{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:K367WRGKM76Y7DFYDBAGFFAHV6","short_pith_number":"pith:K367WRGK","canonical_record":{"source":{"id":"1611.01600","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-11-05T04:23:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c5c70d353cefd2c1c4d83096e1107333b19caa883a6a7f5883a140846969b73f","abstract_canon_sha256":"f9b06a32babfab3cf3c2984d1abdf895735db3d3f2692bef792bb391715be71c"},"schema_version":"1.0"},"canonical_sha256":"56fdfb44ca67fd8f8cb81840629407afaabd8ac7e5e5332029bda37c5f96020a","source":{"kind":"arxiv","id":"1611.01600","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.01600","created_at":"2026-05-18T00:16:16Z"},{"alias_kind":"arxiv_version","alias_value":"1611.01600v3","created_at":"2026-05-18T00:16:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01600","created_at":"2026-05-18T00:16:16Z"},{"alias_kind":"pith_short_12","alias_value":"K367WRGKM76Y","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_16","alias_value":"K367WRGKM76Y7DFY","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_8","alias_value":"K367WRGK","created_at":"2026-05-18T12:30:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:K367WRGKM76Y7DFYDBAGFFAHV6","target":"record","payload":{"canonical_record":{"source":{"id":"1611.01600","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-11-05T04:23:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c5c70d353cefd2c1c4d83096e1107333b19caa883a6a7f5883a140846969b73f","abstract_canon_sha256":"f9b06a32babfab3cf3c2984d1abdf895735db3d3f2692bef792bb391715be71c"},"schema_version":"1.0"},"canonical_sha256":"56fdfb44ca67fd8f8cb81840629407afaabd8ac7e5e5332029bda37c5f96020a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:16.249616Z","signature_b64":"lhl7sG7L+CUhyny7TARJr7Qop7xbI4Fu4tg1CizPP9aetJEYA60mP/s5pW6v3wRev+pNyFlur5it3HamOFmrDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56fdfb44ca67fd8f8cb81840629407afaabd8ac7e5e5332029bda37c5f96020a","last_reissued_at":"2026-05-18T00:16:16.249035Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:16.249035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.01600","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":"2026-05-18T00:16:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nmJofRa2PwkNyMF7/jcAH/NaQRqZVKimiqF+M2W7gfCe176wnMIQ+BfnybivzbQWmqFTX3wI6Pxmdm25TMwRDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T04:49:39.454185Z"},"content_sha256":"8ce6ea55fdf5382199bad17d6004775e2ad3daebd82b357242516b9cde8d9e70","schema_version":"1.0","event_id":"sha256:8ce6ea55fdf5382199bad17d6004775e2ad3daebd82b357242516b9cde8d9e70"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:K367WRGKM76Y7DFYDBAGFFAHV6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Loss-aware Binarization of Deep Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"James T. Kwok, Lu Hou, Quanming Yao","submitted_at":"2016-11-05T04:23:42Z","abstract_excerpt":"Deep neural network models, though very powerful and highly successful, are computationally expensive in terms of space and time. Recently, there have been a number of attempts on binarizing the network weights and activations. This greatly reduces the network size, and replaces the underlying multiplications to additions or even XNOR bit operations. However, existing binarization schemes are based on simple matrix approximation and ignore the effect of binarization on the loss. In this paper, we propose a proximal Newton algorithm with diagonal Hessian approximation that directly minimizes th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01600","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":"2026-05-18T00:16:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yQAJlrZdFSJyzylmywZif5NjjQMrp2N7Wnd1TLu3z/Qc/KOM0ydLtsDw/LNqTXZDRhsQPityCPJMSaASfQPjCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T04:49:39.454746Z"},"content_sha256":"089d5896792fbf0428a9f689f887b012bd99a9a7f7ae5b806b3d81e8ae962952","schema_version":"1.0","event_id":"sha256:089d5896792fbf0428a9f689f887b012bd99a9a7f7ae5b806b3d81e8ae962952"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K367WRGKM76Y7DFYDBAGFFAHV6/bundle.json","state_url":"https://pith.science/pith/K367WRGKM76Y7DFYDBAGFFAHV6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K367WRGKM76Y7DFYDBAGFFAHV6/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":"2026-06-05T04:49:39Z","links":{"resolver":"https://pith.science/pith/K367WRGKM76Y7DFYDBAGFFAHV6","bundle":"https://pith.science/pith/K367WRGKM76Y7DFYDBAGFFAHV6/bundle.json","state":"https://pith.science/pith/K367WRGKM76Y7DFYDBAGFFAHV6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K367WRGKM76Y7DFYDBAGFFAHV6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:K367WRGKM76Y7DFYDBAGFFAHV6","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":"f9b06a32babfab3cf3c2984d1abdf895735db3d3f2692bef792bb391715be71c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-11-05T04:23:42Z","title_canon_sha256":"c5c70d353cefd2c1c4d83096e1107333b19caa883a6a7f5883a140846969b73f"},"schema_version":"1.0","source":{"id":"1611.01600","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.01600","created_at":"2026-05-18T00:16:16Z"},{"alias_kind":"arxiv_version","alias_value":"1611.01600v3","created_at":"2026-05-18T00:16:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01600","created_at":"2026-05-18T00:16:16Z"},{"alias_kind":"pith_short_12","alias_value":"K367WRGKM76Y","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_16","alias_value":"K367WRGKM76Y7DFY","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_8","alias_value":"K367WRGK","created_at":"2026-05-18T12:30:25Z"}],"graph_snapshots":[{"event_id":"sha256:089d5896792fbf0428a9f689f887b012bd99a9a7f7ae5b806b3d81e8ae962952","target":"graph","created_at":"2026-05-18T00:16:16Z","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 network models, though very powerful and highly successful, are computationally expensive in terms of space and time. Recently, there have been a number of attempts on binarizing the network weights and activations. This greatly reduces the network size, and replaces the underlying multiplications to additions or even XNOR bit operations. However, existing binarization schemes are based on simple matrix approximation and ignore the effect of binarization on the loss. In this paper, we propose a proximal Newton algorithm with diagonal Hessian approximation that directly minimizes th","authors_text":"James T. Kwok, Lu Hou, Quanming Yao","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-11-05T04:23:42Z","title":"Loss-aware Binarization of Deep Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01600","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":"sha256:8ce6ea55fdf5382199bad17d6004775e2ad3daebd82b357242516b9cde8d9e70","target":"record","created_at":"2026-05-18T00:16:16Z","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":"f9b06a32babfab3cf3c2984d1abdf895735db3d3f2692bef792bb391715be71c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-11-05T04:23:42Z","title_canon_sha256":"c5c70d353cefd2c1c4d83096e1107333b19caa883a6a7f5883a140846969b73f"},"schema_version":"1.0","source":{"id":"1611.01600","kind":"arxiv","version":3}},"canonical_sha256":"56fdfb44ca67fd8f8cb81840629407afaabd8ac7e5e5332029bda37c5f96020a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56fdfb44ca67fd8f8cb81840629407afaabd8ac7e5e5332029bda37c5f96020a","first_computed_at":"2026-05-18T00:16:16.249035Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:16:16.249035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lhl7sG7L+CUhyny7TARJr7Qop7xbI4Fu4tg1CizPP9aetJEYA60mP/s5pW6v3wRev+pNyFlur5it3HamOFmrDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:16:16.249616Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.01600","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ce6ea55fdf5382199bad17d6004775e2ad3daebd82b357242516b9cde8d9e70","sha256:089d5896792fbf0428a9f689f887b012bd99a9a7f7ae5b806b3d81e8ae962952"],"state_sha256":"704d5bbafaa98744fef19a158ecbed8c55242df964dd9e2821a7cc8207f79a48"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DHUdJvG4G7EQMRZ5Jtx1Gga62+kBXt8/iakD71gkQKRZNkhJDVDfVqmaS7OaKWLytza7d4jY6c9P9wz2oeoUAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T04:49:39.457700Z","bundle_sha256":"2daeef2bcb74f827b189d9ed8c24e60f77378e67a76e7de3cd49a115b6cd4719"}}