{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HMCJ2UDIZOLP4PVO3PRIGUWYWK","short_pith_number":"pith:HMCJ2UDI","schema_version":"1.0","canonical_sha256":"3b049d5068cb96fe3eaedbe28352d8b288703c7b47e659d7a806861a34b9a5b3","source":{"kind":"arxiv","id":"2406.01589","version":2},"attestation_state":"computed","paper":{"title":"Tilting the Odds at the Lottery: the Interplay of Overparameterisation and Curricula in Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.LG","q-bio.NC"],"primary_cat":"stat.ML","authors_text":"Andrew Saxe, Luca Saglietti, Stefano Sarao Mannelli, Yaraslau Ivashynka","submitted_at":"2024-06-03T17:59:33Z","abstract_excerpt":"A wide range of empirical and theoretical works have shown that overparameterisation can amplify the performance of neural networks. According to the lottery ticket hypothesis, overparameterised networks have an increased chance of containing a sub-network that is well-initialised to solve the task at hand. A more parsimonious approach, inspired by animal learning, consists in guiding the learner towards solving the task by curating the order of the examples, i.e. providing a curriculum. However, this learning strategy seems to be hardly beneficial in deep learning applications. In this work, "},"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":"2406.01589","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-06-03T17:59:33Z","cross_cats_sorted":["cond-mat.dis-nn","cs.LG","q-bio.NC"],"title_canon_sha256":"375bf3e8f3cd0ef5c1ecef2c861b95182caa42833c061a72be8f27b7783eb6b8","abstract_canon_sha256":"0e9d48bd868dc9cf303a5d8be79b282b19484ab1dd80655b329421459b4a8252"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:42.852026Z","signature_b64":"SDtpwK/IVGGzyin9bLP0PT7aqnjxU/4Bg36YohjuYwkIXSK6dVQTfW2M/cwjQDVsaj+15HlTHNde+bPggl8VDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b049d5068cb96fe3eaedbe28352d8b288703c7b47e659d7a806861a34b9a5b3","last_reissued_at":"2026-07-05T09:17:42.851536Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:42.851536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tilting the Odds at the Lottery: the Interplay of Overparameterisation and Curricula in Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.LG","q-bio.NC"],"primary_cat":"stat.ML","authors_text":"Andrew Saxe, Luca Saglietti, Stefano Sarao Mannelli, Yaraslau Ivashynka","submitted_at":"2024-06-03T17:59:33Z","abstract_excerpt":"A wide range of empirical and theoretical works have shown that overparameterisation can amplify the performance of neural networks. According to the lottery ticket hypothesis, overparameterised networks have an increased chance of containing a sub-network that is well-initialised to solve the task at hand. A more parsimonious approach, inspired by animal learning, consists in guiding the learner towards solving the task by curating the order of the examples, i.e. providing a curriculum. However, this learning strategy seems to be hardly beneficial in deep learning applications. In this work, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01589","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/2406.01589/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":"2406.01589","created_at":"2026-07-05T09:17:42.851596+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01589v2","created_at":"2026-07-05T09:17:42.851596+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01589","created_at":"2026-07-05T09:17:42.851596+00:00"},{"alias_kind":"pith_short_12","alias_value":"HMCJ2UDIZOLP","created_at":"2026-07-05T09:17:42.851596+00:00"},{"alias_kind":"pith_short_16","alias_value":"HMCJ2UDIZOLP4PVO","created_at":"2026-07-05T09:17:42.851596+00:00"},{"alias_kind":"pith_short_8","alias_value":"HMCJ2UDI","created_at":"2026-07-05T09:17:42.851596+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10237","citing_title":"The Benefits of Temporal Correlations: SGD Learns k-Juntas from Random Walks Efficiently","ref_index":127,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HMCJ2UDIZOLP4PVO3PRIGUWYWK","json":"https://pith.science/pith/HMCJ2UDIZOLP4PVO3PRIGUWYWK.json","graph_json":"https://pith.science/api/pith-number/HMCJ2UDIZOLP4PVO3PRIGUWYWK/graph.json","events_json":"https://pith.science/api/pith-number/HMCJ2UDIZOLP4PVO3PRIGUWYWK/events.json","paper":"https://pith.science/paper/HMCJ2UDI"},"agent_actions":{"view_html":"https://pith.science/pith/HMCJ2UDIZOLP4PVO3PRIGUWYWK","download_json":"https://pith.science/pith/HMCJ2UDIZOLP4PVO3PRIGUWYWK.json","view_paper":"https://pith.science/paper/HMCJ2UDI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01589&json=true","fetch_graph":"https://pith.science/api/pith-number/HMCJ2UDIZOLP4PVO3PRIGUWYWK/graph.json","fetch_events":"https://pith.science/api/pith-number/HMCJ2UDIZOLP4PVO3PRIGUWYWK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HMCJ2UDIZOLP4PVO3PRIGUWYWK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HMCJ2UDIZOLP4PVO3PRIGUWYWK/action/storage_attestation","attest_author":"https://pith.science/pith/HMCJ2UDIZOLP4PVO3PRIGUWYWK/action/author_attestation","sign_citation":"https://pith.science/pith/HMCJ2UDIZOLP4PVO3PRIGUWYWK/action/citation_signature","submit_replication":"https://pith.science/pith/HMCJ2UDIZOLP4PVO3PRIGUWYWK/action/replication_record"}},"created_at":"2026-07-05T09:17:42.851596+00:00","updated_at":"2026-07-05T09:17:42.851596+00:00"}