{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EBUHBL5SOEK7OK7ZBFWRYW2UKF","short_pith_number":"pith:EBUHBL5S","canonical_record":{"source":{"id":"2409.04605","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-06T20:24:19Z","cross_cats_sorted":["cs.SY","eess.SY","stat.ML"],"title_canon_sha256":"6e8c17f86439b8979afce2f904b64b04cd622098db0ff2683d5555b51adc9bc5","abstract_canon_sha256":"72f7eaf1376dcf10abc77b66404ee587a65e578889b080eb1ef465654d11f580"},"schema_version":"1.0"},"canonical_sha256":"206870afb27115f72bf9096d1c5b545163c4040ea3ff42fa61d9cd1a1c268d0b","source":{"kind":"arxiv","id":"2409.04605","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.04605","created_at":"2026-07-05T09:04:15Z"},{"alias_kind":"arxiv_version","alias_value":"2409.04605v1","created_at":"2026-07-05T09:04:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04605","created_at":"2026-07-05T09:04:15Z"},{"alias_kind":"pith_short_12","alias_value":"EBUHBL5SOEK7","created_at":"2026-07-05T09:04:15Z"},{"alias_kind":"pith_short_16","alias_value":"EBUHBL5SOEK7OK7Z","created_at":"2026-07-05T09:04:15Z"},{"alias_kind":"pith_short_8","alias_value":"EBUHBL5S","created_at":"2026-07-05T09:04:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EBUHBL5SOEK7OK7ZBFWRYW2UKF","target":"record","payload":{"canonical_record":{"source":{"id":"2409.04605","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-06T20:24:19Z","cross_cats_sorted":["cs.SY","eess.SY","stat.ML"],"title_canon_sha256":"6e8c17f86439b8979afce2f904b64b04cd622098db0ff2683d5555b51adc9bc5","abstract_canon_sha256":"72f7eaf1376dcf10abc77b66404ee587a65e578889b080eb1ef465654d11f580"},"schema_version":"1.0"},"canonical_sha256":"206870afb27115f72bf9096d1c5b545163c4040ea3ff42fa61d9cd1a1c268d0b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:15.112480Z","signature_b64":"pX9rShoc0pnGZb99XJRl7o53BZtx78LGpfH64HXWnqIGWDVYnXlPdcxU/M8zIMsIgxt/vCl63nOW+hPwBNufDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"206870afb27115f72bf9096d1c5b545163c4040ea3ff42fa61d9cd1a1c268d0b","last_reissued_at":"2026-07-05T09:04:15.112064Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:15.112064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.04605","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:04:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2QqQB+slYu7xVtuKH+612B3M/k8+8VGnhMhVvB9204IomQZPs3ap3yyLUOZsjdZgcYhU8n49QsZO41xeBNgRAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T02:33:16.914724Z"},"content_sha256":"23be71bc7379016c8eee8a9a941a29912a0e99705db36d5f8c4eee73fece2492","schema_version":"1.0","event_id":"sha256:23be71bc7379016c8eee8a9a941a29912a0e99705db36d5f8c4eee73fece2492"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EBUHBL5SOEK7OK7ZBFWRYW2UKF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Whittle Index Learning Algorithms for Restless Bandits with Constant Stepsizes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Rahul Meshram, Surya Prakash, Vishesh Mittal","submitted_at":"2024-09-06T20:24:19Z","abstract_excerpt":"We study the Whittle index learning algorithm for restless multi-armed bandits. We consider index learning algorithm with Q-learning. We first present Q-learning algorithm with exploration policies -- epsilon-greedy, softmax, epsilon-softmax with constant stepsizes. We extend the study of Q-learning to index learning for single-armed restless bandit. The algorithm of index learning is two-timescale variant of stochastic approximation, on slower timescale we update index learning scheme and on faster timescale we update Q-learning assuming fixed index value. In Q-learning updates are in asynchr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04605","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/2409.04605/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":"2026-07-05T09:04:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iJ/vD9V75QPKK9w7V1nZh0uqL+32WHYjDI3x9kmdBA7Jv/9jrkIAENqRXhGwShoH5aPJfJ3W8hRDUAR0lqFUBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T02:33:16.915698Z"},"content_sha256":"7cd1d14cd7ceea74e0e9b32702d2e80f068829c3f1f1532a83d05a098190bb59","schema_version":"1.0","event_id":"sha256:7cd1d14cd7ceea74e0e9b32702d2e80f068829c3f1f1532a83d05a098190bb59"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EBUHBL5SOEK7OK7ZBFWRYW2UKF/bundle.json","state_url":"https://pith.science/pith/EBUHBL5SOEK7OK7ZBFWRYW2UKF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EBUHBL5SOEK7OK7ZBFWRYW2UKF/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":"2026-08-13T02:33:16Z","links":{"resolver":"https://pith.science/pith/EBUHBL5SOEK7OK7ZBFWRYW2UKF","bundle":"https://pith.science/pith/EBUHBL5SOEK7OK7ZBFWRYW2UKF/bundle.json","state":"https://pith.science/pith/EBUHBL5SOEK7OK7ZBFWRYW2UKF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EBUHBL5SOEK7OK7ZBFWRYW2UKF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EBUHBL5SOEK7OK7ZBFWRYW2UKF","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":"72f7eaf1376dcf10abc77b66404ee587a65e578889b080eb1ef465654d11f580","cross_cats_sorted":["cs.SY","eess.SY","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-06T20:24:19Z","title_canon_sha256":"6e8c17f86439b8979afce2f904b64b04cd622098db0ff2683d5555b51adc9bc5"},"schema_version":"1.0","source":{"id":"2409.04605","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.04605","created_at":"2026-07-05T09:04:15Z"},{"alias_kind":"arxiv_version","alias_value":"2409.04605v1","created_at":"2026-07-05T09:04:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04605","created_at":"2026-07-05T09:04:15Z"},{"alias_kind":"pith_short_12","alias_value":"EBUHBL5SOEK7","created_at":"2026-07-05T09:04:15Z"},{"alias_kind":"pith_short_16","alias_value":"EBUHBL5SOEK7OK7Z","created_at":"2026-07-05T09:04:15Z"},{"alias_kind":"pith_short_8","alias_value":"EBUHBL5S","created_at":"2026-07-05T09:04:15Z"}],"graph_snapshots":[{"event_id":"sha256:7cd1d14cd7ceea74e0e9b32702d2e80f068829c3f1f1532a83d05a098190bb59","target":"graph","created_at":"2026-07-05T09:04:15Z","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/2409.04605/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the Whittle index learning algorithm for restless multi-armed bandits. We consider index learning algorithm with Q-learning. We first present Q-learning algorithm with exploration policies -- epsilon-greedy, softmax, epsilon-softmax with constant stepsizes. We extend the study of Q-learning to index learning for single-armed restless bandit. The algorithm of index learning is two-timescale variant of stochastic approximation, on slower timescale we update index learning scheme and on faster timescale we update Q-learning assuming fixed index value. In Q-learning updates are in asynchr","authors_text":"Rahul Meshram, Surya Prakash, Vishesh Mittal","cross_cats":["cs.SY","eess.SY","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-06T20:24:19Z","title":"Whittle Index Learning Algorithms for Restless Bandits with Constant Stepsizes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04605","kind":"arxiv","version":1},"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":"sha256:23be71bc7379016c8eee8a9a941a29912a0e99705db36d5f8c4eee73fece2492","target":"record","created_at":"2026-07-05T09:04:15Z","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":"72f7eaf1376dcf10abc77b66404ee587a65e578889b080eb1ef465654d11f580","cross_cats_sorted":["cs.SY","eess.SY","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-06T20:24:19Z","title_canon_sha256":"6e8c17f86439b8979afce2f904b64b04cd622098db0ff2683d5555b51adc9bc5"},"schema_version":"1.0","source":{"id":"2409.04605","kind":"arxiv","version":1}},"canonical_sha256":"206870afb27115f72bf9096d1c5b545163c4040ea3ff42fa61d9cd1a1c268d0b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"206870afb27115f72bf9096d1c5b545163c4040ea3ff42fa61d9cd1a1c268d0b","first_computed_at":"2026-07-05T09:04:15.112064Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:04:15.112064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pX9rShoc0pnGZb99XJRl7o53BZtx78LGpfH64HXWnqIGWDVYnXlPdcxU/M8zIMsIgxt/vCl63nOW+hPwBNufDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:04:15.112480Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.04605","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23be71bc7379016c8eee8a9a941a29912a0e99705db36d5f8c4eee73fece2492","sha256:7cd1d14cd7ceea74e0e9b32702d2e80f068829c3f1f1532a83d05a098190bb59"],"state_sha256":"456d06240da2eb34db554cf3095a03308eb5f7c12cee8a5130aef9fb929ac2bd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GFa483+rP0sePbTRn5VSPg4zwbXfOwTTWEQ2S+QaZpuK2MO51aECM2bXyJumDUtJreB23pPyFelX8PTTtbTGBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T02:33:16.926809Z","bundle_sha256":"8215ebe0bfb558e517845ca4b37feff552422071899b48b8778d06986cea31a6"}}