{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:QTJ76226TKUC7U2V5VRA7JZC42","short_pith_number":"pith:QTJ76226","canonical_record":{"source":{"id":"1711.00205","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-01T04:41:29Z","cross_cats_sorted":[],"title_canon_sha256":"1c649ef9da1f1a73617c61da97cebf6590fe664cb29e500df8eac5554d85d587","abstract_canon_sha256":"2cb9628104e8d85a0eed44f5c27c71eef4a3d57c992039e3ef19d83efcd376de"},"schema_version":"1.0"},"canonical_sha256":"84d3ff6b5e9aa82fd355ed620fa722e6b9df06e836929b9eaad070917e7f3bf8","source":{"kind":"arxiv","id":"1711.00205","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.00205","created_at":"2026-07-05T02:45:59Z"},{"alias_kind":"arxiv_version","alias_value":"1711.00205v2","created_at":"2026-07-05T02:45:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.00205","created_at":"2026-07-05T02:45:59Z"},{"alias_kind":"pith_short_12","alias_value":"QTJ76226TKUC","created_at":"2026-07-05T02:45:59Z"},{"alias_kind":"pith_short_16","alias_value":"QTJ76226TKUC7U2V","created_at":"2026-07-05T02:45:59Z"},{"alias_kind":"pith_short_8","alias_value":"QTJ76226","created_at":"2026-07-05T02:45:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:QTJ76226TKUC7U2V5VRA7JZC42","target":"record","payload":{"canonical_record":{"source":{"id":"1711.00205","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-01T04:41:29Z","cross_cats_sorted":[],"title_canon_sha256":"1c649ef9da1f1a73617c61da97cebf6590fe664cb29e500df8eac5554d85d587","abstract_canon_sha256":"2cb9628104e8d85a0eed44f5c27c71eef4a3d57c992039e3ef19d83efcd376de"},"schema_version":"1.0"},"canonical_sha256":"84d3ff6b5e9aa82fd355ed620fa722e6b9df06e836929b9eaad070917e7f3bf8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:45:59.214156Z","signature_b64":"LBj+3MpkaYsBi+Nor34xMAWe02Hu5OaKWqZd192Q4Z5xY2wr0GaSM3kNtkwq3T+Ivrzbvgf9TtBJRNZl4m9MBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84d3ff6b5e9aa82fd355ed620fa722e6b9df06e836929b9eaad070917e7f3bf8","last_reissued_at":"2026-07-05T02:45:59.213776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:45:59.213776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.00205","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":"2026-07-05T02:45:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EBUETAhhHgRJFa/jXutc9LAcYJEU23wto/M21E/LovDAHWQiD1XOWMKODBWA6ZbdiPnp0prrGUdQNOJATtzHCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T13:01:01.667129Z"},"content_sha256":"af65626e07f5017f7d7f87a1f92bf5f8971858dfb391570385167b0aaf04a5da","schema_version":"1.0","event_id":"sha256:af65626e07f5017f7d7f87a1f92bf5f8971858dfb391570385167b0aaf04a5da"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:QTJ76226TKUC7U2V5VRA7JZC42","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Effective Low-bitwidth Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohan Zhuang, Chunhua Shen, Ian Reid, Lingqiao Liu, Mingkui Tan","submitted_at":"2017-11-01T04:41:29Z","abstract_excerpt":"This paper tackles the problem of training a deep convolutional neural network with both low-precision weights and low-bitwidth activations. Optimizing a low-precision network is very challenging since the training process can easily get trapped in a poor local minima, which results in substantial accuracy loss. To mitigate this problem, we propose three simple-yet-effective approaches to improve the network training. First, we propose to use a two-stage optimization strategy to progressively find good local minima. Specifically, we propose to first optimize a net with quantized weights and th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.00205","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1711.00205/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":"2026-07-05T02:45:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CkKkOMOyTgVnD+w5JH+hA43Nad+5UNfNqe/G0MKPjdeXWPeKFjG3/oKzEOzWzfRuTg1zDY8Djb5T0i4v7KeACw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T13:01:01.667739Z"},"content_sha256":"f8bc5f0b5cda989585100052f6ca49685874d4ab045d5e91631aa921aa3ab8a9","schema_version":"1.0","event_id":"sha256:f8bc5f0b5cda989585100052f6ca49685874d4ab045d5e91631aa921aa3ab8a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QTJ76226TKUC7U2V5VRA7JZC42/bundle.json","state_url":"https://pith.science/pith/QTJ76226TKUC7U2V5VRA7JZC42/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QTJ76226TKUC7U2V5VRA7JZC42/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":"2026-08-17T13:01:01Z","links":{"resolver":"https://pith.science/pith/QTJ76226TKUC7U2V5VRA7JZC42","bundle":"https://pith.science/pith/QTJ76226TKUC7U2V5VRA7JZC42/bundle.json","state":"https://pith.science/pith/QTJ76226TKUC7U2V5VRA7JZC42/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QTJ76226TKUC7U2V5VRA7JZC42/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:QTJ76226TKUC7U2V5VRA7JZC42","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":"2cb9628104e8d85a0eed44f5c27c71eef4a3d57c992039e3ef19d83efcd376de","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-01T04:41:29Z","title_canon_sha256":"1c649ef9da1f1a73617c61da97cebf6590fe664cb29e500df8eac5554d85d587"},"schema_version":"1.0","source":{"id":"1711.00205","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.00205","created_at":"2026-07-05T02:45:59Z"},{"alias_kind":"arxiv_version","alias_value":"1711.00205v2","created_at":"2026-07-05T02:45:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.00205","created_at":"2026-07-05T02:45:59Z"},{"alias_kind":"pith_short_12","alias_value":"QTJ76226TKUC","created_at":"2026-07-05T02:45:59Z"},{"alias_kind":"pith_short_16","alias_value":"QTJ76226TKUC7U2V","created_at":"2026-07-05T02:45:59Z"},{"alias_kind":"pith_short_8","alias_value":"QTJ76226","created_at":"2026-07-05T02:45:59Z"}],"graph_snapshots":[{"event_id":"sha256:f8bc5f0b5cda989585100052f6ca49685874d4ab045d5e91631aa921aa3ab8a9","target":"graph","created_at":"2026-07-05T02:45:59Z","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/1711.00205/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 with both low-precision weights and low-bitwidth activations. Optimizing a low-precision network is very challenging since the training process can easily get trapped in a poor local minima, which results in substantial accuracy loss. To mitigate this problem, we propose three simple-yet-effective approaches to improve the network training. First, we propose to use a two-stage optimization strategy to progressively find good local minima. Specifically, we propose to first optimize a net with quantized weights and th","authors_text":"Bohan Zhuang, Chunhua Shen, Ian Reid, Lingqiao Liu, Mingkui Tan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-01T04:41:29Z","title":"Towards Effective Low-bitwidth Convolutional Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.00205","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:af65626e07f5017f7d7f87a1f92bf5f8971858dfb391570385167b0aaf04a5da","target":"record","created_at":"2026-07-05T02:45:59Z","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":"2cb9628104e8d85a0eed44f5c27c71eef4a3d57c992039e3ef19d83efcd376de","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-01T04:41:29Z","title_canon_sha256":"1c649ef9da1f1a73617c61da97cebf6590fe664cb29e500df8eac5554d85d587"},"schema_version":"1.0","source":{"id":"1711.00205","kind":"arxiv","version":2}},"canonical_sha256":"84d3ff6b5e9aa82fd355ed620fa722e6b9df06e836929b9eaad070917e7f3bf8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84d3ff6b5e9aa82fd355ed620fa722e6b9df06e836929b9eaad070917e7f3bf8","first_computed_at":"2026-07-05T02:45:59.213776Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:45:59.213776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LBj+3MpkaYsBi+Nor34xMAWe02Hu5OaKWqZd192Q4Z5xY2wr0GaSM3kNtkwq3T+Ivrzbvgf9TtBJRNZl4m9MBw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:45:59.214156Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.00205","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af65626e07f5017f7d7f87a1f92bf5f8971858dfb391570385167b0aaf04a5da","sha256:f8bc5f0b5cda989585100052f6ca49685874d4ab045d5e91631aa921aa3ab8a9"],"state_sha256":"55d8189dacd4c20bebd7bd2e84ff2ca0d8eda313f20f3c6d96e2dc8551955fb4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"naAPNY3EeHyMU/wcR3EOlsq4EUyFuxLbKCpkC2FTVd+gHhneAV3uvFfka/8wAgFSOPIwycYUVQ6TeCNk4fovAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T13:01:01.671580Z","bundle_sha256":"724698c059e21d03e91f790a35ad0d61e0cf74108050e20963f21c952b5abd53"}}