{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QBCMDKPCZYNEAJ7H3MUSRYMQNO","short_pith_number":"pith:QBCMDKPC","schema_version":"1.0","canonical_sha256":"8044c1a9e2ce1a4027e7db2928e1906b829f4e4a9cad1780e9f5b22a8048865c","source":{"kind":"arxiv","id":"2606.28925","version":1},"attestation_state":"computed","paper":{"title":"Multi-Agent Routing as Set-Valued Prediction: A WildChat Benchmark and Cost-Aware Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.MA"],"primary_cat":"cs.LG","authors_text":"Ananto Nayan Bala, Faisal Muhammad Shah","submitted_at":"2026-06-27T13:59:46Z","abstract_excerpt":"Tool and agent routing from natural-language prompts is naturally a set-valued prediction problem: a single query may require multiple agents, while over-selection increases execution cost. The benchmark introduced here is derived from WildChat and contains 3,000 prompts over a fixed 12-agent catalog, with AI-assisted heuristic labels under a fixed schema and controlled rebalancing for multi-label evaluation. The evaluation protocol combines set-level metrics (Precision, Recall, F1, Jaccard, and Exact Match), latency, an execution-oriented capability-coverage simulation, and a constrained weig"},"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":"2606.28925","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-27T13:59:46Z","cross_cats_sorted":["cs.AI","cs.IR","cs.MA"],"title_canon_sha256":"2bc3f67ffa4ce4a5653783f25edab8b23a58b8f1f84418be94a6a730bfaad81b","abstract_canon_sha256":"c90b1a8f47af8f3596f4e901084fb461aeb32ddf63de50983e9239b588ace680"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:45.604085Z","signature_b64":"vwHBr40jjyyXxWw5Q3dwvCrR8vAWjFpCc3AOAshLe+2Pd1lcST83YZr7VxLjZInQP7gZ9dFvF0EUP+bPWb4OBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8044c1a9e2ce1a4027e7db2928e1906b829f4e4a9cad1780e9f5b22a8048865c","last_reissued_at":"2026-06-30T01:17:45.603568Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:45.603568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Agent Routing as Set-Valued Prediction: A WildChat Benchmark and Cost-Aware Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.MA"],"primary_cat":"cs.LG","authors_text":"Ananto Nayan Bala, Faisal Muhammad Shah","submitted_at":"2026-06-27T13:59:46Z","abstract_excerpt":"Tool and agent routing from natural-language prompts is naturally a set-valued prediction problem: a single query may require multiple agents, while over-selection increases execution cost. The benchmark introduced here is derived from WildChat and contains 3,000 prompts over a fixed 12-agent catalog, with AI-assisted heuristic labels under a fixed schema and controlled rebalancing for multi-label evaluation. The evaluation protocol combines set-level metrics (Precision, Recall, F1, Jaccard, and Exact Match), latency, an execution-oriented capability-coverage simulation, and a constrained weig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28925","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/2606.28925/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":"2606.28925","created_at":"2026-06-30T01:17:45.603642+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.28925v1","created_at":"2026-06-30T01:17:45.603642+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28925","created_at":"2026-06-30T01:17:45.603642+00:00"},{"alias_kind":"pith_short_12","alias_value":"QBCMDKPCZYNE","created_at":"2026-06-30T01:17:45.603642+00:00"},{"alias_kind":"pith_short_16","alias_value":"QBCMDKPCZYNEAJ7H","created_at":"2026-06-30T01:17:45.603642+00:00"},{"alias_kind":"pith_short_8","alias_value":"QBCMDKPC","created_at":"2026-06-30T01:17:45.603642+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/QBCMDKPCZYNEAJ7H3MUSRYMQNO","json":"https://pith.science/pith/QBCMDKPCZYNEAJ7H3MUSRYMQNO.json","graph_json":"https://pith.science/api/pith-number/QBCMDKPCZYNEAJ7H3MUSRYMQNO/graph.json","events_json":"https://pith.science/api/pith-number/QBCMDKPCZYNEAJ7H3MUSRYMQNO/events.json","paper":"https://pith.science/paper/QBCMDKPC"},"agent_actions":{"view_html":"https://pith.science/pith/QBCMDKPCZYNEAJ7H3MUSRYMQNO","download_json":"https://pith.science/pith/QBCMDKPCZYNEAJ7H3MUSRYMQNO.json","view_paper":"https://pith.science/paper/QBCMDKPC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.28925&json=true","fetch_graph":"https://pith.science/api/pith-number/QBCMDKPCZYNEAJ7H3MUSRYMQNO/graph.json","fetch_events":"https://pith.science/api/pith-number/QBCMDKPCZYNEAJ7H3MUSRYMQNO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QBCMDKPCZYNEAJ7H3MUSRYMQNO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QBCMDKPCZYNEAJ7H3MUSRYMQNO/action/storage_attestation","attest_author":"https://pith.science/pith/QBCMDKPCZYNEAJ7H3MUSRYMQNO/action/author_attestation","sign_citation":"https://pith.science/pith/QBCMDKPCZYNEAJ7H3MUSRYMQNO/action/citation_signature","submit_replication":"https://pith.science/pith/QBCMDKPCZYNEAJ7H3MUSRYMQNO/action/replication_record"}},"created_at":"2026-06-30T01:17:45.603642+00:00","updated_at":"2026-06-30T01:17:45.603642+00:00"}