{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ATKYHQEHMVQQSLY6PFD4XCXP6Y","short_pith_number":"pith:ATKYHQEH","schema_version":"1.0","canonical_sha256":"04d583c0876561092f1e7947cb8aeff6280e0cb2c75566859d934cd148637ff4","source":{"kind":"arxiv","id":"2003.09855","version":2},"attestation_state":"computed","paper":{"title":"TanhExp: A Smooth Activation Function with High Convergence Speed for Lightweight Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Xiaoguang Di, Xinyu Liu","submitted_at":"2020-03-22T10:40:31Z","abstract_excerpt":"Lightweight or mobile neural networks used for real-time computer vision tasks contain fewer parameters than normal networks, which lead to a constrained performance. In this work, we proposed a novel activation function named Tanh Exponential Activation Function (TanhExp) which can improve the performance for these networks on image classification task significantly. The definition of TanhExp is f(x) = xtanh(e^x). We demonstrate the simplicity, efficiency, and robustness of TanhExp on various datasets and network models and TanhExp outperforms its counterparts in both convergence speed and ac"},"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":"2003.09855","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-22T10:40:31Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"83c1b3e087027d64f541e9618c82d88f08781f54191618413e0d5572010ca365","abstract_canon_sha256":"f283dd9ae28df9b14704fed8d99183998fec904104e429cbd1ff0cf4e16b9b63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:34:07.056874Z","signature_b64":"WJoPQFw91CGGrmBnUiqpXQQ8T5xblEYvCTPsoIzniwIsXgXhho4srFs/eJR1VGDzNW3uonyHoCTFs66aLtCdCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04d583c0876561092f1e7947cb8aeff6280e0cb2c75566859d934cd148637ff4","last_reissued_at":"2026-07-05T01:34:07.056399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:34:07.056399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TanhExp: A Smooth Activation Function with High Convergence Speed for Lightweight Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Xiaoguang Di, Xinyu Liu","submitted_at":"2020-03-22T10:40:31Z","abstract_excerpt":"Lightweight or mobile neural networks used for real-time computer vision tasks contain fewer parameters than normal networks, which lead to a constrained performance. In this work, we proposed a novel activation function named Tanh Exponential Activation Function (TanhExp) which can improve the performance for these networks on image classification task significantly. The definition of TanhExp is f(x) = xtanh(e^x). We demonstrate the simplicity, efficiency, and robustness of TanhExp on various datasets and network models and TanhExp outperforms its counterparts in both convergence speed and ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.09855","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/2003.09855/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":"2003.09855","created_at":"2026-07-05T01:34:07.056461+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.09855v2","created_at":"2026-07-05T01:34:07.056461+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.09855","created_at":"2026-07-05T01:34:07.056461+00:00"},{"alias_kind":"pith_short_12","alias_value":"ATKYHQEHMVQQ","created_at":"2026-07-05T01:34:07.056461+00:00"},{"alias_kind":"pith_short_16","alias_value":"ATKYHQEHMVQQSLY6","created_at":"2026-07-05T01:34:07.056461+00:00"},{"alias_kind":"pith_short_8","alias_value":"ATKYHQEH","created_at":"2026-07-05T01:34:07.056461+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22372","citing_title":"Testing $\\Lambda$CDM with ANN-Reconstructed Expansion History from Cosmic Chronometers","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ATKYHQEHMVQQSLY6PFD4XCXP6Y","json":"https://pith.science/pith/ATKYHQEHMVQQSLY6PFD4XCXP6Y.json","graph_json":"https://pith.science/api/pith-number/ATKYHQEHMVQQSLY6PFD4XCXP6Y/graph.json","events_json":"https://pith.science/api/pith-number/ATKYHQEHMVQQSLY6PFD4XCXP6Y/events.json","paper":"https://pith.science/paper/ATKYHQEH"},"agent_actions":{"view_html":"https://pith.science/pith/ATKYHQEHMVQQSLY6PFD4XCXP6Y","download_json":"https://pith.science/pith/ATKYHQEHMVQQSLY6PFD4XCXP6Y.json","view_paper":"https://pith.science/paper/ATKYHQEH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.09855&json=true","fetch_graph":"https://pith.science/api/pith-number/ATKYHQEHMVQQSLY6PFD4XCXP6Y/graph.json","fetch_events":"https://pith.science/api/pith-number/ATKYHQEHMVQQSLY6PFD4XCXP6Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ATKYHQEHMVQQSLY6PFD4XCXP6Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ATKYHQEHMVQQSLY6PFD4XCXP6Y/action/storage_attestation","attest_author":"https://pith.science/pith/ATKYHQEHMVQQSLY6PFD4XCXP6Y/action/author_attestation","sign_citation":"https://pith.science/pith/ATKYHQEHMVQQSLY6PFD4XCXP6Y/action/citation_signature","submit_replication":"https://pith.science/pith/ATKYHQEHMVQQSLY6PFD4XCXP6Y/action/replication_record"}},"created_at":"2026-07-05T01:34:07.056461+00:00","updated_at":"2026-07-05T01:34:07.056461+00:00"}