{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KK6HVQZ4G3GJSBRRGHKWMVEIO7","short_pith_number":"pith:KK6HVQZ4","schema_version":"1.0","canonical_sha256":"52bc7ac33c36cc99063131d566548877c5782f857923614952787e6f10b9ec1f","source":{"kind":"arxiv","id":"2310.14526","version":3},"attestation_state":"computed","paper":{"title":"Towards a Pretrained Model for Restless Bandits via Multi-arm Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aparna Taneja, Dheeraj Nagaraj, Edward Hughes, Edwin Zhang, Karl Tuyls, Milind Tambe, Nikhil Behari, Yunfan Zhao","submitted_at":"2023-10-23T03:16:32Z","abstract_excerpt":"Restless multi-arm bandits (RMABs), a class of resource allocation problems with broad application in areas such as healthcare, online advertising, and anti-poaching, have recently been studied from a multi-agent reinforcement learning perspective. Prior RMAB research suffers from several limitations, e.g., it fails to adequately address continuous states, and requires retraining from scratch when arms opt-in and opt-out over time, a common challenge in many real world applications. We address these limitations by developing a neural network-based pre-trained model (PreFeRMAB) that has general"},"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":"2310.14526","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-23T03:16:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7d039e34d8fd2559a0863d82d94224511d0d5b2cf10f533d98f408970e2be237","abstract_canon_sha256":"57f5ebcecffc48adec6081488befca25da88193296bee0c00ad19c2dcefc011a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:52.990185Z","signature_b64":"irA7U4vIQPlAGBwjr8GaW0OvOKG40TnF8vYgTQS5VKf764P+wYezF95u5hN9Xwv5+oLQ5burI3AodELs8HORBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52bc7ac33c36cc99063131d566548877c5782f857923614952787e6f10b9ec1f","last_reissued_at":"2026-07-05T07:38:52.989727Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:52.989727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards a Pretrained Model for Restless Bandits via Multi-arm Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aparna Taneja, Dheeraj Nagaraj, Edward Hughes, Edwin Zhang, Karl Tuyls, Milind Tambe, Nikhil Behari, Yunfan Zhao","submitted_at":"2023-10-23T03:16:32Z","abstract_excerpt":"Restless multi-arm bandits (RMABs), a class of resource allocation problems with broad application in areas such as healthcare, online advertising, and anti-poaching, have recently been studied from a multi-agent reinforcement learning perspective. Prior RMAB research suffers from several limitations, e.g., it fails to adequately address continuous states, and requires retraining from scratch when arms opt-in and opt-out over time, a common challenge in many real world applications. We address these limitations by developing a neural network-based pre-trained model (PreFeRMAB) that has general"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14526","kind":"arxiv","version":3},"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/2310.14526/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":"2310.14526","created_at":"2026-07-05T07:38:52.989790+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.14526v3","created_at":"2026-07-05T07:38:52.989790+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14526","created_at":"2026-07-05T07:38:52.989790+00:00"},{"alias_kind":"pith_short_12","alias_value":"KK6HVQZ4G3GJ","created_at":"2026-07-05T07:38:52.989790+00:00"},{"alias_kind":"pith_short_16","alias_value":"KK6HVQZ4G3GJSBRR","created_at":"2026-07-05T07:38:52.989790+00:00"},{"alias_kind":"pith_short_8","alias_value":"KK6HVQZ4","created_at":"2026-07-05T07:38:52.989790+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.07384","citing_title":"Decisions and Deployment: The Five-Year SAHELI Project (2020-2025) on Restless Multi-Armed Bandits for Improving Maternal and Child Health","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KK6HVQZ4G3GJSBRRGHKWMVEIO7","json":"https://pith.science/pith/KK6HVQZ4G3GJSBRRGHKWMVEIO7.json","graph_json":"https://pith.science/api/pith-number/KK6HVQZ4G3GJSBRRGHKWMVEIO7/graph.json","events_json":"https://pith.science/api/pith-number/KK6HVQZ4G3GJSBRRGHKWMVEIO7/events.json","paper":"https://pith.science/paper/KK6HVQZ4"},"agent_actions":{"view_html":"https://pith.science/pith/KK6HVQZ4G3GJSBRRGHKWMVEIO7","download_json":"https://pith.science/pith/KK6HVQZ4G3GJSBRRGHKWMVEIO7.json","view_paper":"https://pith.science/paper/KK6HVQZ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.14526&json=true","fetch_graph":"https://pith.science/api/pith-number/KK6HVQZ4G3GJSBRRGHKWMVEIO7/graph.json","fetch_events":"https://pith.science/api/pith-number/KK6HVQZ4G3GJSBRRGHKWMVEIO7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KK6HVQZ4G3GJSBRRGHKWMVEIO7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KK6HVQZ4G3GJSBRRGHKWMVEIO7/action/storage_attestation","attest_author":"https://pith.science/pith/KK6HVQZ4G3GJSBRRGHKWMVEIO7/action/author_attestation","sign_citation":"https://pith.science/pith/KK6HVQZ4G3GJSBRRGHKWMVEIO7/action/citation_signature","submit_replication":"https://pith.science/pith/KK6HVQZ4G3GJSBRRGHKWMVEIO7/action/replication_record"}},"created_at":"2026-07-05T07:38:52.989790+00:00","updated_at":"2026-07-05T07:38:52.989790+00:00"}