{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FMZXY2LKGHDYJVRXVSKYXG7I53","short_pith_number":"pith:FMZXY2LK","schema_version":"1.0","canonical_sha256":"2b337c696a31c784d637ac958b9be8eee8d77ab4365ec9cdbc940985b5ab5129","source":{"kind":"arxiv","id":"2504.15100","version":1},"attestation_state":"computed","paper":{"title":"Application of Sensitivity Analysis Methods for Studying Neural Network Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"Jiaxuan Miao, Sergey Matveev","submitted_at":"2025-04-21T13:41:20Z","abstract_excerpt":"This study demonstrates the capabilities of several methods for analyzing the sensitivity of neural networks to perturbations of the input data and interpreting their underlying mechanisms. The investigated approaches include the Sobol global sensitivity analysis, the local sensitivity method for input pixel perturbations and the activation maximization technique. As examples, in this study we consider a small feedforward neural network for analyzing an open tabular dataset of clinical diabetes data, as well as two classical convolutional architectures, VGG-16 and ResNet-18, which are widely u"},"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":"2504.15100","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2025-04-21T13:41:20Z","cross_cats_sorted":["cs.LG","cs.NA"],"title_canon_sha256":"ba3a281e751e90a3533fec7ebd97c6a15eeeaf7f69921ce5614c08d2c04081a6","abstract_canon_sha256":"37910b7509801f15c6c0a96765336044b584f22aa555ec21f1484e76b2ab5bc5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:56.234173Z","signature_b64":"U5SejRbjvFYCmdHp8sbdLOSVJyVdw7MQLEe7tDpdCSzUryIHmN3NwnBmu4zpkm+aZzDkC282GRdFWHmJEZWJCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b337c696a31c784d637ac958b9be8eee8d77ab4365ec9cdbc940985b5ab5129","last_reissued_at":"2026-07-05T10:51:56.233637Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:56.233637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Application of Sensitivity Analysis Methods for Studying Neural Network Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"Jiaxuan Miao, Sergey Matveev","submitted_at":"2025-04-21T13:41:20Z","abstract_excerpt":"This study demonstrates the capabilities of several methods for analyzing the sensitivity of neural networks to perturbations of the input data and interpreting their underlying mechanisms. The investigated approaches include the Sobol global sensitivity analysis, the local sensitivity method for input pixel perturbations and the activation maximization technique. As examples, in this study we consider a small feedforward neural network for analyzing an open tabular dataset of clinical diabetes data, as well as two classical convolutional architectures, VGG-16 and ResNet-18, which are widely u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15100","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/2504.15100/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":"2504.15100","created_at":"2026-07-05T10:51:56.233691+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.15100v1","created_at":"2026-07-05T10:51:56.233691+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15100","created_at":"2026-07-05T10:51:56.233691+00:00"},{"alias_kind":"pith_short_12","alias_value":"FMZXY2LKGHDY","created_at":"2026-07-05T10:51:56.233691+00:00"},{"alias_kind":"pith_short_16","alias_value":"FMZXY2LKGHDYJVRX","created_at":"2026-07-05T10:51:56.233691+00:00"},{"alias_kind":"pith_short_8","alias_value":"FMZXY2LK","created_at":"2026-07-05T10:51:56.233691+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/FMZXY2LKGHDYJVRXVSKYXG7I53","json":"https://pith.science/pith/FMZXY2LKGHDYJVRXVSKYXG7I53.json","graph_json":"https://pith.science/api/pith-number/FMZXY2LKGHDYJVRXVSKYXG7I53/graph.json","events_json":"https://pith.science/api/pith-number/FMZXY2LKGHDYJVRXVSKYXG7I53/events.json","paper":"https://pith.science/paper/FMZXY2LK"},"agent_actions":{"view_html":"https://pith.science/pith/FMZXY2LKGHDYJVRXVSKYXG7I53","download_json":"https://pith.science/pith/FMZXY2LKGHDYJVRXVSKYXG7I53.json","view_paper":"https://pith.science/paper/FMZXY2LK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.15100&json=true","fetch_graph":"https://pith.science/api/pith-number/FMZXY2LKGHDYJVRXVSKYXG7I53/graph.json","fetch_events":"https://pith.science/api/pith-number/FMZXY2LKGHDYJVRXVSKYXG7I53/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FMZXY2LKGHDYJVRXVSKYXG7I53/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FMZXY2LKGHDYJVRXVSKYXG7I53/action/storage_attestation","attest_author":"https://pith.science/pith/FMZXY2LKGHDYJVRXVSKYXG7I53/action/author_attestation","sign_citation":"https://pith.science/pith/FMZXY2LKGHDYJVRXVSKYXG7I53/action/citation_signature","submit_replication":"https://pith.science/pith/FMZXY2LKGHDYJVRXVSKYXG7I53/action/replication_record"}},"created_at":"2026-07-05T10:51:56.233691+00:00","updated_at":"2026-07-05T10:51:56.233691+00:00"}