{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3C2V2EDNUSG33W6JEYXI4QLEWD","short_pith_number":"pith:3C2V2EDN","schema_version":"1.0","canonical_sha256":"d8b55d106da48dbddbc9262e8e4164b0e3315ab74a42cd93635200909dfc2b10","source":{"kind":"arxiv","id":"2210.02637","version":1},"attestation_state":"computed","paper":{"title":"IR2Net: Information Restriction and Information Recovery for Accurate Binary Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingfei Chang, Ping Xue, Xing Wei, Yang Lu, Zhen Wei","submitted_at":"2022-10-06T02:03:26Z","abstract_excerpt":"Weight and activation binarization can efficiently compress deep neural networks and accelerate model inference, but cause severe accuracy degradation. Existing optimization methods for binary neural networks (BNNs) focus on fitting full-precision networks to reduce quantization errors, and suffer from the trade-off between accuracy and computational complexity. In contrast, considering the limited learning ability and information loss caused by the limited representational capability of BNNs, we propose IR$^2$Net to stimulate the potential of BNNs and improve the network accuracy by restricti"},"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":"2210.02637","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-06T02:03:26Z","cross_cats_sorted":[],"title_canon_sha256":"c50c5c04c13bfb0c512de1590085585f4a51072649709ba1f53d0252c4182255","abstract_canon_sha256":"db751e0bd1ed5c140333c46e4d5a197f838f6b6ef4640cd68d62cf22085c2118"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:54.879031Z","signature_b64":"YDbzeqYig3WGvxL+QbcCNL37eaU/HqxRLeQn2RPqkwfz2hpS/cQV+RM0fK/AXGcoP5U8aSuP/dq7bZ7fCP7XDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8b55d106da48dbddbc9262e8e4164b0e3315ab74a42cd93635200909dfc2b10","last_reissued_at":"2026-07-05T05:03:54.878634Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:54.878634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IR2Net: Information Restriction and Information Recovery for Accurate Binary Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingfei Chang, Ping Xue, Xing Wei, Yang Lu, Zhen Wei","submitted_at":"2022-10-06T02:03:26Z","abstract_excerpt":"Weight and activation binarization can efficiently compress deep neural networks and accelerate model inference, but cause severe accuracy degradation. Existing optimization methods for binary neural networks (BNNs) focus on fitting full-precision networks to reduce quantization errors, and suffer from the trade-off between accuracy and computational complexity. In contrast, considering the limited learning ability and information loss caused by the limited representational capability of BNNs, we propose IR$^2$Net to stimulate the potential of BNNs and improve the network accuracy by restricti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.02637","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/2210.02637/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":"2210.02637","created_at":"2026-07-05T05:03:54.878686+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.02637v1","created_at":"2026-07-05T05:03:54.878686+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.02637","created_at":"2026-07-05T05:03:54.878686+00:00"},{"alias_kind":"pith_short_12","alias_value":"3C2V2EDNUSG3","created_at":"2026-07-05T05:03:54.878686+00:00"},{"alias_kind":"pith_short_16","alias_value":"3C2V2EDNUSG33W6J","created_at":"2026-07-05T05:03:54.878686+00:00"},{"alias_kind":"pith_short_8","alias_value":"3C2V2EDN","created_at":"2026-07-05T05:03:54.878686+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/3C2V2EDNUSG33W6JEYXI4QLEWD","json":"https://pith.science/pith/3C2V2EDNUSG33W6JEYXI4QLEWD.json","graph_json":"https://pith.science/api/pith-number/3C2V2EDNUSG33W6JEYXI4QLEWD/graph.json","events_json":"https://pith.science/api/pith-number/3C2V2EDNUSG33W6JEYXI4QLEWD/events.json","paper":"https://pith.science/paper/3C2V2EDN"},"agent_actions":{"view_html":"https://pith.science/pith/3C2V2EDNUSG33W6JEYXI4QLEWD","download_json":"https://pith.science/pith/3C2V2EDNUSG33W6JEYXI4QLEWD.json","view_paper":"https://pith.science/paper/3C2V2EDN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.02637&json=true","fetch_graph":"https://pith.science/api/pith-number/3C2V2EDNUSG33W6JEYXI4QLEWD/graph.json","fetch_events":"https://pith.science/api/pith-number/3C2V2EDNUSG33W6JEYXI4QLEWD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3C2V2EDNUSG33W6JEYXI4QLEWD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3C2V2EDNUSG33W6JEYXI4QLEWD/action/storage_attestation","attest_author":"https://pith.science/pith/3C2V2EDNUSG33W6JEYXI4QLEWD/action/author_attestation","sign_citation":"https://pith.science/pith/3C2V2EDNUSG33W6JEYXI4QLEWD/action/citation_signature","submit_replication":"https://pith.science/pith/3C2V2EDNUSG33W6JEYXI4QLEWD/action/replication_record"}},"created_at":"2026-07-05T05:03:54.878686+00:00","updated_at":"2026-07-05T05:03:54.878686+00:00"}