{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XA3YAOJOV5SEH5LFDAZ5A4EYES","short_pith_number":"pith:XA3YAOJO","schema_version":"1.0","canonical_sha256":"b83780392eaf6443f5651833d0709824abd041de276d6ee08e774652cb2606ac","source":{"kind":"arxiv","id":"2504.10681","version":1},"attestation_state":"computed","paper":{"title":"EMAFusion: A Self-Optimizing System for Seamless LLM Selection and Integration","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kumar Shridhar, Soham Shah, Souvik Sen, Surojit Chatterjee","submitted_at":"2025-04-14T20:04:54Z","abstract_excerpt":"While recent advances in large language models (LLMs) have significantly enhanced performance across diverse natural language tasks, the high computational and financial costs associated with their deployment remain substantial barriers. Existing routing strategies partially alleviate this challenge by assigning queries to cheaper or specialized models, but they frequently rely on extensive labeled data or fragile task-specific heuristics. Conversely, fusion techniques aggregate multiple LLM outputs to boost accuracy and robustness, yet they often exacerbate cost and may reinforce shared biase"},"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":"2504.10681","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-14T20:04:54Z","cross_cats_sorted":[],"title_canon_sha256":"43844223438aac1f42cfd7ca1778ae491192042d3d78068337bb76436ec6b54f","abstract_canon_sha256":"823fde3cd8f3107f63b99e0ded0b23c06f9c0f3fd08239ad51f1d3c96e461d52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:22.001802Z","signature_b64":"qYow9v5sxp9uthsNLHKR9Jf0Yvvbl3N0ni32OFsvqBr9Rm86fVB4KqV2iVgg+Jx0hG1rxUPuHYxXbifv7181BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b83780392eaf6443f5651833d0709824abd041de276d6ee08e774652cb2606ac","last_reissued_at":"2026-07-05T10:49:22.001329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:22.001329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EMAFusion: A Self-Optimizing System for Seamless LLM Selection and Integration","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kumar Shridhar, Soham Shah, Souvik Sen, Surojit Chatterjee","submitted_at":"2025-04-14T20:04:54Z","abstract_excerpt":"While recent advances in large language models (LLMs) have significantly enhanced performance across diverse natural language tasks, the high computational and financial costs associated with their deployment remain substantial barriers. Existing routing strategies partially alleviate this challenge by assigning queries to cheaper or specialized models, but they frequently rely on extensive labeled data or fragile task-specific heuristics. Conversely, fusion techniques aggregate multiple LLM outputs to boost accuracy and robustness, yet they often exacerbate cost and may reinforce shared biase"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.10681","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/2504.10681/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":"2504.10681","created_at":"2026-07-05T10:49:22.001388+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.10681v1","created_at":"2026-07-05T10:49:22.001388+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.10681","created_at":"2026-07-05T10:49:22.001388+00:00"},{"alias_kind":"pith_short_12","alias_value":"XA3YAOJOV5SE","created_at":"2026-07-05T10:49:22.001388+00:00"},{"alias_kind":"pith_short_16","alias_value":"XA3YAOJOV5SEH5LF","created_at":"2026-07-05T10:49:22.001388+00:00"},{"alias_kind":"pith_short_8","alias_value":"XA3YAOJO","created_at":"2026-07-05T10:49:22.001388+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/XA3YAOJOV5SEH5LFDAZ5A4EYES","json":"https://pith.science/pith/XA3YAOJOV5SEH5LFDAZ5A4EYES.json","graph_json":"https://pith.science/api/pith-number/XA3YAOJOV5SEH5LFDAZ5A4EYES/graph.json","events_json":"https://pith.science/api/pith-number/XA3YAOJOV5SEH5LFDAZ5A4EYES/events.json","paper":"https://pith.science/paper/XA3YAOJO"},"agent_actions":{"view_html":"https://pith.science/pith/XA3YAOJOV5SEH5LFDAZ5A4EYES","download_json":"https://pith.science/pith/XA3YAOJOV5SEH5LFDAZ5A4EYES.json","view_paper":"https://pith.science/paper/XA3YAOJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.10681&json=true","fetch_graph":"https://pith.science/api/pith-number/XA3YAOJOV5SEH5LFDAZ5A4EYES/graph.json","fetch_events":"https://pith.science/api/pith-number/XA3YAOJOV5SEH5LFDAZ5A4EYES/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XA3YAOJOV5SEH5LFDAZ5A4EYES/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XA3YAOJOV5SEH5LFDAZ5A4EYES/action/storage_attestation","attest_author":"https://pith.science/pith/XA3YAOJOV5SEH5LFDAZ5A4EYES/action/author_attestation","sign_citation":"https://pith.science/pith/XA3YAOJOV5SEH5LFDAZ5A4EYES/action/citation_signature","submit_replication":"https://pith.science/pith/XA3YAOJOV5SEH5LFDAZ5A4EYES/action/replication_record"}},"created_at":"2026-07-05T10:49:22.001388+00:00","updated_at":"2026-07-05T10:49:22.001388+00:00"}