical weight scaling and residual expansion methods to reduce the bit-width of the whole network weight parameters to ternary values (i.e. -1, 0, +1), with the objectives to greatly reduce model size, computation cost and accuracy degr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.07948","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":"2026-05-18T00:10:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/gxJjAakKQaEovgkaFS9eo5U4IBrLGwD7EuYMDeWOMS30vXaoiBu+LrtF6n5+dugdQTmh0IkdPUZA3bvAT/iBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:01:57.750790Z"},"content_sha256":"11594ff52a43178cfe906c7204db48455c61ca121742ec1958f3e030ed9cf913","schema_version":"1.0","event_id":"sha256:11594ff52a43178cfe906c7204db48455c61ca121742ec1958f3e030ed9cf913"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PAXZXUXY7EQMFNCV4LTZ3R4WX2/bundle.json","state_url":"https://pith.science/pith/PAXZXUXY7EQMFNCV4LTZ3R4WX2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PAXZXUXY7EQMFNCV4LTZ3R4WX2/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":"2026-05-25T17:01:57Z","links":{"resolver":"https://pith.science/pith/PAXZXUXY7EQMFNCV4LTZ3R4WX2","bundle":"https://pith.science/pith/PAXZXUXY7EQMFNCV4LTZ3R4WX2/bundle.json","state":"https://pith.science/pith/PAXZXUXY7EQMFNCV4LTZ3R4WX2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PAXZXUXY7EQMFNCV4LTZ3R4WX2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:PAXZXUXY7EQMFNCV4LTZ3R4WX2","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":"5dfe9710bb92a890b23bbfa1125e7628b9e2ee76ed2a0e993f41f8db2b629774","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-20T17:36:05Z","title_canon_sha256":"2e1af0e95d520a43f52344d7fff87f9a2b36b005e6925431ae1666b280a0e748"},"schema_version":"1.0","source":{"id":"1807.07948","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.07948","created_at":"2026-05-18T00:10:14Z"},{"alias_kind":"arxiv_version","alias_value":"1807.07948v1","created_at":"2026-05-18T00:10:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.07948","created_at":"2026-05-18T00:10:14Z"},{"alias_kind":"pith_short_12","alias_value":"PAXZXUXY7EQM","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"PAXZXUXY7EQMFNCV","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"PAXZXUXY","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:11594ff52a43178cfe906c7204db48455c61ca121742ec1958f3e030ed9cf913","target":"graph","created_at":"2026-05-18T00:10:14Z","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"},"paper":{"abstract_excerpt":"Deep convolution neural network has achieved great success in many artificial intelligence applications. However, its enormous model size and massive computation cost have become the main obstacle for deployment of such powerful algorithm in the low power and resource-limited embedded systems. As the countermeasure to this problem, in this work, we propose statistical weight scaling and residual expansion methods to reduce the bit-width of the whole network weight parameters to ternary values (i.e. -1, 0, +1), with the objectives to greatly reduce model size, computation cost and accuracy degr","authors_text":"Boqing Gong, Deliang Fan, Zhezhi He","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-20T17:36:05Z","title":"Optimize Deep Convolutional Neural Network with Ternarized Weights and High Accuracy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.07948","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:cca57663e7f1714ec25691f1c898e72d7e4e2075ad7a268de22dbcd55c8233f4","target":"record","created_at":"2026-05-18T00:10:14Z","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":"5dfe9710bb92a890b23bbfa1125e7628b9e2ee76ed2a0e993f41f8db2b629774","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-20T17:36:05Z","title_canon_sha256":"2e1af0e95d520a43f52344d7fff87f9a2b36b005e6925431ae1666b280a0e748"},"schema_version":"1.0","source":{"id":"1807.07948","kind":"arxiv","version":1}},"canonical_sha256":"782f9bd2f8f920c2b455e2e79dc796be977b37549837821b12f4c97fdd99e981","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"782f9bd2f8f920c2b455e2e79dc796be977b37549837821b12f4c97fdd99e981","first_computed_at":"2026-05-18T00:10:14.867643Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:10:14.867643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nk3iuYCmrunyHRfaK3gnBaMtdGNjLA1zVYwW27U5wKlLrL2IF39mpENHUR28EGvVt30KZL2zWzoZcbofEleEBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:10:14.868519Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.07948","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cca57663e7f1714ec25691f1c898e72d7e4e2075ad7a268de22dbcd55c8233f4","sha256:11594ff52a43178cfe906c7204db48455c61ca121742ec1958f3e030ed9cf913"],"state_sha256":"c3a8b8527b00e3c6ea50729ac1f16b31da0e14fe60593d0bf4ef6b108695adac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kp3M5nBx3mvVNwuCIpfmwdukWU82tBVy3W3ge8X/zyzV/bKvqZsrhvMQ7HlOexJf8FHaMk0GbhkvN/3pqndMCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T17:01:57.754630Z","bundle_sha256":"aea435769397f2f67a32af30239306060492bcda836abbf490ba535270070fb3"}}