{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZP7BTB3WLAVMJVKCQXOFLG33AV","short_pith_number":"pith:ZP7BTB3W","schema_version":"1.0","canonical_sha256":"cbfe198776582ac4d54285dc559b7b0567324614a5764ee9e8ca56348cd0bacb","source":{"kind":"arxiv","id":"2410.14470","version":1},"attestation_state":"computed","paper":{"title":"How Do Training Methods Influence the Utilization of Vision Models?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Janis Keuper, Margret Keuper, Paul Gavrikov, Shashank Agnihotri","submitted_at":"2024-10-18T13:54:46Z","abstract_excerpt":"Not all learnable parameters (e.g., weights) contribute equally to a neural network's decision function. In fact, entire layers' parameters can sometimes be reset to random values with little to no impact on the model's decisions. We revisit earlier studies that examined how architecture and task complexity influence this phenomenon and ask: is this phenomenon also affected by how we train the model? We conducted experimental evaluations on a diverse set of ImageNet-1k classification models to explore this, keeping the architecture and training data constant but varying the training pipeline. "},"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":"2410.14470","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-18T13:54:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1678cc16f6989d9cf1d6e6aaa26d3c8ddb810032ff86b14401cb4cc375376e12","abstract_canon_sha256":"97817bbf8784feba24767437a0fd918e1b2cfe4ac2625e9067f425ce5edca7c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:32.901016Z","signature_b64":"o0qJMnhZboN6qqzRjkJvbvM4wIfdLQL/Qotw8Pk2E4L/NDA5cV27WIXvjpe6bleAYQZhfGmDRrKZiyEMjF9dAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbfe198776582ac4d54285dc559b7b0567324614a5764ee9e8ca56348cd0bacb","last_reissued_at":"2026-07-05T09:22:32.900656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:32.900656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Do Training Methods Influence the Utilization of Vision Models?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Janis Keuper, Margret Keuper, Paul Gavrikov, Shashank Agnihotri","submitted_at":"2024-10-18T13:54:46Z","abstract_excerpt":"Not all learnable parameters (e.g., weights) contribute equally to a neural network's decision function. In fact, entire layers' parameters can sometimes be reset to random values with little to no impact on the model's decisions. We revisit earlier studies that examined how architecture and task complexity influence this phenomenon and ask: is this phenomenon also affected by how we train the model? We conducted experimental evaluations on a diverse set of ImageNet-1k classification models to explore this, keeping the architecture and training data constant but varying the training pipeline. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14470","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/2410.14470/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":"2410.14470","created_at":"2026-07-05T09:22:32.900711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.14470v1","created_at":"2026-07-05T09:22:32.900711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14470","created_at":"2026-07-05T09:22:32.900711+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZP7BTB3WLAVM","created_at":"2026-07-05T09:22:32.900711+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZP7BTB3WLAVMJVKC","created_at":"2026-07-05T09:22:32.900711+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZP7BTB3W","created_at":"2026-07-05T09:22:32.900711+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/ZP7BTB3WLAVMJVKCQXOFLG33AV","json":"https://pith.science/pith/ZP7BTB3WLAVMJVKCQXOFLG33AV.json","graph_json":"https://pith.science/api/pith-number/ZP7BTB3WLAVMJVKCQXOFLG33AV/graph.json","events_json":"https://pith.science/api/pith-number/ZP7BTB3WLAVMJVKCQXOFLG33AV/events.json","paper":"https://pith.science/paper/ZP7BTB3W"},"agent_actions":{"view_html":"https://pith.science/pith/ZP7BTB3WLAVMJVKCQXOFLG33AV","download_json":"https://pith.science/pith/ZP7BTB3WLAVMJVKCQXOFLG33AV.json","view_paper":"https://pith.science/paper/ZP7BTB3W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.14470&json=true","fetch_graph":"https://pith.science/api/pith-number/ZP7BTB3WLAVMJVKCQXOFLG33AV/graph.json","fetch_events":"https://pith.science/api/pith-number/ZP7BTB3WLAVMJVKCQXOFLG33AV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZP7BTB3WLAVMJVKCQXOFLG33AV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZP7BTB3WLAVMJVKCQXOFLG33AV/action/storage_attestation","attest_author":"https://pith.science/pith/ZP7BTB3WLAVMJVKCQXOFLG33AV/action/author_attestation","sign_citation":"https://pith.science/pith/ZP7BTB3WLAVMJVKCQXOFLG33AV/action/citation_signature","submit_replication":"https://pith.science/pith/ZP7BTB3WLAVMJVKCQXOFLG33AV/action/replication_record"}},"created_at":"2026-07-05T09:22:32.900711+00:00","updated_at":"2026-07-05T09:22:32.900711+00:00"}