{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VWBRKWQGTI6CPXP55BG6IRJT37","short_pith_number":"pith:VWBRKWQG","schema_version":"1.0","canonical_sha256":"ad83155a069a3c27ddfde84de44533dfeb54b625aaec23a348a43f253df7709f","source":{"kind":"arxiv","id":"2507.10560","version":1},"attestation_state":"computed","paper":{"title":"Tangma: A Tanh-Guided Activation Function with Learnable Parameters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.NE","authors_text":"Shreel Golwala","submitted_at":"2025-07-02T21:01:27Z","abstract_excerpt":"Activation functions are key to effective backpropagation and expressiveness in deep neural networks. This work introduces Tangma, a new activation function that combines the smooth shape of the hyperbolic tangent with two learnable parameters: $\\alpha$, which shifts the curve's inflection point to adjust neuron activation, and $\\gamma$, which adds linearity to preserve weak gradients and improve training stability. Tangma was evaluated on MNIST and CIFAR-10 using custom networks composed of convolutional and linear layers, and compared against ReLU, Swish, and GELU. On MNIST, Tangma achieved "},"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":"2507.10560","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2025-07-02T21:01:27Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"46a360cdb40620188062a129f8b9cd3a92ea26fcd1a4a7b96e53da272b433437","abstract_canon_sha256":"1a58bd2638fa040269b53351338ac2c315c25b4477426219000dee0f532a3980"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:26.912985Z","signature_b64":"OsvIP1oJAJHTWVewRJmu8jx9o7/BbgpHG6uS0A4AVj/wZDEa5jwILsKWA46f4s81T/vGRYHG0H/Qb6Gzgn9VAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad83155a069a3c27ddfde84de44533dfeb54b625aaec23a348a43f253df7709f","last_reissued_at":"2026-07-05T11:37:26.912497Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:26.912497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tangma: A Tanh-Guided Activation Function with Learnable Parameters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.NE","authors_text":"Shreel Golwala","submitted_at":"2025-07-02T21:01:27Z","abstract_excerpt":"Activation functions are key to effective backpropagation and expressiveness in deep neural networks. This work introduces Tangma, a new activation function that combines the smooth shape of the hyperbolic tangent with two learnable parameters: $\\alpha$, which shifts the curve's inflection point to adjust neuron activation, and $\\gamma$, which adds linearity to preserve weak gradients and improve training stability. Tangma was evaluated on MNIST and CIFAR-10 using custom networks composed of convolutional and linear layers, and compared against ReLU, Swish, and GELU. On MNIST, Tangma achieved "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10560","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/2507.10560/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":"2507.10560","created_at":"2026-07-05T11:37:26.912557+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.10560v1","created_at":"2026-07-05T11:37:26.912557+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10560","created_at":"2026-07-05T11:37:26.912557+00:00"},{"alias_kind":"pith_short_12","alias_value":"VWBRKWQGTI6C","created_at":"2026-07-05T11:37:26.912557+00:00"},{"alias_kind":"pith_short_16","alias_value":"VWBRKWQGTI6CPXP5","created_at":"2026-07-05T11:37:26.912557+00:00"},{"alias_kind":"pith_short_8","alias_value":"VWBRKWQG","created_at":"2026-07-05T11:37:26.912557+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VWBRKWQGTI6CPXP55BG6IRJT37","json":"https://pith.science/pith/VWBRKWQGTI6CPXP55BG6IRJT37.json","graph_json":"https://pith.science/api/pith-number/VWBRKWQGTI6CPXP55BG6IRJT37/graph.json","events_json":"https://pith.science/api/pith-number/VWBRKWQGTI6CPXP55BG6IRJT37/events.json","paper":"https://pith.science/paper/VWBRKWQG"},"agent_actions":{"view_html":"https://pith.science/pith/VWBRKWQGTI6CPXP55BG6IRJT37","download_json":"https://pith.science/pith/VWBRKWQGTI6CPXP55BG6IRJT37.json","view_paper":"https://pith.science/paper/VWBRKWQG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.10560&json=true","fetch_graph":"https://pith.science/api/pith-number/VWBRKWQGTI6CPXP55BG6IRJT37/graph.json","fetch_events":"https://pith.science/api/pith-number/VWBRKWQGTI6CPXP55BG6IRJT37/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VWBRKWQGTI6CPXP55BG6IRJT37/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VWBRKWQGTI6CPXP55BG6IRJT37/action/storage_attestation","attest_author":"https://pith.science/pith/VWBRKWQGTI6CPXP55BG6IRJT37/action/author_attestation","sign_citation":"https://pith.science/pith/VWBRKWQGTI6CPXP55BG6IRJT37/action/citation_signature","submit_replication":"https://pith.science/pith/VWBRKWQGTI6CPXP55BG6IRJT37/action/replication_record"}},"created_at":"2026-07-05T11:37:26.912557+00:00","updated_at":"2026-07-05T11:37:26.912557+00:00"}