{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MRFXLB7XRURPXA4VMKXDK6MHGC","short_pith_number":"pith:MRFXLB7X","schema_version":"1.0","canonical_sha256":"644b7587f78d22fb839562ae357987308fea5cea62132b992022bc228fbfa18e","source":{"kind":"arxiv","id":"2605.27999","version":1},"attestation_state":"computed","paper":{"title":"Learning to Assign Prediction Tasks to Agents with Capacity Constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Padhraic Smyth, Saatvik Kher, Shang Wu","submitted_at":"2026-05-27T05:45:47Z","abstract_excerpt":"We address the problem of learning to assign prediction tasks to one agent from a set of available human or AI agents. In particular, we focus on the sequential learning of agent expertise and assignment policies where each agent is constrained to handle a fraction of tasks. We provide a general theoretical characterization of this problem in terms of agent capacities, differences in agent expertise, and task context. We then develop a framework of sequential explore-exploit policy-learning algorithms that seek to maximize overall performance. Experimental results over a variety of tabular, im"},"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":"2605.27999","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2026-05-27T05:45:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5d6a755a146344f5b401509537d4ae08ef547c7127ddcffca0cc0507a4c7db4c","abstract_canon_sha256":"0dc77ffabfa1fbbcaf7647359bc3b731e3cfbafbffc47211ac6e01cf3699531b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:55.655281Z","signature_b64":"b8Hq91fTy3Yg3kEvHdEvHZTb/bFg9IUsRsdLGTsC7R+BNz1noVIOfnrE9C7JygnkvTI/bNHJvcQRLqjVPpZZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"644b7587f78d22fb839562ae357987308fea5cea62132b992022bc228fbfa18e","last_reissued_at":"2026-05-28T01:04:55.654869Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:55.654869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Assign Prediction Tasks to Agents with Capacity Constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Padhraic Smyth, Saatvik Kher, Shang Wu","submitted_at":"2026-05-27T05:45:47Z","abstract_excerpt":"We address the problem of learning to assign prediction tasks to one agent from a set of available human or AI agents. In particular, we focus on the sequential learning of agent expertise and assignment policies where each agent is constrained to handle a fraction of tasks. We provide a general theoretical characterization of this problem in terms of agent capacities, differences in agent expertise, and task context. We then develop a framework of sequential explore-exploit policy-learning algorithms that seek to maximize overall performance. Experimental results over a variety of tabular, im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27999","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/2605.27999/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":"2605.27999","created_at":"2026-05-28T01:04:55.654927+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27999v1","created_at":"2026-05-28T01:04:55.654927+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27999","created_at":"2026-05-28T01:04:55.654927+00:00"},{"alias_kind":"pith_short_12","alias_value":"MRFXLB7XRURP","created_at":"2026-05-28T01:04:55.654927+00:00"},{"alias_kind":"pith_short_16","alias_value":"MRFXLB7XRURPXA4V","created_at":"2026-05-28T01:04:55.654927+00:00"},{"alias_kind":"pith_short_8","alias_value":"MRFXLB7X","created_at":"2026-05-28T01:04:55.654927+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/MRFXLB7XRURPXA4VMKXDK6MHGC","json":"https://pith.science/pith/MRFXLB7XRURPXA4VMKXDK6MHGC.json","graph_json":"https://pith.science/api/pith-number/MRFXLB7XRURPXA4VMKXDK6MHGC/graph.json","events_json":"https://pith.science/api/pith-number/MRFXLB7XRURPXA4VMKXDK6MHGC/events.json","paper":"https://pith.science/paper/MRFXLB7X"},"agent_actions":{"view_html":"https://pith.science/pith/MRFXLB7XRURPXA4VMKXDK6MHGC","download_json":"https://pith.science/pith/MRFXLB7XRURPXA4VMKXDK6MHGC.json","view_paper":"https://pith.science/paper/MRFXLB7X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27999&json=true","fetch_graph":"https://pith.science/api/pith-number/MRFXLB7XRURPXA4VMKXDK6MHGC/graph.json","fetch_events":"https://pith.science/api/pith-number/MRFXLB7XRURPXA4VMKXDK6MHGC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MRFXLB7XRURPXA4VMKXDK6MHGC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MRFXLB7XRURPXA4VMKXDK6MHGC/action/storage_attestation","attest_author":"https://pith.science/pith/MRFXLB7XRURPXA4VMKXDK6MHGC/action/author_attestation","sign_citation":"https://pith.science/pith/MRFXLB7XRURPXA4VMKXDK6MHGC/action/citation_signature","submit_replication":"https://pith.science/pith/MRFXLB7XRURPXA4VMKXDK6MHGC/action/replication_record"}},"created_at":"2026-05-28T01:04:55.654927+00:00","updated_at":"2026-05-28T01:04:55.654927+00:00"}