{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:INLECC22GKSR3VLGLSV3BGQ3YM","short_pith_number":"pith:INLECC22","canonical_record":{"source":{"id":"1612.01064","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-04T05:00:22Z","cross_cats_sorted":[],"title_canon_sha256":"9011337601eb7480e6fe6a2c4daca3bdfda037b551f8b1d2c0c067ca568d0acd","abstract_canon_sha256":"2ff66f9cae73d70a75b74648b22b9c1f10aa75440ad42ce1f827c29c618f14a1"},"schema_version":"1.0"},"canonical_sha256":"4356410b5a32a51dd5665cabb09a1bc3143007a1d8533d7171796a589eaff9e0","source":{"kind":"arxiv","id":"1612.01064","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.01064","created_at":"2026-05-18T00:50:09Z"},{"alias_kind":"arxiv_version","alias_value":"1612.01064v3","created_at":"2026-05-18T00:50:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.01064","created_at":"2026-05-18T00:50:09Z"},{"alias_kind":"pith_short_12","alias_value":"INLECC22GKSR","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_16","alias_value":"INLECC22GKSR3VLG","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_8","alias_value":"INLECC22","created_at":"2026-05-18T12:30:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:INLECC22GKSR3VLGLSV3BGQ3YM","target":"record","payload":{"canonical_record":{"source":{"id":"1612.01064","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-04T05:00:22Z","cross_cats_sorted":[],"title_canon_sha256":"9011337601eb7480e6fe6a2c4daca3bdfda037b551f8b1d2c0c067ca568d0acd","abstract_canon_sha256":"2ff66f9cae73d70a75b74648b22b9c1f10aa75440ad42ce1f827c29c618f14a1"},"schema_version":"1.0"},"canonical_sha256":"4356410b5a32a51dd5665cabb09a1bc3143007a1d8533d7171796a589eaff9e0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:09.172916Z","signature_b64":"07izwy+BYM7KpAX1W3xBnuvf2Xb9zBPNroAnBhzNYckND0dx0VDJHXhdSvt9h1ul5udPENBnWx9lnzTayWBzBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4356410b5a32a51dd5665cabb09a1bc3143007a1d8533d7171796a589eaff9e0","last_reissued_at":"2026-05-18T00:50:09.172302Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:09.172302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1612.01064","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:50:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MfOIrVkHJyaeHt3Zv541wj27Kgz3oZRVwxTCJ+stXVO2als8+vpW8WaP7TU65n0AwofTNSZg8JWZCjq8ozn5AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T11:59:36.336712Z"},"content_sha256":"e40ad60e37054f0f569bf869799a13ea42808815a83f4dfb2051a9283fb34212","schema_version":"1.0","event_id":"sha256:e40ad60e37054f0f569bf869799a13ea42808815a83f4dfb2051a9283fb34212"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:INLECC22GKSR3VLGLSV3BGQ3YM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Trained Ternary Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenzhuo Zhu, Huizi Mao, Song Han, William J. Dally","submitted_at":"2016-12-04T05:00:22Z","abstract_excerpt":"Deep neural networks are widely used in machine learning applications. However, the deployment of large neural networks models can be difficult to deploy on mobile devices with limited power budgets. To solve this problem, we propose Trained Ternary Quantization (TTQ), a method that can reduce the precision of weights in neural networks to ternary values. This method has very little accuracy degradation and can even improve the accuracy of some models (32, 44, 56-layer ResNet) on CIFAR-10 and AlexNet on ImageNet. And our AlexNet model is trained from scratch, which means it's as easy as to tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.01064","kind":"arxiv","version":3},"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":"2026-05-18T00:50:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XrN/4BjEhd5cINEfjNUBm1N+JJuw7lldPfGXflS9XMZJMMiCPSG9VSriB6iuPIOF4PSMTovwrW7n6kP2B2xMCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T11:59:36.337296Z"},"content_sha256":"2be6bd3f3990a0454acd2305fd469dbe8d2f1f9f1b56b69581687faaf370077f","schema_version":"1.0","event_id":"sha256:2be6bd3f3990a0454acd2305fd469dbe8d2f1f9f1b56b69581687faaf370077f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/INLECC22GKSR3VLGLSV3BGQ3YM/bundle.json","state_url":"https://pith.science/pith/INLECC22GKSR3VLGLSV3BGQ3YM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/INLECC22GKSR3VLGLSV3BGQ3YM/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":"2026-05-26T11:59:36Z","links":{"resolver":"https://pith.science/pith/INLECC22GKSR3VLGLSV3BGQ3YM","bundle":"https://pith.science/pith/INLECC22GKSR3VLGLSV3BGQ3YM/bundle.json","state":"https://pith.science/pith/INLECC22GKSR3VLGLSV3BGQ3YM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/INLECC22GKSR3VLGLSV3BGQ3YM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:INLECC22GKSR3VLGLSV3BGQ3YM","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":"2ff66f9cae73d70a75b74648b22b9c1f10aa75440ad42ce1f827c29c618f14a1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-04T05:00:22Z","title_canon_sha256":"9011337601eb7480e6fe6a2c4daca3bdfda037b551f8b1d2c0c067ca568d0acd"},"schema_version":"1.0","source":{"id":"1612.01064","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.01064","created_at":"2026-05-18T00:50:09Z"},{"alias_kind":"arxiv_version","alias_value":"1612.01064v3","created_at":"2026-05-18T00:50:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.01064","created_at":"2026-05-18T00:50:09Z"},{"alias_kind":"pith_short_12","alias_value":"INLECC22GKSR","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_16","alias_value":"INLECC22GKSR3VLG","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_8","alias_value":"INLECC22","created_at":"2026-05-18T12:30:22Z"}],"graph_snapshots":[{"event_id":"sha256:2be6bd3f3990a0454acd2305fd469dbe8d2f1f9f1b56b69581687faaf370077f","target":"graph","created_at":"2026-05-18T00:50:09Z","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 neural networks are widely used in machine learning applications. However, the deployment of large neural networks models can be difficult to deploy on mobile devices with limited power budgets. To solve this problem, we propose Trained Ternary Quantization (TTQ), a method that can reduce the precision of weights in neural networks to ternary values. This method has very little accuracy degradation and can even improve the accuracy of some models (32, 44, 56-layer ResNet) on CIFAR-10 and AlexNet on ImageNet. And our AlexNet model is trained from scratch, which means it's as easy as to tra","authors_text":"Chenzhuo Zhu, Huizi Mao, Song Han, William J. Dally","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-04T05:00:22Z","title":"Trained Ternary Quantization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.01064","kind":"arxiv","version":3},"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:e40ad60e37054f0f569bf869799a13ea42808815a83f4dfb2051a9283fb34212","target":"record","created_at":"2026-05-18T00:50:09Z","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":"2ff66f9cae73d70a75b74648b22b9c1f10aa75440ad42ce1f827c29c618f14a1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-04T05:00:22Z","title_canon_sha256":"9011337601eb7480e6fe6a2c4daca3bdfda037b551f8b1d2c0c067ca568d0acd"},"schema_version":"1.0","source":{"id":"1612.01064","kind":"arxiv","version":3}},"canonical_sha256":"4356410b5a32a51dd5665cabb09a1bc3143007a1d8533d7171796a589eaff9e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4356410b5a32a51dd5665cabb09a1bc3143007a1d8533d7171796a589eaff9e0","first_computed_at":"2026-05-18T00:50:09.172302Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:50:09.172302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"07izwy+BYM7KpAX1W3xBnuvf2Xb9zBPNroAnBhzNYckND0dx0VDJHXhdSvt9h1ul5udPENBnWx9lnzTayWBzBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:50:09.172916Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.01064","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e40ad60e37054f0f569bf869799a13ea42808815a83f4dfb2051a9283fb34212","sha256:2be6bd3f3990a0454acd2305fd469dbe8d2f1f9f1b56b69581687faaf370077f"],"state_sha256":"84b6d3186dfe283fea39e7674b5ea0d8fc045a38e51ca5f4ffd0c9525f1c592e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XUT7RZ1c+mk5QS0oLWp2taifiX0KedC7zrgNQd4vyJZ9SZJkC3V7ZZydxlK0RjLvCkLbuj6aVzDOozkx2xoAAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T11:59:36.340731Z","bundle_sha256":"1972221dc48192fab798f724f5ffece5239464a59dd2a6eca56a7a6f9e1124f7"}}