{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3YIS3YQJAZIJDWW2LHGSGK5EFU","short_pith_number":"pith:3YIS3YQJ","schema_version":"1.0","canonical_sha256":"de112de209065091dada59cd232ba42d3b8ecbe8ee20a4b041b7ca8e4d31ed67","source":{"kind":"arxiv","id":"2406.14971","version":1},"attestation_state":"computed","paper":{"title":"Domain Adaptation of Llama3-70B-Instruct through Continual Pre-Training and Model Merging: A Comprehensive Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anneketh Vij, Charles Goddard, Fernando Fernandes Neto, Jacob Solawetz, Lucas Atkins, Luke Meyers, Mark McQuade, Mary MacCarthy, Shamane Siriwardhana, Thomas Gauthier, Tyler Odenthal","submitted_at":"2024-06-21T08:29:31Z","abstract_excerpt":"We conducted extensive experiments on domain adaptation of the Meta-Llama-3-70B-Instruct model on SEC data, exploring its performance on both general and domain-specific benchmarks. Our focus included continual pre-training (CPT) and model merging, aiming to enhance the model's domain-specific capabilities while mitigating catastrophic forgetting. Through this study, we evaluated the impact of integrating financial regulatory data into a robust language model and examined the effectiveness of our model merging techniques in preserving and improving the model's instructive abilities. The model "},"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":"2406.14971","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T08:29:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d6d1bbda8a553557580b55a342907bc72d447283f16dbd0d676c44ca78fcc133","abstract_canon_sha256":"0849074d9999e5953bd5fa47e930cc5297b04b6660236f42a76cdf803af07563"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:11.362890Z","signature_b64":"6fIG06TSEFm2QI/bfWtCW561YUB8PY8tEjxijcLqzbkVA00hOgzBjNXUG0CI2D2ay5qagN6DZ6zjnddDfm9IDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de112de209065091dada59cd232ba42d3b8ecbe8ee20a4b041b7ca8e4d31ed67","last_reissued_at":"2026-07-05T08:35:11.362491Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:11.362491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain Adaptation of Llama3-70B-Instruct through Continual Pre-Training and Model Merging: A Comprehensive Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anneketh Vij, Charles Goddard, Fernando Fernandes Neto, Jacob Solawetz, Lucas Atkins, Luke Meyers, Mark McQuade, Mary MacCarthy, Shamane Siriwardhana, Thomas Gauthier, Tyler Odenthal","submitted_at":"2024-06-21T08:29:31Z","abstract_excerpt":"We conducted extensive experiments on domain adaptation of the Meta-Llama-3-70B-Instruct model on SEC data, exploring its performance on both general and domain-specific benchmarks. Our focus included continual pre-training (CPT) and model merging, aiming to enhance the model's domain-specific capabilities while mitigating catastrophic forgetting. Through this study, we evaluated the impact of integrating financial regulatory data into a robust language model and examined the effectiveness of our model merging techniques in preserving and improving the model's instructive abilities. The model "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14971","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/2406.14971/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":"2406.14971","created_at":"2026-07-05T08:35:11.362549+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14971v1","created_at":"2026-07-05T08:35:11.362549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14971","created_at":"2026-07-05T08:35:11.362549+00:00"},{"alias_kind":"pith_short_12","alias_value":"3YIS3YQJAZIJ","created_at":"2026-07-05T08:35:11.362549+00:00"},{"alias_kind":"pith_short_16","alias_value":"3YIS3YQJAZIJDWW2","created_at":"2026-07-05T08:35:11.362549+00:00"},{"alias_kind":"pith_short_8","alias_value":"3YIS3YQJ","created_at":"2026-07-05T08:35:11.362549+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.09056","citing_title":"Adapting Language-Specific LLMs to a Reasoning Model in One Day via Model Merging -- An Open Recipe","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3YIS3YQJAZIJDWW2LHGSGK5EFU","json":"https://pith.science/pith/3YIS3YQJAZIJDWW2LHGSGK5EFU.json","graph_json":"https://pith.science/api/pith-number/3YIS3YQJAZIJDWW2LHGSGK5EFU/graph.json","events_json":"https://pith.science/api/pith-number/3YIS3YQJAZIJDWW2LHGSGK5EFU/events.json","paper":"https://pith.science/paper/3YIS3YQJ"},"agent_actions":{"view_html":"https://pith.science/pith/3YIS3YQJAZIJDWW2LHGSGK5EFU","download_json":"https://pith.science/pith/3YIS3YQJAZIJDWW2LHGSGK5EFU.json","view_paper":"https://pith.science/paper/3YIS3YQJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14971&json=true","fetch_graph":"https://pith.science/api/pith-number/3YIS3YQJAZIJDWW2LHGSGK5EFU/graph.json","fetch_events":"https://pith.science/api/pith-number/3YIS3YQJAZIJDWW2LHGSGK5EFU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3YIS3YQJAZIJDWW2LHGSGK5EFU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3YIS3YQJAZIJDWW2LHGSGK5EFU/action/storage_attestation","attest_author":"https://pith.science/pith/3YIS3YQJAZIJDWW2LHGSGK5EFU/action/author_attestation","sign_citation":"https://pith.science/pith/3YIS3YQJAZIJDWW2LHGSGK5EFU/action/citation_signature","submit_replication":"https://pith.science/pith/3YIS3YQJAZIJDWW2LHGSGK5EFU/action/replication_record"}},"created_at":"2026-07-05T08:35:11.362549+00:00","updated_at":"2026-07-05T08:35:11.362549+00:00"}