{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NTEURLT3PTX3U6IK455EPI6STA","short_pith_number":"pith:NTEURLT3","schema_version":"1.0","canonical_sha256":"6cc948ae7b7cefba790ae77a47a3d2982e7728cec92f4ed26515fdddaed04849","source":{"kind":"arxiv","id":"2310.07999","version":1},"attestation_state":"computed","paper":{"title":"LEMON: Lossless model expansion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cong Xie, Haibin Lin, Hanlin Lu, Hongxia Yang, Jiahao Su, Jianbo Yuan, Ruoyu Sun, Tianyi Liu, Yite Wang","submitted_at":"2023-10-12T03:02:41Z","abstract_excerpt":"Scaling of deep neural networks, especially Transformers, is pivotal for their surging performance and has further led to the emergence of sophisticated reasoning capabilities in foundation models. Such scaling generally requires training large models from scratch with random initialization, failing to leverage the knowledge acquired by their smaller counterparts, which are already resource-intensive to obtain. To tackle this inefficiency, we present $\\textbf{L}$ossl$\\textbf{E}$ss $\\textbf{MO}$del Expansio$\\textbf{N}$ (LEMON), a recipe to initialize scaled models using the weights of their sma"},"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":"2310.07999","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-12T03:02:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a0b7d750069a06432b41426fb862432daabc5d098ec783844e9d3cb582a28d54","abstract_canon_sha256":"4add0579c6b441b99795eb5cc53b69c46b41cae4a7d47e15e0705b3777ba04c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:59.146202Z","signature_b64":"GBwdZ9rTk/+tgNDDF/RifirBxgS/G7XvtkR9WQJzZ7x3JIz47HZYh7ifzG/ea4tbbHiNoBHi73zLvuAMIzMkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cc948ae7b7cefba790ae77a47a3d2982e7728cec92f4ed26515fdddaed04849","last_reissued_at":"2026-07-05T06:59:59.145723Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:59.145723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LEMON: Lossless model expansion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cong Xie, Haibin Lin, Hanlin Lu, Hongxia Yang, Jiahao Su, Jianbo Yuan, Ruoyu Sun, Tianyi Liu, Yite Wang","submitted_at":"2023-10-12T03:02:41Z","abstract_excerpt":"Scaling of deep neural networks, especially Transformers, is pivotal for their surging performance and has further led to the emergence of sophisticated reasoning capabilities in foundation models. Such scaling generally requires training large models from scratch with random initialization, failing to leverage the knowledge acquired by their smaller counterparts, which are already resource-intensive to obtain. To tackle this inefficiency, we present $\\textbf{L}$ossl$\\textbf{E}$ss $\\textbf{MO}$del Expansio$\\textbf{N}$ (LEMON), a recipe to initialize scaled models using the weights of their sma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07999","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/2310.07999/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":"2310.07999","created_at":"2026-07-05T06:59:59.145783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.07999v1","created_at":"2026-07-05T06:59:59.145783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07999","created_at":"2026-07-05T06:59:59.145783+00:00"},{"alias_kind":"pith_short_12","alias_value":"NTEURLT3PTX3","created_at":"2026-07-05T06:59:59.145783+00:00"},{"alias_kind":"pith_short_16","alias_value":"NTEURLT3PTX3U6IK","created_at":"2026-07-05T06:59:59.145783+00:00"},{"alias_kind":"pith_short_8","alias_value":"NTEURLT3","created_at":"2026-07-05T06:59:59.145783+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/NTEURLT3PTX3U6IK455EPI6STA","json":"https://pith.science/pith/NTEURLT3PTX3U6IK455EPI6STA.json","graph_json":"https://pith.science/api/pith-number/NTEURLT3PTX3U6IK455EPI6STA/graph.json","events_json":"https://pith.science/api/pith-number/NTEURLT3PTX3U6IK455EPI6STA/events.json","paper":"https://pith.science/paper/NTEURLT3"},"agent_actions":{"view_html":"https://pith.science/pith/NTEURLT3PTX3U6IK455EPI6STA","download_json":"https://pith.science/pith/NTEURLT3PTX3U6IK455EPI6STA.json","view_paper":"https://pith.science/paper/NTEURLT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.07999&json=true","fetch_graph":"https://pith.science/api/pith-number/NTEURLT3PTX3U6IK455EPI6STA/graph.json","fetch_events":"https://pith.science/api/pith-number/NTEURLT3PTX3U6IK455EPI6STA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NTEURLT3PTX3U6IK455EPI6STA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NTEURLT3PTX3U6IK455EPI6STA/action/storage_attestation","attest_author":"https://pith.science/pith/NTEURLT3PTX3U6IK455EPI6STA/action/author_attestation","sign_citation":"https://pith.science/pith/NTEURLT3PTX3U6IK455EPI6STA/action/citation_signature","submit_replication":"https://pith.science/pith/NTEURLT3PTX3U6IK455EPI6STA/action/replication_record"}},"created_at":"2026-07-05T06:59:59.145783+00:00","updated_at":"2026-07-05T06:59:59.145783+00:00"}