{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:NPSFQZY7OX2T7SIV22CAYY4KOC","short_pith_number":"pith:NPSFQZY7","schema_version":"1.0","canonical_sha256":"6be458671f75f53fc915d6840c638a7082418114fabba5a81fa028b712079776","source":{"kind":"arxiv","id":"2012.07037","version":1},"attestation_state":"computed","paper":{"title":"Fault Injectors for TensorFlow: Evaluation of the Impact of Random Hardware Faults on Deep CNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrey Morozov, Christoph Schorn, Emil Valiev, Kai Ding, Klaus Janschek, Lydia Gauerhof, Michael Beyer","submitted_at":"2020-12-13T11:16:25Z","abstract_excerpt":"Today, Deep Learning (DL) enhances almost every industrial sector, including safety-critical areas. The next generation of safety standards will define appropriate verification techniques for DL-based applications and propose adequate fault tolerance mechanisms. DL-based applications, like any other software, are susceptible to common random hardware faults such as bit flips, which occur in RAM and CPU registers. Such faults can lead to silent data corruption. Therefore, it is crucial to develop methods and tools that help to evaluate how DL components operate under the presence of such faults"},"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":"2012.07037","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-13T11:16:25Z","cross_cats_sorted":[],"title_canon_sha256":"191ba224a611afd4b9be9b9f6169fa7db5560ec86a8a03ab68f3010c78e3deaf","abstract_canon_sha256":"847a3caa53a44818eb6cb36db4eda415c7623feba9be050710f90d6bb7dafd22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:59:16.622621Z","signature_b64":"+C9sEcLmLu3Mjx/R37zMEXL2taYcoGrwAAdzDPnpiPPMnbfNA1FUokV+izjZmhhOWeRBlSBukpDMxHpDVh/oBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6be458671f75f53fc915d6840c638a7082418114fabba5a81fa028b712079776","last_reissued_at":"2026-07-05T01:59:16.622281Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:59:16.622281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fault Injectors for TensorFlow: Evaluation of the Impact of Random Hardware Faults on Deep CNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrey Morozov, Christoph Schorn, Emil Valiev, Kai Ding, Klaus Janschek, Lydia Gauerhof, Michael Beyer","submitted_at":"2020-12-13T11:16:25Z","abstract_excerpt":"Today, Deep Learning (DL) enhances almost every industrial sector, including safety-critical areas. The next generation of safety standards will define appropriate verification techniques for DL-based applications and propose adequate fault tolerance mechanisms. DL-based applications, like any other software, are susceptible to common random hardware faults such as bit flips, which occur in RAM and CPU registers. Such faults can lead to silent data corruption. Therefore, it is crucial to develop methods and tools that help to evaluate how DL components operate under the presence of such faults"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.07037","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/2012.07037/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":"2012.07037","created_at":"2026-07-05T01:59:16.622343+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.07037v1","created_at":"2026-07-05T01:59:16.622343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.07037","created_at":"2026-07-05T01:59:16.622343+00:00"},{"alias_kind":"pith_short_12","alias_value":"NPSFQZY7OX2T","created_at":"2026-07-05T01:59:16.622343+00:00"},{"alias_kind":"pith_short_16","alias_value":"NPSFQZY7OX2T7SIV","created_at":"2026-07-05T01:59:16.622343+00:00"},{"alias_kind":"pith_short_8","alias_value":"NPSFQZY7","created_at":"2026-07-05T01:59:16.622343+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/NPSFQZY7OX2T7SIV22CAYY4KOC","json":"https://pith.science/pith/NPSFQZY7OX2T7SIV22CAYY4KOC.json","graph_json":"https://pith.science/api/pith-number/NPSFQZY7OX2T7SIV22CAYY4KOC/graph.json","events_json":"https://pith.science/api/pith-number/NPSFQZY7OX2T7SIV22CAYY4KOC/events.json","paper":"https://pith.science/paper/NPSFQZY7"},"agent_actions":{"view_html":"https://pith.science/pith/NPSFQZY7OX2T7SIV22CAYY4KOC","download_json":"https://pith.science/pith/NPSFQZY7OX2T7SIV22CAYY4KOC.json","view_paper":"https://pith.science/paper/NPSFQZY7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.07037&json=true","fetch_graph":"https://pith.science/api/pith-number/NPSFQZY7OX2T7SIV22CAYY4KOC/graph.json","fetch_events":"https://pith.science/api/pith-number/NPSFQZY7OX2T7SIV22CAYY4KOC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NPSFQZY7OX2T7SIV22CAYY4KOC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NPSFQZY7OX2T7SIV22CAYY4KOC/action/storage_attestation","attest_author":"https://pith.science/pith/NPSFQZY7OX2T7SIV22CAYY4KOC/action/author_attestation","sign_citation":"https://pith.science/pith/NPSFQZY7OX2T7SIV22CAYY4KOC/action/citation_signature","submit_replication":"https://pith.science/pith/NPSFQZY7OX2T7SIV22CAYY4KOC/action/replication_record"}},"created_at":"2026-07-05T01:59:16.622343+00:00","updated_at":"2026-07-05T01:59:16.622343+00:00"}