{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:HZPKZ24PXGVG5RVFVMFPOHAXFA","short_pith_number":"pith:HZPKZ24P","canonical_record":{"source":{"id":"1702.03044","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-10T02:30:22Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"1c11a5a6f9dce1946cf71c234350853ed35c00e1065932c556f3ed46e6199a7b","abstract_canon_sha256":"fd2339062194b0f8ef5a2b91efd82eef5c985472add26e17dab7b3e33da585c2"},"schema_version":"1.0"},"canonical_sha256":"3e5eaceb8fb9aa6ec6a5ab0af71c1728395d3239e7cdfaa96ad1b2683ac46dcc","source":{"kind":"arxiv","id":"1702.03044","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.03044","created_at":"2026-05-18T00:36:43Z"},{"alias_kind":"arxiv_version","alias_value":"1702.03044v2","created_at":"2026-05-18T00:36:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.03044","created_at":"2026-05-18T00:36:43Z"},{"alias_kind":"pith_short_12","alias_value":"HZPKZ24PXGVG","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"HZPKZ24PXGVG5RVF","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"HZPKZ24P","created_at":"2026-05-18T12:31:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:HZPKZ24PXGVG5RVFVMFPOHAXFA","target":"record","payload":{"canonical_record":{"source":{"id":"1702.03044","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-10T02:30:22Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"1c11a5a6f9dce1946cf71c234350853ed35c00e1065932c556f3ed46e6199a7b","abstract_canon_sha256":"fd2339062194b0f8ef5a2b91efd82eef5c985472add26e17dab7b3e33da585c2"},"schema_version":"1.0"},"canonical_sha256":"3e5eaceb8fb9aa6ec6a5ab0af71c1728395d3239e7cdfaa96ad1b2683ac46dcc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:43.475080Z","signature_b64":"b1FtfJhducNIWS0z6l/J+enqTnR2hbkTKXIjlmehnVmrZ9rpLs66RaM0RSGXRf4ChzT+3avYkgLgyUDMjd9pBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e5eaceb8fb9aa6ec6a5ab0af71c1728395d3239e7cdfaa96ad1b2683ac46dcc","last_reissued_at":"2026-05-18T00:36:43.474310Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:43.474310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.03044","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":"2026-05-18T00:36:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YdpA87WrW7xfozF6lbhRCHThz9TLmHV3fUAHHD8W66l6YvOyAsYrYWkwhGlW6LevsDrXdw1VYVcacpGKPwt0BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T18:27:12.849416Z"},"content_sha256":"2dd30956b686b8cca697931e85b57115cd1eb53cfa3a9d31152cad11716e63be","schema_version":"1.0","event_id":"sha256:2dd30956b686b8cca697931e85b57115cd1eb53cfa3a9d31152cad11716e63be"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:HZPKZ24PXGVG5RVFVMFPOHAXFA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.CV","authors_text":"Anbang Yao, Aojun Zhou, Lin Xu, Yiwen Guo, Yurong Chen","submitted_at":"2017-02-10T02:30:22Z","abstract_excerpt":"This paper presents incremental network quantization (INQ), a novel method, targeting to efficiently convert any pre-trained full-precision convolutional neural network (CNN) model into a low-precision version whose weights are constrained to be either powers of two or zero. Unlike existing methods which are struggled in noticeable accuracy loss, our INQ has the potential to resolve this issue, as benefiting from two innovations. On one hand, we introduce three interdependent operations, namely weight partition, group-wise quantization and re-training. A well-proven measure is employed to divi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.03044","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":"2026-05-18T00:36:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PbiHiej1j0OhFJuKcBNI4q05X5FrW584YlRf82ou7+zKGfCLsoyPwMhwd/GtZ7IOKTQS8X0rJerN4KtQleDaCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T18:27:12.850085Z"},"content_sha256":"3877f80d928e52e481113840374996b7fff82c4d72a0905643e97d09fcb7c330","schema_version":"1.0","event_id":"sha256:3877f80d928e52e481113840374996b7fff82c4d72a0905643e97d09fcb7c330"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HZPKZ24PXGVG5RVFVMFPOHAXFA/bundle.json","state_url":"https://pith.science/pith/HZPKZ24PXGVG5RVFVMFPOHAXFA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HZPKZ24PXGVG5RVFVMFPOHAXFA/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":"2026-05-28T18:27:12Z","links":{"resolver":"https://pith.science/pith/HZPKZ24PXGVG5RVFVMFPOHAXFA","bundle":"https://pith.science/pith/HZPKZ24PXGVG5RVFVMFPOHAXFA/bundle.json","state":"https://pith.science/pith/HZPKZ24PXGVG5RVFVMFPOHAXFA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HZPKZ24PXGVG5RVFVMFPOHAXFA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:HZPKZ24PXGVG5RVFVMFPOHAXFA","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":"fd2339062194b0f8ef5a2b91efd82eef5c985472add26e17dab7b3e33da585c2","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-10T02:30:22Z","title_canon_sha256":"1c11a5a6f9dce1946cf71c234350853ed35c00e1065932c556f3ed46e6199a7b"},"schema_version":"1.0","source":{"id":"1702.03044","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.03044","created_at":"2026-05-18T00:36:43Z"},{"alias_kind":"arxiv_version","alias_value":"1702.03044v2","created_at":"2026-05-18T00:36:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.03044","created_at":"2026-05-18T00:36:43Z"},{"alias_kind":"pith_short_12","alias_value":"HZPKZ24PXGVG","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"HZPKZ24PXGVG5RVF","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"HZPKZ24P","created_at":"2026-05-18T12:31:21Z"}],"graph_snapshots":[{"event_id":"sha256:3877f80d928e52e481113840374996b7fff82c4d72a0905643e97d09fcb7c330","target":"graph","created_at":"2026-05-18T00:36:43Z","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":"This paper presents incremental network quantization (INQ), a novel method, targeting to efficiently convert any pre-trained full-precision convolutional neural network (CNN) model into a low-precision version whose weights are constrained to be either powers of two or zero. Unlike existing methods which are struggled in noticeable accuracy loss, our INQ has the potential to resolve this issue, as benefiting from two innovations. On one hand, we introduce three interdependent operations, namely weight partition, group-wise quantization and re-training. A well-proven measure is employed to divi","authors_text":"Anbang Yao, Aojun Zhou, Lin Xu, Yiwen Guo, Yurong Chen","cross_cats":["cs.AI","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-10T02:30:22Z","title":"Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.03044","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":"sha256:2dd30956b686b8cca697931e85b57115cd1eb53cfa3a9d31152cad11716e63be","target":"record","created_at":"2026-05-18T00:36:43Z","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":"fd2339062194b0f8ef5a2b91efd82eef5c985472add26e17dab7b3e33da585c2","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-10T02:30:22Z","title_canon_sha256":"1c11a5a6f9dce1946cf71c234350853ed35c00e1065932c556f3ed46e6199a7b"},"schema_version":"1.0","source":{"id":"1702.03044","kind":"arxiv","version":2}},"canonical_sha256":"3e5eaceb8fb9aa6ec6a5ab0af71c1728395d3239e7cdfaa96ad1b2683ac46dcc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e5eaceb8fb9aa6ec6a5ab0af71c1728395d3239e7cdfaa96ad1b2683ac46dcc","first_computed_at":"2026-05-18T00:36:43.474310Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:36:43.474310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b1FtfJhducNIWS0z6l/J+enqTnR2hbkTKXIjlmehnVmrZ9rpLs66RaM0RSGXRf4ChzT+3avYkgLgyUDMjd9pBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:36:43.475080Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.03044","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2dd30956b686b8cca697931e85b57115cd1eb53cfa3a9d31152cad11716e63be","sha256:3877f80d928e52e481113840374996b7fff82c4d72a0905643e97d09fcb7c330"],"state_sha256":"ee9e31f8d7a0dac2390937c2121ac1b74287598a85667a334a9c47f196f3614d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kpbvlj+0VGPOAgnElJJ6XWIAcTr1OPCqjf7EIrsC/qJRDyfC3WneGm6/gPfSE49d3kb6s/fJ4h9aY8Zo3V/uAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T18:27:12.853657Z","bundle_sha256":"c3901dc3911ec6e396bb7963b5a613e4d8bf48b9cf52271d403c7fb9a9d12c8e"}}