{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QQG3FRW4IQY6RVRWNWUVNCXMVU","short_pith_number":"pith:QQG3FRW4","schema_version":"1.0","canonical_sha256":"840db2c6dc4431e8d6366da9568aecad0b704fc99be331e1e5a64bccb96359f0","source":{"kind":"arxiv","id":"2309.07537","version":2},"attestation_state":"computed","paper":{"title":"Towards a universal mechanism for successful deep learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ido Kanter, Ofek Tevet, Shiri Hodassman, Yarden Tzach, Yuval Meir","submitted_at":"2023-09-14T09:03:57Z","abstract_excerpt":"Recently, the underlying mechanism for successful deep learning (DL) was presented based on a quantitative method that measures the quality of a single filter in each layer of a DL model, particularly VGG-16 trained on CIFAR-10. This method exemplifies that each filter identifies small clusters of possible output labels, with additional noise selected as labels outside the clusters. This feature is progressively sharpened with each layer, resulting in an enhanced signal-to-noise ratio (SNR), which leads to an increase in the accuracy of the DL network. In this study, this mechanism is verified"},"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":"2309.07537","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-14T09:03:57Z","cross_cats_sorted":[],"title_canon_sha256":"8b9b7c0ea6f87111b5591c2126ac6ee86e265de3be8c3842e035e38d8e60a1b6","abstract_canon_sha256":"060ca90f66777b0358b5d53523ca5ac3ce779dccb8ee1323470ef465edc813ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:51.210494Z","signature_b64":"Gq8bTSXAC5C7z8a4UIApOB3e8wckKCwpB7N4GQv/MMjowZ78ZG7gYcZSwEMQlJMRJM8nPJhn9MYi05bwZP3KCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"840db2c6dc4431e8d6366da9568aecad0b704fc99be331e1e5a64bccb96359f0","last_reissued_at":"2026-07-05T07:54:51.210046Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:51.210046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards a universal mechanism for successful deep learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ido Kanter, Ofek Tevet, Shiri Hodassman, Yarden Tzach, Yuval Meir","submitted_at":"2023-09-14T09:03:57Z","abstract_excerpt":"Recently, the underlying mechanism for successful deep learning (DL) was presented based on a quantitative method that measures the quality of a single filter in each layer of a DL model, particularly VGG-16 trained on CIFAR-10. This method exemplifies that each filter identifies small clusters of possible output labels, with additional noise selected as labels outside the clusters. This feature is progressively sharpened with each layer, resulting in an enhanced signal-to-noise ratio (SNR), which leads to an increase in the accuracy of the DL network. In this study, this mechanism is verified"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07537","kind":"arxiv","version":2},"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/2309.07537/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":"2309.07537","created_at":"2026-07-05T07:54:51.210104+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.07537v2","created_at":"2026-07-05T07:54:51.210104+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07537","created_at":"2026-07-05T07:54:51.210104+00:00"},{"alias_kind":"pith_short_12","alias_value":"QQG3FRW4IQY6","created_at":"2026-07-05T07:54:51.210104+00:00"},{"alias_kind":"pith_short_16","alias_value":"QQG3FRW4IQY6RVRW","created_at":"2026-07-05T07:54:51.210104+00:00"},{"alias_kind":"pith_short_8","alias_value":"QQG3FRW4","created_at":"2026-07-05T07:54:51.210104+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.03407","citing_title":"Learning Mechanism Underlying NLP Pre-Training and Fine-Tuning","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QQG3FRW4IQY6RVRWNWUVNCXMVU","json":"https://pith.science/pith/QQG3FRW4IQY6RVRWNWUVNCXMVU.json","graph_json":"https://pith.science/api/pith-number/QQG3FRW4IQY6RVRWNWUVNCXMVU/graph.json","events_json":"https://pith.science/api/pith-number/QQG3FRW4IQY6RVRWNWUVNCXMVU/events.json","paper":"https://pith.science/paper/QQG3FRW4"},"agent_actions":{"view_html":"https://pith.science/pith/QQG3FRW4IQY6RVRWNWUVNCXMVU","download_json":"https://pith.science/pith/QQG3FRW4IQY6RVRWNWUVNCXMVU.json","view_paper":"https://pith.science/paper/QQG3FRW4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.07537&json=true","fetch_graph":"https://pith.science/api/pith-number/QQG3FRW4IQY6RVRWNWUVNCXMVU/graph.json","fetch_events":"https://pith.science/api/pith-number/QQG3FRW4IQY6RVRWNWUVNCXMVU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QQG3FRW4IQY6RVRWNWUVNCXMVU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QQG3FRW4IQY6RVRWNWUVNCXMVU/action/storage_attestation","attest_author":"https://pith.science/pith/QQG3FRW4IQY6RVRWNWUVNCXMVU/action/author_attestation","sign_citation":"https://pith.science/pith/QQG3FRW4IQY6RVRWNWUVNCXMVU/action/citation_signature","submit_replication":"https://pith.science/pith/QQG3FRW4IQY6RVRWNWUVNCXMVU/action/replication_record"}},"created_at":"2026-07-05T07:54:51.210104+00:00","updated_at":"2026-07-05T07:54:51.210104+00:00"}