{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IVUCZOLE5M3RADWKWYNGFA56LS","short_pith_number":"pith:IVUCZOLE","canonical_record":{"source":{"id":"2408.05686","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-11T03:39:46Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"5ecc7a0fa566f312fb64ea210d27e3b71000fb8a082c29f196eb9742eefe17b3","abstract_canon_sha256":"a63f4b95043f751bd594e76cbad69097b71833b17a6e35dda251cd75eaf5e058"},"schema_version":"1.0"},"canonical_sha256":"45682cb964eb37100ecab61a6283be5cb5dc073257111d708c1b7ea79436269a","source":{"kind":"arxiv","id":"2408.05686","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.05686","created_at":"2026-07-05T10:34:09Z"},{"alias_kind":"arxiv_version","alias_value":"2408.05686v3","created_at":"2026-07-05T10:34:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05686","created_at":"2026-07-05T10:34:09Z"},{"alias_kind":"pith_short_12","alias_value":"IVUCZOLE5M3R","created_at":"2026-07-05T10:34:09Z"},{"alias_kind":"pith_short_16","alias_value":"IVUCZOLE5M3RADWK","created_at":"2026-07-05T10:34:09Z"},{"alias_kind":"pith_short_8","alias_value":"IVUCZOLE","created_at":"2026-07-05T10:34:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IVUCZOLE5M3RADWKWYNGFA56LS","target":"record","payload":{"canonical_record":{"source":{"id":"2408.05686","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-11T03:39:46Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"5ecc7a0fa566f312fb64ea210d27e3b71000fb8a082c29f196eb9742eefe17b3","abstract_canon_sha256":"a63f4b95043f751bd594e76cbad69097b71833b17a6e35dda251cd75eaf5e058"},"schema_version":"1.0"},"canonical_sha256":"45682cb964eb37100ecab61a6283be5cb5dc073257111d708c1b7ea79436269a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:09.611932Z","signature_b64":"9/z3ETjBjZmJQKegj7cT7jFt8OLP2xypWM19qikoVZbca9gH98yvMH2MaXu40ZgX0/bEgmkpUafSaIOJ0vnjCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45682cb964eb37100ecab61a6283be5cb5dc073257111d708c1b7ea79436269a","last_reissued_at":"2026-07-05T10:34:09.611224Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:09.611224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.05686","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:34:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GNCZN82oegNyE9UmxhyeFW/meHN6pCtltih8dlXQjijhsEWRHogWhyrZI6o2iFDqC7GpfSi2rjOFZA6e+D1UCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T09:51:26.017177Z"},"content_sha256":"add570b895ea1b19b1fe6263b834d81ed8df4e1860b7984a2fd6086669987118","schema_version":"1.0","event_id":"sha256:add570b895ea1b19b1fe6263b834d81ed8df4e1860b7984a2fd6086669987118"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IVUCZOLE5M3RADWKWYNGFA56LS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Bandit Whisperer: Communication Learning for Restless Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Aparna Taneja, Dheeraj Nagaraj, Milind Tambe, Tonghan Wang, Yunfan Zhao","submitted_at":"2024-08-11T03:39:46Z","abstract_excerpt":"Applying Reinforcement Learning (RL) to Restless Multi-Arm Bandits (RMABs) offers a promising avenue for addressing allocation problems with resource constraints and temporal dynamics. However, classic RMAB models largely overlook the challenges of (systematic) data errors - a common occurrence in real-world scenarios due to factors like varying data collection protocols and intentional noise for differential privacy. We demonstrate that conventional RL algorithms used to train RMABs can struggle to perform well in such settings. To solve this problem, we propose the first communication learni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05686","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/2408.05686/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:34:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j+In6pxP8T/ex7Pf3+UFI/kJdEQYvZAWXdvXe7eg0XwruFhJSdCrTDDzhLzA6ShwrjyYs5q5R7OxZm5TTJnsAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T09:51:26.017699Z"},"content_sha256":"473c4806430acba63e12dc653f55c51e3feb462206a9a2fa9c706743d9049df6","schema_version":"1.0","event_id":"sha256:473c4806430acba63e12dc653f55c51e3feb462206a9a2fa9c706743d9049df6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IVUCZOLE5M3RADWKWYNGFA56LS/bundle.json","state_url":"https://pith.science/pith/IVUCZOLE5M3RADWKWYNGFA56LS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IVUCZOLE5M3RADWKWYNGFA56LS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-01T09:51:26Z","links":{"resolver":"https://pith.science/pith/IVUCZOLE5M3RADWKWYNGFA56LS","bundle":"https://pith.science/pith/IVUCZOLE5M3RADWKWYNGFA56LS/bundle.json","state":"https://pith.science/pith/IVUCZOLE5M3RADWKWYNGFA56LS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IVUCZOLE5M3RADWKWYNGFA56LS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IVUCZOLE5M3RADWKWYNGFA56LS","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":"a63f4b95043f751bd594e76cbad69097b71833b17a6e35dda251cd75eaf5e058","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-11T03:39:46Z","title_canon_sha256":"5ecc7a0fa566f312fb64ea210d27e3b71000fb8a082c29f196eb9742eefe17b3"},"schema_version":"1.0","source":{"id":"2408.05686","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.05686","created_at":"2026-07-05T10:34:09Z"},{"alias_kind":"arxiv_version","alias_value":"2408.05686v3","created_at":"2026-07-05T10:34:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05686","created_at":"2026-07-05T10:34:09Z"},{"alias_kind":"pith_short_12","alias_value":"IVUCZOLE5M3R","created_at":"2026-07-05T10:34:09Z"},{"alias_kind":"pith_short_16","alias_value":"IVUCZOLE5M3RADWK","created_at":"2026-07-05T10:34:09Z"},{"alias_kind":"pith_short_8","alias_value":"IVUCZOLE","created_at":"2026-07-05T10:34:09Z"}],"graph_snapshots":[{"event_id":"sha256:473c4806430acba63e12dc653f55c51e3feb462206a9a2fa9c706743d9049df6","target":"graph","created_at":"2026-07-05T10:34:09Z","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/2408.05686/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Applying Reinforcement Learning (RL) to Restless Multi-Arm Bandits (RMABs) offers a promising avenue for addressing allocation problems with resource constraints and temporal dynamics. However, classic RMAB models largely overlook the challenges of (systematic) data errors - a common occurrence in real-world scenarios due to factors like varying data collection protocols and intentional noise for differential privacy. We demonstrate that conventional RL algorithms used to train RMABs can struggle to perform well in such settings. To solve this problem, we propose the first communication learni","authors_text":"Aparna Taneja, Dheeraj Nagaraj, Milind Tambe, Tonghan Wang, Yunfan Zhao","cross_cats":["cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-11T03:39:46Z","title":"The Bandit Whisperer: Communication Learning for Restless Bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05686","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:add570b895ea1b19b1fe6263b834d81ed8df4e1860b7984a2fd6086669987118","target":"record","created_at":"2026-07-05T10:34:09Z","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":"a63f4b95043f751bd594e76cbad69097b71833b17a6e35dda251cd75eaf5e058","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-11T03:39:46Z","title_canon_sha256":"5ecc7a0fa566f312fb64ea210d27e3b71000fb8a082c29f196eb9742eefe17b3"},"schema_version":"1.0","source":{"id":"2408.05686","kind":"arxiv","version":3}},"canonical_sha256":"45682cb964eb37100ecab61a6283be5cb5dc073257111d708c1b7ea79436269a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45682cb964eb37100ecab61a6283be5cb5dc073257111d708c1b7ea79436269a","first_computed_at":"2026-07-05T10:34:09.611224Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:34:09.611224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9/z3ETjBjZmJQKegj7cT7jFt8OLP2xypWM19qikoVZbca9gH98yvMH2MaXu40ZgX0/bEgmkpUafSaIOJ0vnjCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:34:09.611932Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.05686","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:add570b895ea1b19b1fe6263b834d81ed8df4e1860b7984a2fd6086669987118","sha256:473c4806430acba63e12dc653f55c51e3feb462206a9a2fa9c706743d9049df6"],"state_sha256":"7d169ceb5a50b64eee3eb1ad4c0fbea113fda7a7c1a61bf4e3cc493f568845bc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a9U9IpOSvEbmf8VwrWRWrlpjHZ50vEWJfqBLkQhgJaVf2QbPYjXJV6i4KPp/tVCFlQ3dSNWA+OpOhZ0NuseKBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T09:51:26.020444Z","bundle_sha256":"a5a8185e9cc88b073b5a048f53d4958e01d7e06f05ee0acfec6e060a324df381"}}