{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6RKLX7VIGKCNMHUCFBYRFO7AV4","short_pith_number":"pith:6RKLX7VI","schema_version":"1.0","canonical_sha256":"f454bbfea83284d61e82287112bbe0af1bb8fc4ff1ed3b6e5e07537fb4d52c2b","source":{"kind":"arxiv","id":"2508.16204","version":1},"attestation_state":"computed","paper":{"title":"Competition and Attraction Improve Model Fusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.AI","authors_text":"Jo\\~ao Abrantes, Robert Tjarko Lange, Yujin Tang","submitted_at":"2025-08-22T08:24:02Z","abstract_excerpt":"Model merging is a powerful technique for integrating the specialized knowledge of multiple machine learning models into a single model. However, existing methods require manually partitioning model parameters into fixed groups for merging, which restricts the exploration of potential combinations and limits performance. To overcome these limitations, we propose Model Merging of Natural Niches (M2N2), an evolutionary algorithm with three key features: (1) dynamic adjustment of merging boundaries to progressively explore a broader range of parameter combinations; (2) a diversity preservation me"},"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":"2508.16204","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-22T08:24:02Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"c5fb57c71f1a6ccf0edcfa2b7cfdc23ec4eed0edc75798ea768d3f4128cc3bd1","abstract_canon_sha256":"4d9b14f00ba51471f8ca12b3194983e9d1311fbd5503b2a772714e5b5b634324"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:43.931950Z","signature_b64":"/iK5r8nyAqYcl5tknGSRyqT9JKQRjfKt5/ld+VJp6zNXL0kLEfdtFzVUKhi7hGkGIvoHmdjeoe5vUi1s/QyPBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f454bbfea83284d61e82287112bbe0af1bb8fc4ff1ed3b6e5e07537fb4d52c2b","last_reissued_at":"2026-07-05T11:57:43.931487Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:43.931487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Competition and Attraction Improve Model Fusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.AI","authors_text":"Jo\\~ao Abrantes, Robert Tjarko Lange, Yujin Tang","submitted_at":"2025-08-22T08:24:02Z","abstract_excerpt":"Model merging is a powerful technique for integrating the specialized knowledge of multiple machine learning models into a single model. However, existing methods require manually partitioning model parameters into fixed groups for merging, which restricts the exploration of potential combinations and limits performance. To overcome these limitations, we propose Model Merging of Natural Niches (M2N2), an evolutionary algorithm with three key features: (1) dynamic adjustment of merging boundaries to progressively explore a broader range of parameter combinations; (2) a diversity preservation me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.16204","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/2508.16204/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":"2508.16204","created_at":"2026-07-05T11:57:43.931545+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.16204v1","created_at":"2026-07-05T11:57:43.931545+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.16204","created_at":"2026-07-05T11:57:43.931545+00:00"},{"alias_kind":"pith_short_12","alias_value":"6RKLX7VIGKCN","created_at":"2026-07-05T11:57:43.931545+00:00"},{"alias_kind":"pith_short_16","alias_value":"6RKLX7VIGKCNMHUC","created_at":"2026-07-05T11:57:43.931545+00:00"},{"alias_kind":"pith_short_8","alias_value":"6RKLX7VI","created_at":"2026-07-05T11:57:43.931545+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2603.12916","citing_title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6RKLX7VIGKCNMHUCFBYRFO7AV4","json":"https://pith.science/pith/6RKLX7VIGKCNMHUCFBYRFO7AV4.json","graph_json":"https://pith.science/api/pith-number/6RKLX7VIGKCNMHUCFBYRFO7AV4/graph.json","events_json":"https://pith.science/api/pith-number/6RKLX7VIGKCNMHUCFBYRFO7AV4/events.json","paper":"https://pith.science/paper/6RKLX7VI"},"agent_actions":{"view_html":"https://pith.science/pith/6RKLX7VIGKCNMHUCFBYRFO7AV4","download_json":"https://pith.science/pith/6RKLX7VIGKCNMHUCFBYRFO7AV4.json","view_paper":"https://pith.science/paper/6RKLX7VI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.16204&json=true","fetch_graph":"https://pith.science/api/pith-number/6RKLX7VIGKCNMHUCFBYRFO7AV4/graph.json","fetch_events":"https://pith.science/api/pith-number/6RKLX7VIGKCNMHUCFBYRFO7AV4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6RKLX7VIGKCNMHUCFBYRFO7AV4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6RKLX7VIGKCNMHUCFBYRFO7AV4/action/storage_attestation","attest_author":"https://pith.science/pith/6RKLX7VIGKCNMHUCFBYRFO7AV4/action/author_attestation","sign_citation":"https://pith.science/pith/6RKLX7VIGKCNMHUCFBYRFO7AV4/action/citation_signature","submit_replication":"https://pith.science/pith/6RKLX7VIGKCNMHUCFBYRFO7AV4/action/replication_record"}},"created_at":"2026-07-05T11:57:43.931545+00:00","updated_at":"2026-07-05T11:57:43.931545+00:00"}