{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PGSOECCUWPQBVYMH4A6RTTNEWS","short_pith_number":"pith:PGSOECCU","schema_version":"1.0","canonical_sha256":"79a4e20854b3e01ae187e03d19cda4b492144485ba82bc5b91cde39ed40703bb","source":{"kind":"arxiv","id":"2310.10126","version":1},"attestation_state":"computed","paper":{"title":"A Non-monotonic Smooth Activation Function","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Koushik Biswas, Meghana Karri, Ula\\c{s} Ba\\u{g}c{\\i}","submitted_at":"2023-10-16T07:09:47Z","abstract_excerpt":"Activation functions are crucial in deep learning models since they introduce non-linearity into the networks, allowing them to learn from errors and make adjustments, which is essential for learning complex patterns. The essential purpose of activation functions is to transform unprocessed input signals into significant output activations, promoting information transmission throughout the neural network. In this study, we propose a new activation function called Sqish, which is a non-monotonic and smooth function and an alternative to existing ones. We showed its superiority in classification"},"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":"2310.10126","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T07:09:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eb1a0a5fec8be28982f7131e7298a19adafd0448c503a17748e9db35c0b286c9","abstract_canon_sha256":"d018514b87f8825cf25bd86fc1a1d6269409215597669211c96c14f5f3df7e49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:15.614874Z","signature_b64":"QQKFoIv+J+jhGH6GwQ2nnlcB3KD5W87UhS0RERo4+5gZI4wJksqV49h7D4sjpnG+pKU9hUP6pX0yLQ7/crIxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79a4e20854b3e01ae187e03d19cda4b492144485ba82bc5b91cde39ed40703bb","last_reissued_at":"2026-07-05T07:01:15.614428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:15.614428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Non-monotonic Smooth Activation Function","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Koushik Biswas, Meghana Karri, Ula\\c{s} Ba\\u{g}c{\\i}","submitted_at":"2023-10-16T07:09:47Z","abstract_excerpt":"Activation functions are crucial in deep learning models since they introduce non-linearity into the networks, allowing them to learn from errors and make adjustments, which is essential for learning complex patterns. The essential purpose of activation functions is to transform unprocessed input signals into significant output activations, promoting information transmission throughout the neural network. In this study, we propose a new activation function called Sqish, which is a non-monotonic and smooth function and an alternative to existing ones. We showed its superiority in classification"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10126","kind":"arxiv","version":1},"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/2310.10126/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":"2310.10126","created_at":"2026-07-05T07:01:15.614484+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.10126v1","created_at":"2026-07-05T07:01:15.614484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10126","created_at":"2026-07-05T07:01:15.614484+00:00"},{"alias_kind":"pith_short_12","alias_value":"PGSOECCUWPQB","created_at":"2026-07-05T07:01:15.614484+00:00"},{"alias_kind":"pith_short_16","alias_value":"PGSOECCUWPQBVYMH","created_at":"2026-07-05T07:01:15.614484+00:00"},{"alias_kind":"pith_short_8","alias_value":"PGSOECCU","created_at":"2026-07-05T07:01:15.614484+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09158","citing_title":"Automatic Contouring of Spinal Vertebrae on X-Ray using a Novel Sandwich U-Net Architecture","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PGSOECCUWPQBVYMH4A6RTTNEWS","json":"https://pith.science/pith/PGSOECCUWPQBVYMH4A6RTTNEWS.json","graph_json":"https://pith.science/api/pith-number/PGSOECCUWPQBVYMH4A6RTTNEWS/graph.json","events_json":"https://pith.science/api/pith-number/PGSOECCUWPQBVYMH4A6RTTNEWS/events.json","paper":"https://pith.science/paper/PGSOECCU"},"agent_actions":{"view_html":"https://pith.science/pith/PGSOECCUWPQBVYMH4A6RTTNEWS","download_json":"https://pith.science/pith/PGSOECCUWPQBVYMH4A6RTTNEWS.json","view_paper":"https://pith.science/paper/PGSOECCU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.10126&json=true","fetch_graph":"https://pith.science/api/pith-number/PGSOECCUWPQBVYMH4A6RTTNEWS/graph.json","fetch_events":"https://pith.science/api/pith-number/PGSOECCUWPQBVYMH4A6RTTNEWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PGSOECCUWPQBVYMH4A6RTTNEWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PGSOECCUWPQBVYMH4A6RTTNEWS/action/storage_attestation","attest_author":"https://pith.science/pith/PGSOECCUWPQBVYMH4A6RTTNEWS/action/author_attestation","sign_citation":"https://pith.science/pith/PGSOECCUWPQBVYMH4A6RTTNEWS/action/citation_signature","submit_replication":"https://pith.science/pith/PGSOECCUWPQBVYMH4A6RTTNEWS/action/replication_record"}},"created_at":"2026-07-05T07:01:15.614484+00:00","updated_at":"2026-07-05T07:01:15.614484+00:00"}