{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MDTOGS2T5YMZ7KAZLZXEJRREQT","short_pith_number":"pith:MDTOGS2T","schema_version":"1.0","canonical_sha256":"60e6e34b53ee199fa8195e6e44c62484c3fdf16d2f7746e4c5a0622282048289","source":{"kind":"arxiv","id":"2405.15706","version":3},"attestation_state":"computed","paper":{"title":"The Impact of Geometric Complexity on Neural Collapse in Transfer Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Benoit Dherin, Javier Gonzalvo, Michael Munn","submitted_at":"2024-05-24T16:52:09Z","abstract_excerpt":"Many of the recent remarkable advances in computer vision and language models can be attributed to the success of transfer learning via the pre-training of large foundation models. However, a theoretical framework which explains this empirical success is incomplete and remains an active area of research. Flatness of the loss surface and neural collapse have recently emerged as useful pre-training metrics which shed light on the implicit biases underlying pre-training. In this paper, we explore the geometric complexity of a model's learned representations as a fundamental mechanism that relates"},"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":"2405.15706","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T16:52:09Z","cross_cats_sorted":[],"title_canon_sha256":"319b89895f2381444c46e2489ac412269f340bc95bc44ea1853895017396e71d","abstract_canon_sha256":"5079cda2dce644d05e5fb63ac24c07f49fd920c5dbe2367f67b2971fc94cdebf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:47.648389Z","signature_b64":"28npFO8UCPlV0+cG9qChYo4xcgryNHOtkgXJ7rnsQv2GZ4La/kGgohSScGIbXfggVJoWgXOw06nKBu6Av75XBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60e6e34b53ee199fa8195e6e44c62484c3fdf16d2f7746e4c5a0622282048289","last_reissued_at":"2026-07-05T09:50:47.647900Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:47.647900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Impact of Geometric Complexity on Neural Collapse in Transfer Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Benoit Dherin, Javier Gonzalvo, Michael Munn","submitted_at":"2024-05-24T16:52:09Z","abstract_excerpt":"Many of the recent remarkable advances in computer vision and language models can be attributed to the success of transfer learning via the pre-training of large foundation models. However, a theoretical framework which explains this empirical success is incomplete and remains an active area of research. Flatness of the loss surface and neural collapse have recently emerged as useful pre-training metrics which shed light on the implicit biases underlying pre-training. In this paper, we explore the geometric complexity of a model's learned representations as a fundamental mechanism that relates"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15706","kind":"arxiv","version":3},"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/2405.15706/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":"2405.15706","created_at":"2026-07-05T09:50:47.647960+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15706v3","created_at":"2026-07-05T09:50:47.647960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15706","created_at":"2026-07-05T09:50:47.647960+00:00"},{"alias_kind":"pith_short_12","alias_value":"MDTOGS2T5YMZ","created_at":"2026-07-05T09:50:47.647960+00:00"},{"alias_kind":"pith_short_16","alias_value":"MDTOGS2T5YMZ7KAZ","created_at":"2026-07-05T09:50:47.647960+00:00"},{"alias_kind":"pith_short_8","alias_value":"MDTOGS2T","created_at":"2026-07-05T09:50:47.647960+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/MDTOGS2T5YMZ7KAZLZXEJRREQT","json":"https://pith.science/pith/MDTOGS2T5YMZ7KAZLZXEJRREQT.json","graph_json":"https://pith.science/api/pith-number/MDTOGS2T5YMZ7KAZLZXEJRREQT/graph.json","events_json":"https://pith.science/api/pith-number/MDTOGS2T5YMZ7KAZLZXEJRREQT/events.json","paper":"https://pith.science/paper/MDTOGS2T"},"agent_actions":{"view_html":"https://pith.science/pith/MDTOGS2T5YMZ7KAZLZXEJRREQT","download_json":"https://pith.science/pith/MDTOGS2T5YMZ7KAZLZXEJRREQT.json","view_paper":"https://pith.science/paper/MDTOGS2T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15706&json=true","fetch_graph":"https://pith.science/api/pith-number/MDTOGS2T5YMZ7KAZLZXEJRREQT/graph.json","fetch_events":"https://pith.science/api/pith-number/MDTOGS2T5YMZ7KAZLZXEJRREQT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MDTOGS2T5YMZ7KAZLZXEJRREQT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MDTOGS2T5YMZ7KAZLZXEJRREQT/action/storage_attestation","attest_author":"https://pith.science/pith/MDTOGS2T5YMZ7KAZLZXEJRREQT/action/author_attestation","sign_citation":"https://pith.science/pith/MDTOGS2T5YMZ7KAZLZXEJRREQT/action/citation_signature","submit_replication":"https://pith.science/pith/MDTOGS2T5YMZ7KAZLZXEJRREQT/action/replication_record"}},"created_at":"2026-07-05T09:50:47.647960+00:00","updated_at":"2026-07-05T09:50:47.647960+00:00"}