{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:SXMJKKYOAM5ZO2ZLCAGWWAZQWU","short_pith_number":"pith:SXMJKKYO","canonical_record":{"source":{"id":"1908.04680","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-08-10T11:48:55Z","cross_cats_sorted":[],"title_canon_sha256":"162d0a54505f4ff7f0f347159c6b135a36647e40fbb1d0356b303052da307645","abstract_canon_sha256":"cbfd25ceb5cbbc03e5ec446bcaef9bfe6955e9c9865728efbd8e6ee5e6046376"},"schema_version":"1.0"},"canonical_sha256":"95d8952b0e033b976b2b100d6b0330b50ae14c43067ac47a87c9c0ce10046d2d","source":{"kind":"arxiv","id":"1908.04680","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.04680","created_at":"2026-07-05T02:46:07Z"},{"alias_kind":"arxiv_version","alias_value":"1908.04680v3","created_at":"2026-07-05T02:46:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04680","created_at":"2026-07-05T02:46:07Z"},{"alias_kind":"pith_short_12","alias_value":"SXMJKKYOAM5Z","created_at":"2026-07-05T02:46:07Z"},{"alias_kind":"pith_short_16","alias_value":"SXMJKKYOAM5ZO2ZL","created_at":"2026-07-05T02:46:07Z"},{"alias_kind":"pith_short_8","alias_value":"SXMJKKYO","created_at":"2026-07-05T02:46:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:SXMJKKYOAM5ZO2ZLCAGWWAZQWU","target":"record","payload":{"canonical_record":{"source":{"id":"1908.04680","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-08-10T11:48:55Z","cross_cats_sorted":[],"title_canon_sha256":"162d0a54505f4ff7f0f347159c6b135a36647e40fbb1d0356b303052da307645","abstract_canon_sha256":"cbfd25ceb5cbbc03e5ec446bcaef9bfe6955e9c9865728efbd8e6ee5e6046376"},"schema_version":"1.0"},"canonical_sha256":"95d8952b0e033b976b2b100d6b0330b50ae14c43067ac47a87c9c0ce10046d2d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:07.661475Z","signature_b64":"40jmp2QbhAuo3RfwlUSmK+FEHy9NxLwUSuDaZMSjci4lbk9PatDi211ekUmV10mmKJcvMV39TLfOh/rirSpTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95d8952b0e033b976b2b100d6b0330b50ae14c43067ac47a87c9c0ce10046d2d","last_reissued_at":"2026-07-05T02:46:07.660950Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:07.660950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.04680","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":"2026-07-05T02:46:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1jeMGHZcM+4ks2ynxad1dx2u/aCLHpO09GxXmZLfYOHgSHrTc693lt25BU7xZmrs9QPinBGokeSFJrunQZLHDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:51:47.407525Z"},"content_sha256":"e489699ae18e3462fe4b06d74d94c61463ae226c480c86e79e5bc66bd97244da","schema_version":"1.0","event_id":"sha256:e489699ae18e3462fe4b06d74d94c61463ae226c480c86e79e5bc66bd97244da"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:SXMJKKYOAM5ZO2ZLCAGWWAZQWU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Effective Training of Convolutional Neural Networks with Low-bitwidth Weights and Activations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohan Zhuang, Chunhua Shen, Ian Reid, Jing Liu, Lingqiao Liu, Mingkui Tan","submitted_at":"2019-08-10T11:48:55Z","abstract_excerpt":"This paper tackles the problem of training a deep convolutional neural network of both low-bitwidth weights and activations. Optimizing a low-precision network is very challenging due to the non-differentiability of the quantizer, which may result in substantial accuracy loss. To address this, we propose three practical approaches, including (i) progressive quantization; (ii) stochastic precision; and (iii) joint knowledge distillation to improve the network training. First, for progressive quantization, we propose two schemes to progressively find good local minima. Specifically, we propose t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.04680","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.04680/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T02:46:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6hQk6/qK475+7j8V7/LfB59dGbXf1DsGWAffTaYTeOspzc4DOVNT6EKgmn8jjahTjKysrm2hHoTPmF4/S88+CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:51:47.408087Z"},"content_sha256":"16600ae451038eeb9d3b9ca7be6ad3d89446a22e2b5db8071505122cf0816a22","schema_version":"1.0","event_id":"sha256:16600ae451038eeb9d3b9ca7be6ad3d89446a22e2b5db8071505122cf0816a22"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SXMJKKYOAM5ZO2ZLCAGWWAZQWU/bundle.json","state_url":"https://pith.science/pith/SXMJKKYOAM5ZO2ZLCAGWWAZQWU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SXMJKKYOAM5ZO2ZLCAGWWAZQWU/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":"2026-08-06T16:51:47Z","links":{"resolver":"https://pith.science/pith/SXMJKKYOAM5ZO2ZLCAGWWAZQWU","bundle":"https://pith.science/pith/SXMJKKYOAM5ZO2ZLCAGWWAZQWU/bundle.json","state":"https://pith.science/pith/SXMJKKYOAM5ZO2ZLCAGWWAZQWU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SXMJKKYOAM5ZO2ZLCAGWWAZQWU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SXMJKKYOAM5ZO2ZLCAGWWAZQWU","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":"cbfd25ceb5cbbc03e5ec446bcaef9bfe6955e9c9865728efbd8e6ee5e6046376","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-08-10T11:48:55Z","title_canon_sha256":"162d0a54505f4ff7f0f347159c6b135a36647e40fbb1d0356b303052da307645"},"schema_version":"1.0","source":{"id":"1908.04680","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.04680","created_at":"2026-07-05T02:46:07Z"},{"alias_kind":"arxiv_version","alias_value":"1908.04680v3","created_at":"2026-07-05T02:46:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04680","created_at":"2026-07-05T02:46:07Z"},{"alias_kind":"pith_short_12","alias_value":"SXMJKKYOAM5Z","created_at":"2026-07-05T02:46:07Z"},{"alias_kind":"pith_short_16","alias_value":"SXMJKKYOAM5ZO2ZL","created_at":"2026-07-05T02:46:07Z"},{"alias_kind":"pith_short_8","alias_value":"SXMJKKYO","created_at":"2026-07-05T02:46:07Z"}],"graph_snapshots":[{"event_id":"sha256:16600ae451038eeb9d3b9ca7be6ad3d89446a22e2b5db8071505122cf0816a22","target":"graph","created_at":"2026-07-05T02:46:07Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1908.04680/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper tackles the problem of training a deep convolutional neural network of both low-bitwidth weights and activations. Optimizing a low-precision network is very challenging due to the non-differentiability of the quantizer, which may result in substantial accuracy loss. To address this, we propose three practical approaches, including (i) progressive quantization; (ii) stochastic precision; and (iii) joint knowledge distillation to improve the network training. First, for progressive quantization, we propose two schemes to progressively find good local minima. Specifically, we propose t","authors_text":"Bohan Zhuang, Chunhua Shen, Ian Reid, Jing Liu, Lingqiao Liu, Mingkui Tan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-08-10T11:48:55Z","title":"Effective Training of Convolutional Neural Networks with Low-bitwidth Weights and Activations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.04680","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:e489699ae18e3462fe4b06d74d94c61463ae226c480c86e79e5bc66bd97244da","target":"record","created_at":"2026-07-05T02:46:07Z","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":"cbfd25ceb5cbbc03e5ec446bcaef9bfe6955e9c9865728efbd8e6ee5e6046376","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-08-10T11:48:55Z","title_canon_sha256":"162d0a54505f4ff7f0f347159c6b135a36647e40fbb1d0356b303052da307645"},"schema_version":"1.0","source":{"id":"1908.04680","kind":"arxiv","version":3}},"canonical_sha256":"95d8952b0e033b976b2b100d6b0330b50ae14c43067ac47a87c9c0ce10046d2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95d8952b0e033b976b2b100d6b0330b50ae14c43067ac47a87c9c0ce10046d2d","first_computed_at":"2026-07-05T02:46:07.660950Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:46:07.660950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"40jmp2QbhAuo3RfwlUSmK+FEHy9NxLwUSuDaZMSjci4lbk9PatDi211ekUmV10mmKJcvMV39TLfOh/rirSpTCA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:46:07.661475Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.04680","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e489699ae18e3462fe4b06d74d94c61463ae226c480c86e79e5bc66bd97244da","sha256:16600ae451038eeb9d3b9ca7be6ad3d89446a22e2b5db8071505122cf0816a22"],"state_sha256":"98f070ed9566ace58b64080056f8eb10485bff2cc110f6348cb1dc840740d3f3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jT7YFedczxQmz0k9Nh+WZCcI2qfpsrt9fGV6lkEWoX+LENAfTAMOY63iSaQRh8XAxhCqxmWy9LQM/Os5R96HBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T16:51:47.413971Z","bundle_sha256":"d9b3141dd55b5f8a30447d96eeb67e976a6dc6c06a0c6532a63d0dc9cbd460eb"}}