{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:4ZVFJZM2CJSC7IPS3DFMDRFPCO","short_pith_number":"pith:4ZVFJZM2","canonical_record":{"source":{"id":"1809.04191","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-11T22:51:55Z","cross_cats_sorted":[],"title_canon_sha256":"410da4a31f72d0ccc3df20c5689eec18ed2d399193c15b4522e4864fffb28363","abstract_canon_sha256":"537867610590c288031a68e017f7f01e06b1564e0040908a01771e203ba1bde7"},"schema_version":"1.0"},"canonical_sha256":"e66a54e59a12642fa1f2d8cac1c4af13bd86a7ce13ce82c550354367dcad08e2","source":{"kind":"arxiv","id":"1809.04191","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.04191","created_at":"2026-05-17T23:52:52Z"},{"alias_kind":"arxiv_version","alias_value":"1809.04191v2","created_at":"2026-05-17T23:52:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04191","created_at":"2026-05-17T23:52:52Z"},{"alias_kind":"pith_short_12","alias_value":"4ZVFJZM2CJSC","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4ZVFJZM2CJSC7IPS","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4ZVFJZM2","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:4ZVFJZM2CJSC7IPS3DFMDRFPCO","target":"record","payload":{"canonical_record":{"source":{"id":"1809.04191","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-11T22:51:55Z","cross_cats_sorted":[],"title_canon_sha256":"410da4a31f72d0ccc3df20c5689eec18ed2d399193c15b4522e4864fffb28363","abstract_canon_sha256":"537867610590c288031a68e017f7f01e06b1564e0040908a01771e203ba1bde7"},"schema_version":"1.0"},"canonical_sha256":"e66a54e59a12642fa1f2d8cac1c4af13bd86a7ce13ce82c550354367dcad08e2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:52.277191Z","signature_b64":"SQzR29cLbjQdwCQP1o47NlNrWrtDO9JjdSugvhUNANCE4OTRpRpXrCjatWAap82A3FcxagBp2o3qefaNSZagCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e66a54e59a12642fa1f2d8cac1c4af13bd86a7ce13ce82c550354367dcad08e2","last_reissued_at":"2026-05-17T23:52:52.276507Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:52.276507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.04191","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:52:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DO3nB8FtgfkK7UuH5lM4mvzKNt2yMU935IwRgH+O2cYTCdjAfNLWk0cskKDqkqQMtDdm33tYwgFjjYPNHQBnDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:56:23.878456Z"},"content_sha256":"a5b6fdb46494957e6c9d0b7d2728469588bb06231afca4e441404ef1f2577609","schema_version":"1.0","event_id":"sha256:a5b6fdb46494957e6c9d0b7d2728469588bb06231afca4e441404ef1f2577609"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:4ZVFJZM2CJSC7IPS3DFMDRFPCO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Discovering Low-Precision Networks Close to Full-Precision Networks for Efficient Embedded Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deepika Bablani, Dharmendra S. Modha, Izzet B. Yildiz, Jeffrey L. McKinstry, John V. Arthur, Rathinakumar Appuswamy, Steven K. Esser","submitted_at":"2018-09-11T22:51:55Z","abstract_excerpt":"To realize the promise of ubiquitous embedded deep network inference, it is essential to seek limits of energy and area efficiency. To this end, low-precision networks offer tremendous promise because both energy and area scale down quadratically with the reduction in precision. Here we demonstrate ResNet-18, -34, -50, -152, Inception-v3, Densenet-161, and VGG-16bn networks on the ImageNet classification benchmark that, at 8-bit precision exceed the accuracy of the full-precision baseline networks after one epoch of finetuning, thereby leveraging the availability of pretrained models. We also "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04191","kind":"arxiv","version":2},"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":"2026-05-17T23:52:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w6ohFcD8A8kNMQlSFz4i1ZUF3KdFbIvXkp/ymvFXXxDBkIgMA2DN3NkUaRFLEy2PRxzWOVKXW4ENyuCB3hdTCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:56:23.878826Z"},"content_sha256":"21282a5211af9a05d2bae3b48ba300464103dec02680a46de65db990d9a179fe","schema_version":"1.0","event_id":"sha256:21282a5211af9a05d2bae3b48ba300464103dec02680a46de65db990d9a179fe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4ZVFJZM2CJSC7IPS3DFMDRFPCO/bundle.json","state_url":"https://pith.science/pith/4ZVFJZM2CJSC7IPS3DFMDRFPCO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4ZVFJZM2CJSC7IPS3DFMDRFPCO/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":"2026-05-25T17:56:23Z","links":{"resolver":"https://pith.science/pith/4ZVFJZM2CJSC7IPS3DFMDRFPCO","bundle":"https://pith.science/pith/4ZVFJZM2CJSC7IPS3DFMDRFPCO/bundle.json","state":"https://pith.science/pith/4ZVFJZM2CJSC7IPS3DFMDRFPCO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4ZVFJZM2CJSC7IPS3DFMDRFPCO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:4ZVFJZM2CJSC7IPS3DFMDRFPCO","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":"537867610590c288031a68e017f7f01e06b1564e0040908a01771e203ba1bde7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-11T22:51:55Z","title_canon_sha256":"410da4a31f72d0ccc3df20c5689eec18ed2d399193c15b4522e4864fffb28363"},"schema_version":"1.0","source":{"id":"1809.04191","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.04191","created_at":"2026-05-17T23:52:52Z"},{"alias_kind":"arxiv_version","alias_value":"1809.04191v2","created_at":"2026-05-17T23:52:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04191","created_at":"2026-05-17T23:52:52Z"},{"alias_kind":"pith_short_12","alias_value":"4ZVFJZM2CJSC","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4ZVFJZM2CJSC7IPS","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4ZVFJZM2","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:21282a5211af9a05d2bae3b48ba300464103dec02680a46de65db990d9a179fe","target":"graph","created_at":"2026-05-17T23:52:52Z","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":"To realize the promise of ubiquitous embedded deep network inference, it is essential to seek limits of energy and area efficiency. To this end, low-precision networks offer tremendous promise because both energy and area scale down quadratically with the reduction in precision. Here we demonstrate ResNet-18, -34, -50, -152, Inception-v3, Densenet-161, and VGG-16bn networks on the ImageNet classification benchmark that, at 8-bit precision exceed the accuracy of the full-precision baseline networks after one epoch of finetuning, thereby leveraging the availability of pretrained models. We also ","authors_text":"Deepika Bablani, Dharmendra S. Modha, Izzet B. Yildiz, Jeffrey L. McKinstry, John V. Arthur, Rathinakumar Appuswamy, Steven K. Esser","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-11T22:51:55Z","title":"Discovering Low-Precision Networks Close to Full-Precision Networks for Efficient Embedded Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04191","kind":"arxiv","version":2},"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:a5b6fdb46494957e6c9d0b7d2728469588bb06231afca4e441404ef1f2577609","target":"record","created_at":"2026-05-17T23:52:52Z","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":"537867610590c288031a68e017f7f01e06b1564e0040908a01771e203ba1bde7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-11T22:51:55Z","title_canon_sha256":"410da4a31f72d0ccc3df20c5689eec18ed2d399193c15b4522e4864fffb28363"},"schema_version":"1.0","source":{"id":"1809.04191","kind":"arxiv","version":2}},"canonical_sha256":"e66a54e59a12642fa1f2d8cac1c4af13bd86a7ce13ce82c550354367dcad08e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e66a54e59a12642fa1f2d8cac1c4af13bd86a7ce13ce82c550354367dcad08e2","first_computed_at":"2026-05-17T23:52:52.276507Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:52.276507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SQzR29cLbjQdwCQP1o47NlNrWrtDO9JjdSugvhUNANCE4OTRpRpXrCjatWAap82A3FcxagBp2o3qefaNSZagCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:52.277191Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.04191","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5b6fdb46494957e6c9d0b7d2728469588bb06231afca4e441404ef1f2577609","sha256:21282a5211af9a05d2bae3b48ba300464103dec02680a46de65db990d9a179fe"],"state_sha256":"fa75ec1ad63eb83657110643122ab37237ae6e8d8688120721184655446b246a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7zIie8qkCn1QKR2/Q9F0bmof0K4zOWwvGbhvUqrX4kagqZ2n3E+jXeS3sV4P2JwvnwqQMHpSp+tF7qTuYWNRCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T17:56:23.881330Z","bundle_sha256":"302407517f2df8a53bd58778128d92c24ea6016d63acf265a6d9ac438f235bf3"}}