{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FIFYMSRRGOE7INHKCI7XKZ2VME","short_pith_number":"pith:FIFYMSRR","schema_version":"1.0","canonical_sha256":"2a0b864a313389f434ea123f756755611b3233dabc4ca37281017cc0bc0c0b5e","source":{"kind":"arxiv","id":"2509.07236","version":1},"attestation_state":"computed","paper":{"title":"Breaking the Conventional Forward-Backward Tie in Neural Networks: Activation Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.NE","authors_text":"Francesco Gissi, Genny Tortora, Luigi Troiano, Vincenzo Benedetto","submitted_at":"2025-09-08T21:30:00Z","abstract_excerpt":"Gradient-based neural network training traditionally enforces symmetry between forward and backward propagation, requiring activation functions to be differentiable (or sub-differentiable) and strictly monotonic in certain regions to prevent flat gradient areas. This symmetry, linking forward activations closely to backward gradients, significantly restricts the selection of activation functions, particularly excluding those with substantial flat or non-differentiable regions. In this paper, we challenge this assumption through mathematical analysis, demonstrating that precise gradient magnitu"},"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":"2509.07236","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2025-09-08T21:30:00Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"12b7b1e7e4a9edf5a68695925385bde365f8ced24ff3e2097d0522df59b03b86","abstract_canon_sha256":"53812e28ed00095f1ac0ee832d5751a82d963faffdeeb8d8e009d14e5b88e743"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:18.101688Z","signature_b64":"gJAm4fjZW4dmuSAyyLrvkq5SB74gQAceGXGT5oOqDZubask12opkzoL07pLM90unZoWcryay+paDXcPzJ+W1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a0b864a313389f434ea123f756755611b3233dabc4ca37281017cc0bc0c0b5e","last_reissued_at":"2026-07-05T12:07:18.101107Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:18.101107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Breaking the Conventional Forward-Backward Tie in Neural Networks: Activation Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.NE","authors_text":"Francesco Gissi, Genny Tortora, Luigi Troiano, Vincenzo Benedetto","submitted_at":"2025-09-08T21:30:00Z","abstract_excerpt":"Gradient-based neural network training traditionally enforces symmetry between forward and backward propagation, requiring activation functions to be differentiable (or sub-differentiable) and strictly monotonic in certain regions to prevent flat gradient areas. This symmetry, linking forward activations closely to backward gradients, significantly restricts the selection of activation functions, particularly excluding those with substantial flat or non-differentiable regions. In this paper, we challenge this assumption through mathematical analysis, demonstrating that precise gradient magnitu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.07236","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/2509.07236/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":"2509.07236","created_at":"2026-07-05T12:07:18.101176+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.07236v1","created_at":"2026-07-05T12:07:18.101176+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.07236","created_at":"2026-07-05T12:07:18.101176+00:00"},{"alias_kind":"pith_short_12","alias_value":"FIFYMSRRGOE7","created_at":"2026-07-05T12:07:18.101176+00:00"},{"alias_kind":"pith_short_16","alias_value":"FIFYMSRRGOE7INHK","created_at":"2026-07-05T12:07:18.101176+00:00"},{"alias_kind":"pith_short_8","alias_value":"FIFYMSRR","created_at":"2026-07-05T12:07:18.101176+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/FIFYMSRRGOE7INHKCI7XKZ2VME","json":"https://pith.science/pith/FIFYMSRRGOE7INHKCI7XKZ2VME.json","graph_json":"https://pith.science/api/pith-number/FIFYMSRRGOE7INHKCI7XKZ2VME/graph.json","events_json":"https://pith.science/api/pith-number/FIFYMSRRGOE7INHKCI7XKZ2VME/events.json","paper":"https://pith.science/paper/FIFYMSRR"},"agent_actions":{"view_html":"https://pith.science/pith/FIFYMSRRGOE7INHKCI7XKZ2VME","download_json":"https://pith.science/pith/FIFYMSRRGOE7INHKCI7XKZ2VME.json","view_paper":"https://pith.science/paper/FIFYMSRR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.07236&json=true","fetch_graph":"https://pith.science/api/pith-number/FIFYMSRRGOE7INHKCI7XKZ2VME/graph.json","fetch_events":"https://pith.science/api/pith-number/FIFYMSRRGOE7INHKCI7XKZ2VME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FIFYMSRRGOE7INHKCI7XKZ2VME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FIFYMSRRGOE7INHKCI7XKZ2VME/action/storage_attestation","attest_author":"https://pith.science/pith/FIFYMSRRGOE7INHKCI7XKZ2VME/action/author_attestation","sign_citation":"https://pith.science/pith/FIFYMSRRGOE7INHKCI7XKZ2VME/action/citation_signature","submit_replication":"https://pith.science/pith/FIFYMSRRGOE7INHKCI7XKZ2VME/action/replication_record"}},"created_at":"2026-07-05T12:07:18.101176+00:00","updated_at":"2026-07-05T12:07:18.101176+00:00"}