{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KK6HVQZ4G3GJSBRRGHKWMVEIO7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"57f5ebcecffc48adec6081488befca25da88193296bee0c00ad19c2dcefc011a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-23T03:16:32Z","title_canon_sha256":"7d039e34d8fd2559a0863d82d94224511d0d5b2cf10f533d98f408970e2be237"},"schema_version":"1.0","source":{"id":"2310.14526","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.14526","created_at":"2026-07-05T07:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"2310.14526v3","created_at":"2026-07-05T07:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14526","created_at":"2026-07-05T07:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"KK6HVQZ4G3GJ","created_at":"2026-07-05T07:38:52Z"},{"alias_kind":"pith_short_16","alias_value":"KK6HVQZ4G3GJSBRR","created_at":"2026-07-05T07:38:52Z"},{"alias_kind":"pith_short_8","alias_value":"KK6HVQZ4","created_at":"2026-07-05T07:38:52Z"}],"graph_snapshots":[{"event_id":"sha256:cdb2b80c14b1641d04d91009a7a6eb2e23cde551b230bc7abd5fdfef479eae26","target":"graph","created_at":"2026-07-05T07:38:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.14526/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aparna Taneja, Dheeraj Nagaraj, Edward Hughes, Edwin Zhang, Karl Tuyls, Milind Tambe, Nikhil Behari, Yunfan Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-23T03:16:32Z","title":"Towards a Pretrained Model for Restless Bandits via Multi-arm Generalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14526","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1d5da77a44091a0fac6a9f5143756430800cfa2e5bbe53d53e41667b07a8fdbb","target":"record","created_at":"2026-07-05T07:38:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"57f5ebcecffc48adec6081488befca25da88193296bee0c00ad19c2dcefc011a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-23T03:16:32Z","title_canon_sha256":"7d039e34d8fd2559a0863d82d94224511d0d5b2cf10f533d98f408970e2be237"},"schema_version":"1.0","source":{"id":"2310.14526","kind":"arxiv","version":3}},"canonical_sha256":"52bc7ac33c36cc99063131d566548877c5782f857923614952787e6f10b9ec1f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52bc7ac33c36cc99063131d566548877c5782f857923614952787e6f10b9ec1f","first_computed_at":"2026-07-05T07:38:52.989727Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:38:52.989727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"irA7U4vIQPlAGBwjr8GaW0OvOKG40TnF8vYgTQS5VKf764P+wYezF95u5hN9Xwv5+oLQ5burI3AodELs8HORBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:38:52.990185Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.14526","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d5da77a44091a0fac6a9f5143756430800cfa2e5bbe53d53e41667b07a8fdbb","sha256:cdb2b80c14b1641d04d91009a7a6eb2e23cde551b230bc7abd5fdfef479eae26"],"state_sha256":"a6cca339378fe14352a9c3d7f5a1ea37a6fd7b72c26c277aba2d5d32c2afa042"}