{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LKF7WYUSXSRAFQJBMLXNUH7JBH","short_pith_number":"pith:LKF7WYUS","schema_version":"1.0","canonical_sha256":"5a8bfb6292bca202c12162eeda1fe909f0da85a0f516754c9e9738c67cbea5e1","source":{"kind":"arxiv","id":"2412.15077","version":1},"attestation_state":"computed","paper":{"title":"Till the Layers Collapse: Compressing a Deep Neural Network through the Lenses of Batch Normalization Layers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Enzo Tartaglione, Nour Hezbri, Van-Tam Nguyen, Victor Qu\\'etu, Zhu Liao","submitted_at":"2024-12-19T17:26:07Z","abstract_excerpt":"Today, deep neural networks are widely used since they can handle a variety of complex tasks. Their generality makes them very powerful tools in modern technology. However, deep neural networks are often overparameterized. The usage of these large models consumes a lot of computation resources. In this paper, we introduce a method called \\textbf{T}ill the \\textbf{L}ayers \\textbf{C}ollapse (TLC), which compresses deep neural networks through the lenses of batch normalization layers. By reducing the depth of these networks, our method decreases deep neural networks' computational requirements an"},"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":"2412.15077","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T17:26:07Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"11ae610147ca9675bb83e86450eae409ebae130ce0b8bf8cca7bcd7b3aa49a7a","abstract_canon_sha256":"18bedfd39ebc0791af70d6e536b078f52fe2c598c1793ea234cf5ee10edd6cf7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:57.627693Z","signature_b64":"uaAkR2wRZoj+Y+BnFUg6ofaRI2MimW8VY4WDrPZPihuoIDSMMJX+QhbivBM21jijZqq/7bSVpbdEYgydBRowCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a8bfb6292bca202c12162eeda1fe909f0da85a0f516754c9e9738c67cbea5e1","last_reissued_at":"2026-07-05T09:51:57.627265Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:57.627265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Till the Layers Collapse: Compressing a Deep Neural Network through the Lenses of Batch Normalization Layers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Enzo Tartaglione, Nour Hezbri, Van-Tam Nguyen, Victor Qu\\'etu, Zhu Liao","submitted_at":"2024-12-19T17:26:07Z","abstract_excerpt":"Today, deep neural networks are widely used since they can handle a variety of complex tasks. Their generality makes them very powerful tools in modern technology. However, deep neural networks are often overparameterized. The usage of these large models consumes a lot of computation resources. In this paper, we introduce a method called \\textbf{T}ill the \\textbf{L}ayers \\textbf{C}ollapse (TLC), which compresses deep neural networks through the lenses of batch normalization layers. By reducing the depth of these networks, our method decreases deep neural networks' computational requirements an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15077","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/2412.15077/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":"2412.15077","created_at":"2026-07-05T09:51:57.627324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.15077v1","created_at":"2026-07-05T09:51:57.627324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15077","created_at":"2026-07-05T09:51:57.627324+00:00"},{"alias_kind":"pith_short_12","alias_value":"LKF7WYUSXSRA","created_at":"2026-07-05T09:51:57.627324+00:00"},{"alias_kind":"pith_short_16","alias_value":"LKF7WYUSXSRAFQJB","created_at":"2026-07-05T09:51:57.627324+00:00"},{"alias_kind":"pith_short_8","alias_value":"LKF7WYUS","created_at":"2026-07-05T09:51:57.627324+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/LKF7WYUSXSRAFQJBMLXNUH7JBH","json":"https://pith.science/pith/LKF7WYUSXSRAFQJBMLXNUH7JBH.json","graph_json":"https://pith.science/api/pith-number/LKF7WYUSXSRAFQJBMLXNUH7JBH/graph.json","events_json":"https://pith.science/api/pith-number/LKF7WYUSXSRAFQJBMLXNUH7JBH/events.json","paper":"https://pith.science/paper/LKF7WYUS"},"agent_actions":{"view_html":"https://pith.science/pith/LKF7WYUSXSRAFQJBMLXNUH7JBH","download_json":"https://pith.science/pith/LKF7WYUSXSRAFQJBMLXNUH7JBH.json","view_paper":"https://pith.science/paper/LKF7WYUS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.15077&json=true","fetch_graph":"https://pith.science/api/pith-number/LKF7WYUSXSRAFQJBMLXNUH7JBH/graph.json","fetch_events":"https://pith.science/api/pith-number/LKF7WYUSXSRAFQJBMLXNUH7JBH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LKF7WYUSXSRAFQJBMLXNUH7JBH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LKF7WYUSXSRAFQJBMLXNUH7JBH/action/storage_attestation","attest_author":"https://pith.science/pith/LKF7WYUSXSRAFQJBMLXNUH7JBH/action/author_attestation","sign_citation":"https://pith.science/pith/LKF7WYUSXSRAFQJBMLXNUH7JBH/action/citation_signature","submit_replication":"https://pith.science/pith/LKF7WYUSXSRAFQJBMLXNUH7JBH/action/replication_record"}},"created_at":"2026-07-05T09:51:57.627324+00:00","updated_at":"2026-07-05T09:51:57.627324+00:00"}