{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BVMPWIFGA7AQ6MUQLO225DDE2I","short_pith_number":"pith:BVMPWIFG","schema_version":"1.0","canonical_sha256":"0d58fb20a607c10f32905bb5ae8c64d22002d0f934dd68854f0f984872a81b40","source":{"kind":"arxiv","id":"2411.00247","version":1},"attestation_state":"computed","paper":{"title":"Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alan Jeffares, Alicia Curth, Mihaela van der Schaar","submitted_at":"2024-10-31T22:54:34Z","abstract_excerpt":"Deep learning sometimes appears to work in unexpected ways. In pursuit of a deeper understanding of its surprising behaviors, we investigate the utility of a simple yet accurate model of a trained neural network consisting of a sequence of first-order approximations telescoping out into a single empirically operational tool for practical analysis. Across three case studies, we illustrate how it can be applied to derive new empirical insights on a diverse range of prominent phenomena in the literature -- including double descent, grokking, linear mode connectivity, and the challenges of applyin"},"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":"2411.00247","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-31T22:54:34Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"aee7fda5a9e1c240bdbaa33f41a2e7c5aac425cd2a6309c7d75ca2cb1f193b6a","abstract_canon_sha256":"abc54ba59d3ade6b08775cde6534406884287add15603cea1e60584b8435cfe2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:39.643463Z","signature_b64":"dgGAWo9d+x4dXMIfCAhBm1JPZ6MxYg11DPWVhmB/PVogRr9EUzo3/mcnvfqyFWJqLydMnPHiDPrvAHkXpd6rCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d58fb20a607c10f32905bb5ae8c64d22002d0f934dd68854f0f984872a81b40","last_reissued_at":"2026-07-05T09:29:39.642984Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:39.642984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alan Jeffares, Alicia Curth, Mihaela van der Schaar","submitted_at":"2024-10-31T22:54:34Z","abstract_excerpt":"Deep learning sometimes appears to work in unexpected ways. In pursuit of a deeper understanding of its surprising behaviors, we investigate the utility of a simple yet accurate model of a trained neural network consisting of a sequence of first-order approximations telescoping out into a single empirically operational tool for practical analysis. Across three case studies, we illustrate how it can be applied to derive new empirical insights on a diverse range of prominent phenomena in the literature -- including double descent, grokking, linear mode connectivity, and the challenges of applyin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00247","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/2411.00247/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":"2411.00247","created_at":"2026-07-05T09:29:39.643037+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.00247v1","created_at":"2026-07-05T09:29:39.643037+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00247","created_at":"2026-07-05T09:29:39.643037+00:00"},{"alias_kind":"pith_short_12","alias_value":"BVMPWIFGA7AQ","created_at":"2026-07-05T09:29:39.643037+00:00"},{"alias_kind":"pith_short_16","alias_value":"BVMPWIFGA7AQ6MUQ","created_at":"2026-07-05T09:29:39.643037+00:00"},{"alias_kind":"pith_short_8","alias_value":"BVMPWIFG","created_at":"2026-07-05T09:29:39.643037+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.23286","citing_title":"Not All Explanations for Deep Learning Phenomena Are Equally Valuable","ref_index":2023,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BVMPWIFGA7AQ6MUQLO225DDE2I","json":"https://pith.science/pith/BVMPWIFGA7AQ6MUQLO225DDE2I.json","graph_json":"https://pith.science/api/pith-number/BVMPWIFGA7AQ6MUQLO225DDE2I/graph.json","events_json":"https://pith.science/api/pith-number/BVMPWIFGA7AQ6MUQLO225DDE2I/events.json","paper":"https://pith.science/paper/BVMPWIFG"},"agent_actions":{"view_html":"https://pith.science/pith/BVMPWIFGA7AQ6MUQLO225DDE2I","download_json":"https://pith.science/pith/BVMPWIFGA7AQ6MUQLO225DDE2I.json","view_paper":"https://pith.science/paper/BVMPWIFG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.00247&json=true","fetch_graph":"https://pith.science/api/pith-number/BVMPWIFGA7AQ6MUQLO225DDE2I/graph.json","fetch_events":"https://pith.science/api/pith-number/BVMPWIFGA7AQ6MUQLO225DDE2I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BVMPWIFGA7AQ6MUQLO225DDE2I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BVMPWIFGA7AQ6MUQLO225DDE2I/action/storage_attestation","attest_author":"https://pith.science/pith/BVMPWIFGA7AQ6MUQLO225DDE2I/action/author_attestation","sign_citation":"https://pith.science/pith/BVMPWIFGA7AQ6MUQLO225DDE2I/action/citation_signature","submit_replication":"https://pith.science/pith/BVMPWIFGA7AQ6MUQLO225DDE2I/action/replication_record"}},"created_at":"2026-07-05T09:29:39.643037+00:00","updated_at":"2026-07-05T09:29:39.643037+00:00"}