{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FYKH4W6TUOZDLBHHFU6TZKYUDT","short_pith_number":"pith:FYKH4W6T","canonical_record":{"source":{"id":"2412.12641","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-17T08:03:53Z","cross_cats_sorted":["cs.AI","math.OC","math.PR"],"title_canon_sha256":"35ce611467458c9fe143fcd3a396a0a890a379fdf93cd009a2a99f5e1289e967","abstract_canon_sha256":"2b7936738988577cfa52fc9bd858de76270fd9aea012d3e7205cd05bf38823da"},"schema_version":"1.0"},"canonical_sha256":"2e147e5bd3a3b23584e72d3d3cab141cdb3ed6a8174c8c4da1f572558a51d0ef","source":{"kind":"arxiv","id":"2412.12641","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12641","created_at":"2026-08-05T01:33:16Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12641v3","created_at":"2026-08-05T01:33:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12641","created_at":"2026-08-05T01:33:16Z"},{"alias_kind":"pith_short_12","alias_value":"FYKH4W6TUOZD","created_at":"2026-08-05T01:33:16Z"},{"alias_kind":"pith_short_16","alias_value":"FYKH4W6TUOZDLBHH","created_at":"2026-08-05T01:33:16Z"},{"alias_kind":"pith_short_8","alias_value":"FYKH4W6T","created_at":"2026-08-05T01:33:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FYKH4W6TUOZDLBHHFU6TZKYUDT","target":"record","payload":{"canonical_record":{"source":{"id":"2412.12641","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-17T08:03:53Z","cross_cats_sorted":["cs.AI","math.OC","math.PR"],"title_canon_sha256":"35ce611467458c9fe143fcd3a396a0a890a379fdf93cd009a2a99f5e1289e967","abstract_canon_sha256":"2b7936738988577cfa52fc9bd858de76270fd9aea012d3e7205cd05bf38823da"},"schema_version":"1.0"},"canonical_sha256":"2e147e5bd3a3b23584e72d3d3cab141cdb3ed6a8174c8c4da1f572558a51d0ef","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:33:16.168607Z","signature_b64":"15zC4fQKWeJ38JrhvLyk7kDKJUMdPbOfpJkXsx1avIf6VkRGDdAYBs6CM+vJ8BuRGgLkYsonHhbfKxs+LVrUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e147e5bd3a3b23584e72d3d3cab141cdb3ed6a8174c8c4da1f572558a51d0ef","last_reissued_at":"2026-08-05T01:33:16.167044Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:33:16.167044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.12641","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":"2026-08-05T01:33:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LeQZP4U8ZCE1sGlzCAYxEWlZ7NbnyVmXf6Q/6Xv90scYn/oiECVXiHDvoQa+6EY4CT+q8jqPUEUWpHswBYZwCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:26:37.803979Z"},"content_sha256":"751c5eae93c2575de1bde151191f9cf5804c7427534132bac86d6074b5410f77","schema_version":"1.0","event_id":"sha256:751c5eae93c2575de1bde151191f9cf5804c7427534132bac86d6074b5410f77"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FYKH4W6TUOZDLBHHFU6TZKYUDT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lagrangian Index Policy for Restless Bandits with Average Reward","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.OC","math.PR"],"primary_cat":"cs.LG","authors_text":"Konstantin Avrachenkov, Pratik Shah, Vivek S. Borkar","submitted_at":"2024-12-17T08:03:53Z","abstract_excerpt":"We study the Lagrangian Index Policy (LIP) for restless multi-armed bandits with long-run average reward. In particular, we compare the performance of LIP with the performance of the Whittle Index Policy (WIP), both heuristic policies known to be asymptotically optimal under certain natural conditions. Even though in most cases their performances are very similar, in the cases when WIP shows bad performance, LIP continues to perform very well. We then propose reinforcement learning algorithms, both tabular and NN-based, to obtain online learning schemes for LIP in the model-free setting. The p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12641","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/2412.12641/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":"2026-08-05T01:33:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"egTBF9DbuAVgUP3sZliRbEMQy4RrRg5lKPRBSgdgSTHaDsACR/kUTqSs5bFeOd8XmjaTzt4Rd+C1EsN2xdqWBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:26:37.804877Z"},"content_sha256":"5f9d97b6312837dcd3e8ca95aa9b0acd10343623334ab8f22b11836d27ba33ce","schema_version":"1.0","event_id":"sha256:5f9d97b6312837dcd3e8ca95aa9b0acd10343623334ab8f22b11836d27ba33ce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FYKH4W6TUOZDLBHHFU6TZKYUDT/bundle.json","state_url":"https://pith.science/pith/FYKH4W6TUOZDLBHHFU6TZKYUDT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FYKH4W6TUOZDLBHHFU6TZKYUDT/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":"2026-08-14T08:26:37Z","links":{"resolver":"https://pith.science/pith/FYKH4W6TUOZDLBHHFU6TZKYUDT","bundle":"https://pith.science/pith/FYKH4W6TUOZDLBHHFU6TZKYUDT/bundle.json","state":"https://pith.science/pith/FYKH4W6TUOZDLBHHFU6TZKYUDT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FYKH4W6TUOZDLBHHFU6TZKYUDT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FYKH4W6TUOZDLBHHFU6TZKYUDT","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":"2b7936738988577cfa52fc9bd858de76270fd9aea012d3e7205cd05bf38823da","cross_cats_sorted":["cs.AI","math.OC","math.PR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-17T08:03:53Z","title_canon_sha256":"35ce611467458c9fe143fcd3a396a0a890a379fdf93cd009a2a99f5e1289e967"},"schema_version":"1.0","source":{"id":"2412.12641","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12641","created_at":"2026-08-05T01:33:16Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12641v3","created_at":"2026-08-05T01:33:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12641","created_at":"2026-08-05T01:33:16Z"},{"alias_kind":"pith_short_12","alias_value":"FYKH4W6TUOZD","created_at":"2026-08-05T01:33:16Z"},{"alias_kind":"pith_short_16","alias_value":"FYKH4W6TUOZDLBHH","created_at":"2026-08-05T01:33:16Z"},{"alias_kind":"pith_short_8","alias_value":"FYKH4W6T","created_at":"2026-08-05T01:33:16Z"}],"graph_snapshots":[{"event_id":"sha256:5f9d97b6312837dcd3e8ca95aa9b0acd10343623334ab8f22b11836d27ba33ce","target":"graph","created_at":"2026-08-05T01:33:16Z","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/2412.12641/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the Lagrangian Index Policy (LIP) for restless multi-armed bandits with long-run average reward. In particular, we compare the performance of LIP with the performance of the Whittle Index Policy (WIP), both heuristic policies known to be asymptotically optimal under certain natural conditions. Even though in most cases their performances are very similar, in the cases when WIP shows bad performance, LIP continues to perform very well. We then propose reinforcement learning algorithms, both tabular and NN-based, to obtain online learning schemes for LIP in the model-free setting. The p","authors_text":"Konstantin Avrachenkov, Pratik Shah, Vivek S. Borkar","cross_cats":["cs.AI","math.OC","math.PR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-17T08:03:53Z","title":"Lagrangian Index Policy for Restless Bandits with Average Reward"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12641","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":"sha256:751c5eae93c2575de1bde151191f9cf5804c7427534132bac86d6074b5410f77","target":"record","created_at":"2026-08-05T01:33:16Z","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":"2b7936738988577cfa52fc9bd858de76270fd9aea012d3e7205cd05bf38823da","cross_cats_sorted":["cs.AI","math.OC","math.PR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-17T08:03:53Z","title_canon_sha256":"35ce611467458c9fe143fcd3a396a0a890a379fdf93cd009a2a99f5e1289e967"},"schema_version":"1.0","source":{"id":"2412.12641","kind":"arxiv","version":3}},"canonical_sha256":"2e147e5bd3a3b23584e72d3d3cab141cdb3ed6a8174c8c4da1f572558a51d0ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e147e5bd3a3b23584e72d3d3cab141cdb3ed6a8174c8c4da1f572558a51d0ef","first_computed_at":"2026-08-05T01:33:16.167044Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T01:33:16.167044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"15zC4fQKWeJ38JrhvLyk7kDKJUMdPbOfpJkXsx1avIf6VkRGDdAYBs6CM+vJ8BuRGgLkYsonHhbfKxs+LVrUDA==","signature_status":"signed_v1","signed_at":"2026-08-05T01:33:16.168607Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.12641","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:751c5eae93c2575de1bde151191f9cf5804c7427534132bac86d6074b5410f77","sha256:5f9d97b6312837dcd3e8ca95aa9b0acd10343623334ab8f22b11836d27ba33ce"],"state_sha256":"a8c15d6b32563c574139c90d3a4cca30a8b719aa25cd6163379e50ed71c60db9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bbVpZQ27iIldAchEXCPq1lXdX9fSEdKCx7YyHTOCBraWrqlKt6tzN9Fdz/t+VLMpzCdfb7zIKxM/Wupo/TyLDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T08:26:37.811964Z","bundle_sha256":"09c470bcf286b65daea069fe4d71c30642ff5d52e5bfdc2f3ce4f9aa24da1ff5"}}