{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KMH3CNGKIEJBCMJMYQU6PGFIDU","short_pith_number":"pith:KMH3CNGK","schema_version":"1.0","canonical_sha256":"530fb134ca411211312cc429e798a81d3bad3a3df7f2667ae95df288217edde5","source":{"kind":"arxiv","id":"1807.10458","version":2},"attestation_state":"computed","paper":{"title":"AXNet: ApproXimate computing using an end-to-end trainable neural network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cewu Lu, Chengwen Xu, Li Jiang, Naifeng Jing, Xiaoyao Liang, Xuyang Chen, Zhenghao Peng","submitted_at":"2018-07-27T06:59:46Z","abstract_excerpt":"Neural network based approximate computing is a universal architecture promising to gain tremendous energy-efficiency for many error resilient applications. To guarantee the approximation quality, existing works deploy two neural networks (NNs), e.g., an approximator and a predictor. The approximator provides the approximate results, while the predictor predicts whether the input data is safe to approximate with the given quality requirement. However, it is non-trivial and time-consuming to make these two neural network coordinate---they have different optimization objectives---by training the"},"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":"1807.10458","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-27T06:59:46Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7153fe7135e273e083d04500e8c5fd875037494b050e096a2d1953a1d96d569b","abstract_canon_sha256":"990d7cfeb8cc040742ba68b3b998c7623d13a94cc109c891676b53d11c0dd775"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:04.333037Z","signature_b64":"56oqWEe9Hksyom4/A1A57qABK5Tp6UTP7UdlGs16KM7P6AUwrSUlzGhjFYg5JNvEAwItP/5tQcIqx6z+3fXtCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"530fb134ca411211312cc429e798a81d3bad3a3df7f2667ae95df288217edde5","last_reissued_at":"2026-05-17T23:58:04.332490Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:04.332490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AXNet: ApproXimate computing using an end-to-end trainable neural network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cewu Lu, Chengwen Xu, Li Jiang, Naifeng Jing, Xiaoyao Liang, Xuyang Chen, Zhenghao Peng","submitted_at":"2018-07-27T06:59:46Z","abstract_excerpt":"Neural network based approximate computing is a universal architecture promising to gain tremendous energy-efficiency for many error resilient applications. To guarantee the approximation quality, existing works deploy two neural networks (NNs), e.g., an approximator and a predictor. The approximator provides the approximate results, while the predictor predicts whether the input data is safe to approximate with the given quality requirement. However, it is non-trivial and time-consuming to make these two neural network coordinate---they have different optimization objectives---by training the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.10458","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":""},"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":"1807.10458","created_at":"2026-05-17T23:58:04.332583+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.10458v2","created_at":"2026-05-17T23:58:04.332583+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.10458","created_at":"2026-05-17T23:58:04.332583+00:00"},{"alias_kind":"pith_short_12","alias_value":"KMH3CNGKIEJB","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KMH3CNGKIEJBCMJM","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KMH3CNGK","created_at":"2026-05-18T12:32:33.847187+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/KMH3CNGKIEJBCMJMYQU6PGFIDU","json":"https://pith.science/pith/KMH3CNGKIEJBCMJMYQU6PGFIDU.json","graph_json":"https://pith.science/api/pith-number/KMH3CNGKIEJBCMJMYQU6PGFIDU/graph.json","events_json":"https://pith.science/api/pith-number/KMH3CNGKIEJBCMJMYQU6PGFIDU/events.json","paper":"https://pith.science/paper/KMH3CNGK"},"agent_actions":{"view_html":"https://pith.science/pith/KMH3CNGKIEJBCMJMYQU6PGFIDU","download_json":"https://pith.science/pith/KMH3CNGKIEJBCMJMYQU6PGFIDU.json","view_paper":"https://pith.science/paper/KMH3CNGK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.10458&json=true","fetch_graph":"https://pith.science/api/pith-number/KMH3CNGKIEJBCMJMYQU6PGFIDU/graph.json","fetch_events":"https://pith.science/api/pith-number/KMH3CNGKIEJBCMJMYQU6PGFIDU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KMH3CNGKIEJBCMJMYQU6PGFIDU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KMH3CNGKIEJBCMJMYQU6PGFIDU/action/storage_attestation","attest_author":"https://pith.science/pith/KMH3CNGKIEJBCMJMYQU6PGFIDU/action/author_attestation","sign_citation":"https://pith.science/pith/KMH3CNGKIEJBCMJMYQU6PGFIDU/action/citation_signature","submit_replication":"https://pith.science/pith/KMH3CNGKIEJBCMJMYQU6PGFIDU/action/replication_record"}},"created_at":"2026-05-17T23:58:04.332583+00:00","updated_at":"2026-05-17T23:58:04.332583+00:00"}