{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EO4G2BA7E5FNDRS5FSP5LH3PV2","short_pith_number":"pith:EO4G2BA7","schema_version":"1.0","canonical_sha256":"23b86d041f274ad1c65d2c9fd59f6fae97662983ffd5dcb92c9b070851f75521","source":{"kind":"arxiv","id":"2307.15907","version":1},"attestation_state":"computed","paper":{"title":"An Automata-Theoretic Approach to Synthesizing Binarized Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.FL"],"primary_cat":"cs.LG","authors_text":"Fu Song, Hongxu Zhu, Ji Wang, Wanwei Liu, Ye Tao, Zhen Liang","submitted_at":"2023-07-29T06:27:28Z","abstract_excerpt":"Deep neural networks, (DNNs, a.k.a. NNs), have been widely used in various tasks and have been proven to be successful. However, the accompanied expensive computing and storage costs make the deployments in resource-constrained devices a significant concern. To solve this issue, quantization has emerged as an effective way to reduce the costs of DNNs with little accuracy degradation by quantizing floating-point numbers to low-width fixed-point representations. Quantized neural networks (QNNs) have been developed, with binarized neural networks (BNNs) restricted to binary values as a special ca"},"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":"2307.15907","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-29T06:27:28Z","cross_cats_sorted":["cs.FL"],"title_canon_sha256":"34f3decaab16628134da8426aa93e4045c1dd22d0230ccbff59d0a1e5c960d02","abstract_canon_sha256":"80ff8f6dbc4047eb172340d627333d4edd0df3e565c7aac8bd07df85a66c2d0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:56.280560Z","signature_b64":"HAyUbJdknMhbLTCa+vKTSqqyUC3OX7U96vwe7bDtOr6ZkMxB7Qxo9b86/ACFYrmXZehG60Ra899mhYAujVCWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23b86d041f274ad1c65d2c9fd59f6fae97662983ffd5dcb92c9b070851f75521","last_reissued_at":"2026-07-05T06:35:56.280142Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:56.280142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Automata-Theoretic Approach to Synthesizing Binarized Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.FL"],"primary_cat":"cs.LG","authors_text":"Fu Song, Hongxu Zhu, Ji Wang, Wanwei Liu, Ye Tao, Zhen Liang","submitted_at":"2023-07-29T06:27:28Z","abstract_excerpt":"Deep neural networks, (DNNs, a.k.a. NNs), have been widely used in various tasks and have been proven to be successful. However, the accompanied expensive computing and storage costs make the deployments in resource-constrained devices a significant concern. To solve this issue, quantization has emerged as an effective way to reduce the costs of DNNs with little accuracy degradation by quantizing floating-point numbers to low-width fixed-point representations. Quantized neural networks (QNNs) have been developed, with binarized neural networks (BNNs) restricted to binary values as a special ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15907","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/2307.15907/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":"2307.15907","created_at":"2026-07-05T06:35:56.280198+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.15907v1","created_at":"2026-07-05T06:35:56.280198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15907","created_at":"2026-07-05T06:35:56.280198+00:00"},{"alias_kind":"pith_short_12","alias_value":"EO4G2BA7E5FN","created_at":"2026-07-05T06:35:56.280198+00:00"},{"alias_kind":"pith_short_16","alias_value":"EO4G2BA7E5FNDRS5","created_at":"2026-07-05T06:35:56.280198+00:00"},{"alias_kind":"pith_short_8","alias_value":"EO4G2BA7","created_at":"2026-07-05T06:35:56.280198+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/EO4G2BA7E5FNDRS5FSP5LH3PV2","json":"https://pith.science/pith/EO4G2BA7E5FNDRS5FSP5LH3PV2.json","graph_json":"https://pith.science/api/pith-number/EO4G2BA7E5FNDRS5FSP5LH3PV2/graph.json","events_json":"https://pith.science/api/pith-number/EO4G2BA7E5FNDRS5FSP5LH3PV2/events.json","paper":"https://pith.science/paper/EO4G2BA7"},"agent_actions":{"view_html":"https://pith.science/pith/EO4G2BA7E5FNDRS5FSP5LH3PV2","download_json":"https://pith.science/pith/EO4G2BA7E5FNDRS5FSP5LH3PV2.json","view_paper":"https://pith.science/paper/EO4G2BA7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.15907&json=true","fetch_graph":"https://pith.science/api/pith-number/EO4G2BA7E5FNDRS5FSP5LH3PV2/graph.json","fetch_events":"https://pith.science/api/pith-number/EO4G2BA7E5FNDRS5FSP5LH3PV2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EO4G2BA7E5FNDRS5FSP5LH3PV2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EO4G2BA7E5FNDRS5FSP5LH3PV2/action/storage_attestation","attest_author":"https://pith.science/pith/EO4G2BA7E5FNDRS5FSP5LH3PV2/action/author_attestation","sign_citation":"https://pith.science/pith/EO4G2BA7E5FNDRS5FSP5LH3PV2/action/citation_signature","submit_replication":"https://pith.science/pith/EO4G2BA7E5FNDRS5FSP5LH3PV2/action/replication_record"}},"created_at":"2026-07-05T06:35:56.280198+00:00","updated_at":"2026-07-05T06:35:56.280198+00:00"}