{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PNVK4L7SX6YDJSDE6HGCP6GW3I","short_pith_number":"pith:PNVK4L7S","schema_version":"1.0","canonical_sha256":"7b6aae2ff2bfb034c864f1cc27f8d6da228d66f12b58368f907b5714d9055e53","source":{"kind":"arxiv","id":"2502.04030","version":2},"attestation_state":"computed","paper":{"title":"Fine, I'll Merge It Myself: A Multi-Fidelity Framework for Automated Model Merging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Guinan Su, Jonas Geiping","submitted_at":"2025-02-06T12:47:25Z","abstract_excerpt":"Reasoning capabilities represent a critical frontier for large language models (LLMs), but developing them requires extensive proprietary datasets and computational resources. One way to efficiently supplement capabilities with is by model merging, which offers a promising alternative by combining multiple models without retraining. However, current merging approaches rely on manually-designed strategies for merging hyperparameters, limiting the exploration of potential model combinations and requiring significant human effort. We propose an Automated Model Merging Framework that enables fine-"},"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":"2502.04030","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-06T12:47:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4a9601cbf279131142f39004078c3654390e164ac298e0f2ae34d44089771657","abstract_canon_sha256":"ba647ab8e445c5a0d1a9a26ac03701a7e416ac8427225d4a6e87f0be78d22f14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:47.498218Z","signature_b64":"1B8Lr7Vm++kCBTIP3xNG00l4FbsWekJlB8HvMGA74aEBg56XilZCok76Zrp9wIvYsVsBE0V3HI6OnURY12A6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b6aae2ff2bfb034c864f1cc27f8d6da228d66f12b58368f907b5714d9055e53","last_reissued_at":"2026-07-05T11:26:47.497737Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:47.497737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine, I'll Merge It Myself: A Multi-Fidelity Framework for Automated Model Merging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Guinan Su, Jonas Geiping","submitted_at":"2025-02-06T12:47:25Z","abstract_excerpt":"Reasoning capabilities represent a critical frontier for large language models (LLMs), but developing them requires extensive proprietary datasets and computational resources. One way to efficiently supplement capabilities with is by model merging, which offers a promising alternative by combining multiple models without retraining. However, current merging approaches rely on manually-designed strategies for merging hyperparameters, limiting the exploration of potential model combinations and requiring significant human effort. We propose an Automated Model Merging Framework that enables fine-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04030","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/2502.04030/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":"2502.04030","created_at":"2026-07-05T11:26:47.497794+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.04030v2","created_at":"2026-07-05T11:26:47.497794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04030","created_at":"2026-07-05T11:26:47.497794+00:00"},{"alias_kind":"pith_short_12","alias_value":"PNVK4L7SX6YD","created_at":"2026-07-05T11:26:47.497794+00:00"},{"alias_kind":"pith_short_16","alias_value":"PNVK4L7SX6YDJSDE","created_at":"2026-07-05T11:26:47.497794+00:00"},{"alias_kind":"pith_short_8","alias_value":"PNVK4L7S","created_at":"2026-07-05T11:26:47.497794+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.20480","citing_title":"GPTailor: Large Language Model Pruning Through Layer Cutting and Stitching","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PNVK4L7SX6YDJSDE6HGCP6GW3I","json":"https://pith.science/pith/PNVK4L7SX6YDJSDE6HGCP6GW3I.json","graph_json":"https://pith.science/api/pith-number/PNVK4L7SX6YDJSDE6HGCP6GW3I/graph.json","events_json":"https://pith.science/api/pith-number/PNVK4L7SX6YDJSDE6HGCP6GW3I/events.json","paper":"https://pith.science/paper/PNVK4L7S"},"agent_actions":{"view_html":"https://pith.science/pith/PNVK4L7SX6YDJSDE6HGCP6GW3I","download_json":"https://pith.science/pith/PNVK4L7SX6YDJSDE6HGCP6GW3I.json","view_paper":"https://pith.science/paper/PNVK4L7S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.04030&json=true","fetch_graph":"https://pith.science/api/pith-number/PNVK4L7SX6YDJSDE6HGCP6GW3I/graph.json","fetch_events":"https://pith.science/api/pith-number/PNVK4L7SX6YDJSDE6HGCP6GW3I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PNVK4L7SX6YDJSDE6HGCP6GW3I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PNVK4L7SX6YDJSDE6HGCP6GW3I/action/storage_attestation","attest_author":"https://pith.science/pith/PNVK4L7SX6YDJSDE6HGCP6GW3I/action/author_attestation","sign_citation":"https://pith.science/pith/PNVK4L7SX6YDJSDE6HGCP6GW3I/action/citation_signature","submit_replication":"https://pith.science/pith/PNVK4L7SX6YDJSDE6HGCP6GW3I/action/replication_record"}},"created_at":"2026-07-05T11:26:47.497794+00:00","updated_at":"2026-07-05T11:26:47.497794+00:00"}