{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QACDKC7SR4ZC6F7GGRIGHDUCTU","short_pith_number":"pith:QACDKC7S","schema_version":"1.0","canonical_sha256":"8004350bf28f322f17e63450638e829d089d531bc61bd5d562bcdf51fe5e7bbc","source":{"kind":"arxiv","id":"2305.07537","version":2},"attestation_state":"computed","paper":{"title":"Saturated Non-Monotonic Activation Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Junjia Chen, Zhibin Pan","submitted_at":"2023-05-12T15:01:06Z","abstract_excerpt":"Activation functions are essential to deep learning networks. Popular and versatile activation functions are mostly monotonic functions, some non-monotonic activation functions are being explored and show promising performance. But by introducing non-monotonicity, they also alter the positive input, which is proved to be unnecessary by the success of ReLU and its variants. In this paper, we double down on the non-monotonic activation functions' development and propose the Saturated Gaussian Error Linear Units by combining the characteristics of ReLU and non-monotonic activation functions. We p"},"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":"2305.07537","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2023-05-12T15:01:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fe7810dc6639893850e2a8a0f5b2eda99baacaad02a93d5f32d0a8ebe9b1ecf6","abstract_canon_sha256":"2c44b75a6f8b3f2f4e25842e20c64aab6cf10a77d25b0771a77b1bda57258206"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:39.430561Z","signature_b64":"qw7/BhNvWcYnwCpmeZSx/JviKkKkXbJNnVD6Knk1g0IwvZ1ovR3TBRrx2pJZDQnUGfKlrC4kJKD9pnQInCnNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8004350bf28f322f17e63450638e829d089d531bc61bd5d562bcdf51fe5e7bbc","last_reissued_at":"2026-07-05T06:13:39.430069Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:39.430069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Saturated Non-Monotonic Activation Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Junjia Chen, Zhibin Pan","submitted_at":"2023-05-12T15:01:06Z","abstract_excerpt":"Activation functions are essential to deep learning networks. Popular and versatile activation functions are mostly monotonic functions, some non-monotonic activation functions are being explored and show promising performance. But by introducing non-monotonicity, they also alter the positive input, which is proved to be unnecessary by the success of ReLU and its variants. In this paper, we double down on the non-monotonic activation functions' development and propose the Saturated Gaussian Error Linear Units by combining the characteristics of ReLU and non-monotonic activation functions. We p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.07537","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/2305.07537/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":"2305.07537","created_at":"2026-07-05T06:13:39.430133+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.07537v2","created_at":"2026-07-05T06:13:39.430133+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07537","created_at":"2026-07-05T06:13:39.430133+00:00"},{"alias_kind":"pith_short_12","alias_value":"QACDKC7SR4ZC","created_at":"2026-07-05T06:13:39.430133+00:00"},{"alias_kind":"pith_short_16","alias_value":"QACDKC7SR4ZC6F7G","created_at":"2026-07-05T06:13:39.430133+00:00"},{"alias_kind":"pith_short_8","alias_value":"QACDKC7S","created_at":"2026-07-05T06:13:39.430133+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21677","citing_title":"Geometric Monomial (GEM): a family of rational 2N-differentiable activation functions","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QACDKC7SR4ZC6F7GGRIGHDUCTU","json":"https://pith.science/pith/QACDKC7SR4ZC6F7GGRIGHDUCTU.json","graph_json":"https://pith.science/api/pith-number/QACDKC7SR4ZC6F7GGRIGHDUCTU/graph.json","events_json":"https://pith.science/api/pith-number/QACDKC7SR4ZC6F7GGRIGHDUCTU/events.json","paper":"https://pith.science/paper/QACDKC7S"},"agent_actions":{"view_html":"https://pith.science/pith/QACDKC7SR4ZC6F7GGRIGHDUCTU","download_json":"https://pith.science/pith/QACDKC7SR4ZC6F7GGRIGHDUCTU.json","view_paper":"https://pith.science/paper/QACDKC7S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.07537&json=true","fetch_graph":"https://pith.science/api/pith-number/QACDKC7SR4ZC6F7GGRIGHDUCTU/graph.json","fetch_events":"https://pith.science/api/pith-number/QACDKC7SR4ZC6F7GGRIGHDUCTU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QACDKC7SR4ZC6F7GGRIGHDUCTU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QACDKC7SR4ZC6F7GGRIGHDUCTU/action/storage_attestation","attest_author":"https://pith.science/pith/QACDKC7SR4ZC6F7GGRIGHDUCTU/action/author_attestation","sign_citation":"https://pith.science/pith/QACDKC7SR4ZC6F7GGRIGHDUCTU/action/citation_signature","submit_replication":"https://pith.science/pith/QACDKC7SR4ZC6F7GGRIGHDUCTU/action/replication_record"}},"created_at":"2026-07-05T06:13:39.430133+00:00","updated_at":"2026-07-05T06:13:39.430133+00:00"}