{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:N6GLBY2QKVVK7VWG75DA5G2RC3","short_pith_number":"pith:N6GLBY2Q","schema_version":"1.0","canonical_sha256":"6f8cb0e350556aafd6c6ff460e9b5116da2534164e0c56aacb6a5f4c489d577c","source":{"kind":"arxiv","id":"2010.04871","version":1},"attestation_state":"computed","paper":{"title":"Training Binary Neural Networks through Learning with Noisy Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Xu, Chunjing Xu, Enhua Wu, Kai Han, Yixing Xu, Yunhe Wang","submitted_at":"2020-10-10T01:59:39Z","abstract_excerpt":"This paper formalizes the binarization operations over neural networks from a learning perspective. In contrast to classical hand crafted rules (\\eg hard thresholding) to binarize full-precision neurons, we propose to learn a mapping from full-precision neurons to the target binary ones. Each individual weight entry will not be binarized independently. Instead, they are taken as a whole to accomplish the binarization, just as they work together in generating convolution features. To help the training of the binarization mapping, the full-precision neurons after taking sign operations is regard"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2010.04871","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-10-10T01:59:39Z","cross_cats_sorted":[],"title_canon_sha256":"2c64a20bc16ea5a8b20bb894fb1e66905c38cd7719ec40d0a1aa925462af12dd","abstract_canon_sha256":"12f0179eee31549c86ae3cc31746e9e25f15de6d73d9f8759eeefd9d6bc6e850"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:42:00.207231Z","signature_b64":"7W/nis/WMJ+vYIMExAbzCrn7f48HxzwazvMHWIa7Y9oaYczJLxUdTcgMP5Uo78G8S25xU76eVygM/gDxNwEQBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f8cb0e350556aafd6c6ff460e9b5116da2534164e0c56aacb6a5f4c489d577c","last_reissued_at":"2026-07-05T01:42:00.206851Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:42:00.206851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Binary Neural Networks through Learning with Noisy Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Xu, Chunjing Xu, Enhua Wu, Kai Han, Yixing Xu, Yunhe Wang","submitted_at":"2020-10-10T01:59:39Z","abstract_excerpt":"This paper formalizes the binarization operations over neural networks from a learning perspective. In contrast to classical hand crafted rules (\\eg hard thresholding) to binarize full-precision neurons, we propose to learn a mapping from full-precision neurons to the target binary ones. Each individual weight entry will not be binarized independently. Instead, they are taken as a whole to accomplish the binarization, just as they work together in generating convolution features. To help the training of the binarization mapping, the full-precision neurons after taking sign operations is regard"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.04871","kind":"arxiv","version":1},"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/2010.04871/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2010.04871","created_at":"2026-07-05T01:42:00.206907+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.04871v1","created_at":"2026-07-05T01:42:00.206907+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.04871","created_at":"2026-07-05T01:42:00.206907+00:00"},{"alias_kind":"pith_short_12","alias_value":"N6GLBY2QKVVK","created_at":"2026-07-05T01:42:00.206907+00:00"},{"alias_kind":"pith_short_16","alias_value":"N6GLBY2QKVVK7VWG","created_at":"2026-07-05T01:42:00.206907+00:00"},{"alias_kind":"pith_short_8","alias_value":"N6GLBY2Q","created_at":"2026-07-05T01:42:00.206907+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N6GLBY2QKVVK7VWG75DA5G2RC3","json":"https://pith.science/pith/N6GLBY2QKVVK7VWG75DA5G2RC3.json","graph_json":"https://pith.science/api/pith-number/N6GLBY2QKVVK7VWG75DA5G2RC3/graph.json","events_json":"https://pith.science/api/pith-number/N6GLBY2QKVVK7VWG75DA5G2RC3/events.json","paper":"https://pith.science/paper/N6GLBY2Q"},"agent_actions":{"view_html":"https://pith.science/pith/N6GLBY2QKVVK7VWG75DA5G2RC3","download_json":"https://pith.science/pith/N6GLBY2QKVVK7VWG75DA5G2RC3.json","view_paper":"https://pith.science/paper/N6GLBY2Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.04871&json=true","fetch_graph":"https://pith.science/api/pith-number/N6GLBY2QKVVK7VWG75DA5G2RC3/graph.json","fetch_events":"https://pith.science/api/pith-number/N6GLBY2QKVVK7VWG75DA5G2RC3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N6GLBY2QKVVK7VWG75DA5G2RC3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N6GLBY2QKVVK7VWG75DA5G2RC3/action/storage_attestation","attest_author":"https://pith.science/pith/N6GLBY2QKVVK7VWG75DA5G2RC3/action/author_attestation","sign_citation":"https://pith.science/pith/N6GLBY2QKVVK7VWG75DA5G2RC3/action/citation_signature","submit_replication":"https://pith.science/pith/N6GLBY2QKVVK7VWG75DA5G2RC3/action/replication_record"}},"created_at":"2026-07-05T01:42:00.206907+00:00","updated_at":"2026-07-05T01:42:00.206907+00:00"}