{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WHH26DLQZVRCAGX6ZXKTNEHNK5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"964757152874ef95b6511d09d36f3f8c2bbd83e02ac44e68c220389ded2a6fa9","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-08T18:49:09Z","title_canon_sha256":"289cd8f042f4d1233113b8ba2f0a14b5cb6f56565c826af35e629d921887aeb0"},"schema_version":"1.0","source":{"id":"2402.05913","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05913","created_at":"2026-07-05T09:19:54Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05913v2","created_at":"2026-07-05T09:19:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05913","created_at":"2026-07-05T09:19:54Z"},{"alias_kind":"pith_short_12","alias_value":"WHH26DLQZVRC","created_at":"2026-07-05T09:19:54Z"},{"alias_kind":"pith_short_16","alias_value":"WHH26DLQZVRCAGX6","created_at":"2026-07-05T09:19:54Z"},{"alias_kind":"pith_short_8","alias_value":"WHH26DLQ","created_at":"2026-07-05T09:19:54Z"}],"graph_snapshots":[{"event_id":"sha256:b12ab5e12d9896f913f527baf6d3403573b62438a5e4b50450ec248653c55004","target":"graph","created_at":"2026-07-05T09:19:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.05913/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent developments in large language models have sparked interest in efficient pretraining methods. Stagewise training approaches to improve efficiency, like gradual stacking and layer dropping (Reddi et al, 2023; Zhang & He, 2020), have recently garnered attention. The prevailing view suggests that stagewise dropping strategies, such as layer dropping, are ineffective, especially when compared to stacking-based approaches. This paper challenges this notion by demonstrating that, with proper design, dropping strategies can be competitive, if not better, than stacking methods. Specifically, we","authors_text":"Abhishek Panigrahi, Kaifeng Lyu, Nikunj Saunshi, Sanjiv Kumar, Sashank Reddi, Satyen Kale, Sobhan Miryoosefi","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-08T18:49:09Z","title":"Efficient Stagewise Pretraining via Progressive Subnetworks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05913","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4c251c52eb613ff6370ce20f55ac97621e3f78cefd39117ae86725dd5da973e0","target":"record","created_at":"2026-07-05T09:19:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"964757152874ef95b6511d09d36f3f8c2bbd83e02ac44e68c220389ded2a6fa9","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-08T18:49:09Z","title_canon_sha256":"289cd8f042f4d1233113b8ba2f0a14b5cb6f56565c826af35e629d921887aeb0"},"schema_version":"1.0","source":{"id":"2402.05913","kind":"arxiv","version":2}},"canonical_sha256":"b1cfaf0d70cd62201afecdd53690ed57475a1bda03bdd2c62c842c2a524d10de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1cfaf0d70cd62201afecdd53690ed57475a1bda03bdd2c62c842c2a524d10de","first_computed_at":"2026-07-05T09:19:54.035498Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:54.035498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B0Vy8QgRfMw2ZOofrehMSWReTn8Iu476pUo1KuxhSNN0hxe0uhSu+9yZrnpnwD82bjlYh5Z9A1ecHIgLOwoeAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:54.035957Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.05913","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c251c52eb613ff6370ce20f55ac97621e3f78cefd39117ae86725dd5da973e0","sha256:b12ab5e12d9896f913f527baf6d3403573b62438a5e4b50450ec248653c55004"],"state_sha256":"894fdd2597d582254398a64bbb28be5d6a878a5d6c9a5b9d37458841da8ff61c"}