{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ETKYYLS6HWKZWCZIPJ4RP3MIWV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"aac37732d3b487b136d35896c0b1c591dbc229bc718987cc5d5e805f6960c971","cross_cats_sorted":["cs.AI","cs.NA","cs.NE","math.NA"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-07T07:36:49Z","title_canon_sha256":"3a9734e76d2dc8cb0dd588a7428bebd1cfd110e3491389e868896fe8a16f8bc7"},"schema_version":"1.0","source":{"id":"2408.03599","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.03599","created_at":"2026-07-05T08:55:51Z"},{"alias_kind":"arxiv_version","alias_value":"2408.03599v2","created_at":"2026-07-05T08:55:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.03599","created_at":"2026-07-05T08:55:51Z"},{"alias_kind":"pith_short_12","alias_value":"ETKYYLS6HWKZ","created_at":"2026-07-05T08:55:51Z"},{"alias_kind":"pith_short_16","alias_value":"ETKYYLS6HWKZWCZI","created_at":"2026-07-05T08:55:51Z"},{"alias_kind":"pith_short_8","alias_value":"ETKYYLS6","created_at":"2026-07-05T08:55:51Z"}],"graph_snapshots":[{"event_id":"sha256:922e9e8ffaefdb01edc6d51ce5086545416cb7132ca5ec4e737ac90fe488f441","target":"graph","created_at":"2026-07-05T08:55:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2408.03599/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Activation functions are non-linearities in neural networks that allow them to learn complex mapping between inputs and outputs. Typical choices for activation functions are ReLU, Tanh, Sigmoid etc., where the choice generally depends on the application domain. In this work, we propose a framework/strategy that unifies several works on activation functions and theoretically explains the performance benefits of these works. We also propose novel techniques that originate from the framework and allow us to obtain ``extensions'' (i.e. special generalizations of a given neural network) of neural n","authors_text":"Arindam Jati, Chandramouli Kamanchi, Dzung Phan, Kameshwaran Sampath, Pankaj Dayama, Sumanta Mukherjee, Vijay Ekambaram","cross_cats":["cs.AI","cs.NA","cs.NE","math.NA"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-07T07:36:49Z","title":"Activations Through Extensions: A Framework To Boost Performance Of Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.03599","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8970364c4aa9dab78dbc4dfee29de1b0835d1c03ea002c018874d7b58f109a54","target":"record","created_at":"2026-07-05T08:55:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"aac37732d3b487b136d35896c0b1c591dbc229bc718987cc5d5e805f6960c971","cross_cats_sorted":["cs.AI","cs.NA","cs.NE","math.NA"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-07T07:36:49Z","title_canon_sha256":"3a9734e76d2dc8cb0dd588a7428bebd1cfd110e3491389e868896fe8a16f8bc7"},"schema_version":"1.0","source":{"id":"2408.03599","kind":"arxiv","version":2}},"canonical_sha256":"24d58c2e5e3d959b0b287a7917ed88b545dd2233b4004c5a7c5912567d884055","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24d58c2e5e3d959b0b287a7917ed88b545dd2233b4004c5a7c5912567d884055","first_computed_at":"2026-07-05T08:55:51.885737Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:55:51.885737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o324j5oH8IqR5TcGPhCcx3YcyppyKASHH2Gn9Hdpn+Q6WqIObo1jJP4RQhf6+/qra3+XdCe5smy0nJd12J37Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:55:51.886156Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.03599","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8970364c4aa9dab78dbc4dfee29de1b0835d1c03ea002c018874d7b58f109a54","sha256:922e9e8ffaefdb01edc6d51ce5086545416cb7132ca5ec4e737ac90fe488f441"],"state_sha256":"cb17dd767214bdfc32028849da95ba02c6250e6aeff01c11533086d7286613cf"}