{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3ZPKWDXLG573MK65R35UGJ2MDT","short_pith_number":"pith:3ZPKWDXL","schema_version":"1.0","canonical_sha256":"de5eab0eeb377fb62bdd8efb43274c1cf52e2b660d9378651b0e0c02cfe7175f","source":{"kind":"arxiv","id":"1906.09529","version":3},"attestation_state":"computed","paper":{"title":"Learning Activation Functions: A new paradigm for understanding Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Brejesh Lall, Mohit Goyal, Rajan Goyal","submitted_at":"2019-06-23T01:54:36Z","abstract_excerpt":"The scope of research in the domain of activation functions remains limited and centered around improving the ease of optimization or generalization quality of neural networks (NNs). However, to develop a deeper understanding of deep learning, it becomes important to look at the non linear component of NNs more carefully. In this paper, we aim to provide a generic form of activation function along with appropriate mathematical grounding so as to allow for insights into the working of NNs in future. We propose \"Self-Learnable Activation Functions\" (SLAF), which are learned during training and a"},"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":"1906.09529","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-23T01:54:36Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"2f02834d23c4b74dec40b86594b8a6bcac56b0824e9be8049f5752cdc3bd8f5f","abstract_canon_sha256":"8ec5a723c389faeb9c6a14b6058daf249b7076eef3a8b6fb088cff99b134abb3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:58:06.949250Z","signature_b64":"7wFQPtsk2rjPhhABiP9bLkAkh9ZwN/h52ChHNa37LpE38lpVMZBdmrKryc3D0pK/5mbv9mw0iCWLk9b5dqL4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de5eab0eeb377fb62bdd8efb43274c1cf52e2b660d9378651b0e0c02cfe7175f","last_reissued_at":"2026-07-05T01:58:06.948746Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:58:06.948746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Activation Functions: A new paradigm for understanding Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Brejesh Lall, Mohit Goyal, Rajan Goyal","submitted_at":"2019-06-23T01:54:36Z","abstract_excerpt":"The scope of research in the domain of activation functions remains limited and centered around improving the ease of optimization or generalization quality of neural networks (NNs). However, to develop a deeper understanding of deep learning, it becomes important to look at the non linear component of NNs more carefully. In this paper, we aim to provide a generic form of activation function along with appropriate mathematical grounding so as to allow for insights into the working of NNs in future. We propose \"Self-Learnable Activation Functions\" (SLAF), which are learned during training and a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.09529","kind":"arxiv","version":3},"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/1906.09529/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":"1906.09529","created_at":"2026-07-05T01:58:06.948806+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.09529v3","created_at":"2026-07-05T01:58:06.948806+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.09529","created_at":"2026-07-05T01:58:06.948806+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ZPKWDXLG573","created_at":"2026-07-05T01:58:06.948806+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ZPKWDXLG573MK65","created_at":"2026-07-05T01:58:06.948806+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ZPKWDXL","created_at":"2026-07-05T01:58:06.948806+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26647","citing_title":"More Expressive Feedforward Layers: Part I. Token-Adaptive Mixing of Activations","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2404.19756","citing_title":"KAN: Kolmogorov-Arnold Networks","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16842","citing_title":"Singularity Formation: Synergy in Theoretical, Numerical and Machine Learning Approaches","ref_index":135,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3ZPKWDXLG573MK65R35UGJ2MDT","json":"https://pith.science/pith/3ZPKWDXLG573MK65R35UGJ2MDT.json","graph_json":"https://pith.science/api/pith-number/3ZPKWDXLG573MK65R35UGJ2MDT/graph.json","events_json":"https://pith.science/api/pith-number/3ZPKWDXLG573MK65R35UGJ2MDT/events.json","paper":"https://pith.science/paper/3ZPKWDXL"},"agent_actions":{"view_html":"https://pith.science/pith/3ZPKWDXLG573MK65R35UGJ2MDT","download_json":"https://pith.science/pith/3ZPKWDXLG573MK65R35UGJ2MDT.json","view_paper":"https://pith.science/paper/3ZPKWDXL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.09529&json=true","fetch_graph":"https://pith.science/api/pith-number/3ZPKWDXLG573MK65R35UGJ2MDT/graph.json","fetch_events":"https://pith.science/api/pith-number/3ZPKWDXLG573MK65R35UGJ2MDT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ZPKWDXLG573MK65R35UGJ2MDT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ZPKWDXLG573MK65R35UGJ2MDT/action/storage_attestation","attest_author":"https://pith.science/pith/3ZPKWDXLG573MK65R35UGJ2MDT/action/author_attestation","sign_citation":"https://pith.science/pith/3ZPKWDXLG573MK65R35UGJ2MDT/action/citation_signature","submit_replication":"https://pith.science/pith/3ZPKWDXLG573MK65R35UGJ2MDT/action/replication_record"}},"created_at":"2026-07-05T01:58:06.948806+00:00","updated_at":"2026-07-05T01:58:06.948806+00:00"}