{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YZDR7ZUYK4QDKTUU3THCWMMDXZ","short_pith_number":"pith:YZDR7ZUY","schema_version":"1.0","canonical_sha256":"c6471fe6985720354e94dcce2b3183be685ccb50cb5fe0722b33d22bb1d3709c","source":{"kind":"arxiv","id":"2606.20292","version":1},"attestation_state":"computed","paper":{"title":"Shifting-based Optimizable Linear Relaxations for General Activation Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LO"],"primary_cat":"cs.LG","authors_text":"Carsten Sinz, Erika \\'Abr\\'aham, L\\'aszl\\'o Antal, Philipp Kern","submitted_at":"2026-06-18T14:32:05Z","abstract_excerpt":"The use of neural networks (NNs) is rapidly increasing, including in safety- and security-critical domains. To provide formal guarantees about NN behavior, many verification methods rely on optimizable linear relaxations of activation functions. However, existing techniques depend on hand-crafted relaxations for each activation function. Extension to state-of-the-art activation functions therefore requires substantial manual effort. In contrast, our approach SLiR (Shifting-based Linear Relaxations) is broadly applicable, requiring only a Lipschitz constant or a set of critical points. SLiR par"},"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":"2606.20292","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-18T14:32:05Z","cross_cats_sorted":["cs.LO"],"title_canon_sha256":"bd9be8430ad187dd3365c299fc05d00a43dee8edd366ba967389f33b58573f60","abstract_canon_sha256":"1122e96788bfc439368de099dcc1f713bae54453f5d1e9b496e9aedb56e2a2de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:13:07.982958Z","signature_b64":"c3BjOd0k5p5dOS01xiWdcHvdac6lMbOJLR5bNHerrVWQ7QpSVG0bAVH0BXzN1nvmYnsFOcaMi+JL1DDTXB8CBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6471fe6985720354e94dcce2b3183be685ccb50cb5fe0722b33d22bb1d3709c","last_reissued_at":"2026-06-19T16:13:07.982568Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:13:07.982568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Shifting-based Optimizable Linear Relaxations for General Activation Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LO"],"primary_cat":"cs.LG","authors_text":"Carsten Sinz, Erika \\'Abr\\'aham, L\\'aszl\\'o Antal, Philipp Kern","submitted_at":"2026-06-18T14:32:05Z","abstract_excerpt":"The use of neural networks (NNs) is rapidly increasing, including in safety- and security-critical domains. To provide formal guarantees about NN behavior, many verification methods rely on optimizable linear relaxations of activation functions. However, existing techniques depend on hand-crafted relaxations for each activation function. Extension to state-of-the-art activation functions therefore requires substantial manual effort. In contrast, our approach SLiR (Shifting-based Linear Relaxations) is broadly applicable, requiring only a Lipschitz constant or a set of critical points. SLiR par"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20292","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/2606.20292/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":"2606.20292","created_at":"2026-06-19T16:13:07.982630+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20292v1","created_at":"2026-06-19T16:13:07.982630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20292","created_at":"2026-06-19T16:13:07.982630+00:00"},{"alias_kind":"pith_short_12","alias_value":"YZDR7ZUYK4QD","created_at":"2026-06-19T16:13:07.982630+00:00"},{"alias_kind":"pith_short_16","alias_value":"YZDR7ZUYK4QDKTUU","created_at":"2026-06-19T16:13:07.982630+00:00"},{"alias_kind":"pith_short_8","alias_value":"YZDR7ZUY","created_at":"2026-06-19T16:13:07.982630+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/YZDR7ZUYK4QDKTUU3THCWMMDXZ","json":"https://pith.science/pith/YZDR7ZUYK4QDKTUU3THCWMMDXZ.json","graph_json":"https://pith.science/api/pith-number/YZDR7ZUYK4QDKTUU3THCWMMDXZ/graph.json","events_json":"https://pith.science/api/pith-number/YZDR7ZUYK4QDKTUU3THCWMMDXZ/events.json","paper":"https://pith.science/paper/YZDR7ZUY"},"agent_actions":{"view_html":"https://pith.science/pith/YZDR7ZUYK4QDKTUU3THCWMMDXZ","download_json":"https://pith.science/pith/YZDR7ZUYK4QDKTUU3THCWMMDXZ.json","view_paper":"https://pith.science/paper/YZDR7ZUY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20292&json=true","fetch_graph":"https://pith.science/api/pith-number/YZDR7ZUYK4QDKTUU3THCWMMDXZ/graph.json","fetch_events":"https://pith.science/api/pith-number/YZDR7ZUYK4QDKTUU3THCWMMDXZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YZDR7ZUYK4QDKTUU3THCWMMDXZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YZDR7ZUYK4QDKTUU3THCWMMDXZ/action/storage_attestation","attest_author":"https://pith.science/pith/YZDR7ZUYK4QDKTUU3THCWMMDXZ/action/author_attestation","sign_citation":"https://pith.science/pith/YZDR7ZUYK4QDKTUU3THCWMMDXZ/action/citation_signature","submit_replication":"https://pith.science/pith/YZDR7ZUYK4QDKTUU3THCWMMDXZ/action/replication_record"}},"created_at":"2026-06-19T16:13:07.982630+00:00","updated_at":"2026-06-19T16:13:07.982630+00:00"}