{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:OBF5C7T4PGGQC2JINZ3TIANBJN","short_pith_number":"pith:OBF5C7T4","schema_version":"1.0","canonical_sha256":"704bd17e7c798d0169286e773401a14b7b9731c331453aae166f470a427e9f12","source":{"kind":"arxiv","id":"2001.05936","version":2},"attestation_state":"computed","paper":{"title":"MeliusNet: Can Binary Neural Networks Achieve MobileNet-level Accuracy?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christian Bartz, Christoph Meinel, Haojin Yang, Joseph Bethge, Ying Chen","submitted_at":"2020-01-16T16:56:10Z","abstract_excerpt":"Binary Neural Networks (BNNs) are neural networks which use binary weights and activations instead of the typical 32-bit floating point values. They have reduced model sizes and allow for efficient inference on mobile or embedded devices with limited power and computational resources. However, the binarization of weights and activations leads to feature maps of lower quality and lower capacity and thus a drop in accuracy compared to traditional networks. Previous work has increased the number of channels or used multiple binary bases to alleviate these problems. In this paper, we instead prese"},"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":"2001.05936","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-16T16:56:10Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"15eecb7ce9486fc6011a3bac473cf36d29dd51e3352f3be2e75768c31e60d346","abstract_canon_sha256":"754e0b329bfa45e12c737e13608235b2f28aa8c96e0324a91942f056a3195d11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:50:12.748553Z","signature_b64":"YbYFgSjF9/gFtrWPB/rwB/WpYNDQEs1ttVfy6NOEMBCbFYl6JT7RlgOyKLjFtZ72KOr0VHyrasIiQc+7lhdaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"704bd17e7c798d0169286e773401a14b7b9731c331453aae166f470a427e9f12","last_reissued_at":"2026-07-05T00:50:12.748065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:50:12.748065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MeliusNet: Can Binary Neural Networks Achieve MobileNet-level Accuracy?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christian Bartz, Christoph Meinel, Haojin Yang, Joseph Bethge, Ying Chen","submitted_at":"2020-01-16T16:56:10Z","abstract_excerpt":"Binary Neural Networks (BNNs) are neural networks which use binary weights and activations instead of the typical 32-bit floating point values. They have reduced model sizes and allow for efficient inference on mobile or embedded devices with limited power and computational resources. However, the binarization of weights and activations leads to feature maps of lower quality and lower capacity and thus a drop in accuracy compared to traditional networks. Previous work has increased the number of channels or used multiple binary bases to alleviate these problems. In this paper, we instead prese"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.05936","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/2001.05936/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":"2001.05936","created_at":"2026-07-05T00:50:12.748122+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.05936v2","created_at":"2026-07-05T00:50:12.748122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.05936","created_at":"2026-07-05T00:50:12.748122+00:00"},{"alias_kind":"pith_short_12","alias_value":"OBF5C7T4PGGQ","created_at":"2026-07-05T00:50:12.748122+00:00"},{"alias_kind":"pith_short_16","alias_value":"OBF5C7T4PGGQC2JI","created_at":"2026-07-05T00:50:12.748122+00:00"},{"alias_kind":"pith_short_8","alias_value":"OBF5C7T4","created_at":"2026-07-05T00:50:12.748122+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.05463","citing_title":"Task complexity shapes internal representations and robustness in neural networks","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OBF5C7T4PGGQC2JINZ3TIANBJN","json":"https://pith.science/pith/OBF5C7T4PGGQC2JINZ3TIANBJN.json","graph_json":"https://pith.science/api/pith-number/OBF5C7T4PGGQC2JINZ3TIANBJN/graph.json","events_json":"https://pith.science/api/pith-number/OBF5C7T4PGGQC2JINZ3TIANBJN/events.json","paper":"https://pith.science/paper/OBF5C7T4"},"agent_actions":{"view_html":"https://pith.science/pith/OBF5C7T4PGGQC2JINZ3TIANBJN","download_json":"https://pith.science/pith/OBF5C7T4PGGQC2JINZ3TIANBJN.json","view_paper":"https://pith.science/paper/OBF5C7T4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.05936&json=true","fetch_graph":"https://pith.science/api/pith-number/OBF5C7T4PGGQC2JINZ3TIANBJN/graph.json","fetch_events":"https://pith.science/api/pith-number/OBF5C7T4PGGQC2JINZ3TIANBJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OBF5C7T4PGGQC2JINZ3TIANBJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OBF5C7T4PGGQC2JINZ3TIANBJN/action/storage_attestation","attest_author":"https://pith.science/pith/OBF5C7T4PGGQC2JINZ3TIANBJN/action/author_attestation","sign_citation":"https://pith.science/pith/OBF5C7T4PGGQC2JINZ3TIANBJN/action/citation_signature","submit_replication":"https://pith.science/pith/OBF5C7T4PGGQC2JINZ3TIANBJN/action/replication_record"}},"created_at":"2026-07-05T00:50:12.748122+00:00","updated_at":"2026-07-05T00:50:12.748122+00:00"}