{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:T2CGGSQYQZDMYSOQLFFHZJ52PR","short_pith_number":"pith:T2CGGSQY","canonical_record":{"source":{"id":"2406.13633","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-19T15:29:14Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"93f0ce35b246ebe07f2c210dbe0ef210f02c02b31ad0a7526eab3dc359506ad6","abstract_canon_sha256":"a4cff1852dfce6bc57361c00cc4582f5e02e3d6add67b3ed7c86db326b6a5d03"},"schema_version":"1.0"},"canonical_sha256":"9e84634a188646cc49d0594a7ca7ba7c6ac0f5fb9f07d4f597319791296de045","source":{"kind":"arxiv","id":"2406.13633","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.13633","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"arxiv_version","alias_value":"2406.13633v3","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13633","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"pith_short_12","alias_value":"T2CGGSQYQZDM","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"pith_short_16","alias_value":"T2CGGSQYQZDMYSOQ","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"pith_short_8","alias_value":"T2CGGSQY","created_at":"2026-07-05T09:19:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:T2CGGSQYQZDMYSOQLFFHZJ52PR","target":"record","payload":{"canonical_record":{"source":{"id":"2406.13633","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-19T15:29:14Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"93f0ce35b246ebe07f2c210dbe0ef210f02c02b31ad0a7526eab3dc359506ad6","abstract_canon_sha256":"a4cff1852dfce6bc57361c00cc4582f5e02e3d6add67b3ed7c86db326b6a5d03"},"schema_version":"1.0"},"canonical_sha256":"9e84634a188646cc49d0594a7ca7ba7c6ac0f5fb9f07d4f597319791296de045","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:59.692469Z","signature_b64":"eU1QdRBPrDnDTKV+sIevbvFVrFEix68yeiiMeXJmK3E/m2ada+BR4ZwG+2I9ZtMVx9TxaN2ySupcPCJL/6nrDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e84634a188646cc49d0594a7ca7ba7c6ac0f5fb9f07d4f597319791296de045","last_reissued_at":"2026-07-05T09:19:59.691994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:59.691994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.13633","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":"2026-07-05T09:19:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"acHyY+YV9jK5TqzHLGs5L2n3NDSO9XHl0C8IbQ9awEQ/eg5uZYg8oU0E2SoQCNmXEXghw5D9If/mjkDJCiQvAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:44:50.301127Z"},"content_sha256":"c33e2dd79edf801e83caa9f08596ec9c88d039be738c86ef662bd82b14d72999","schema_version":"1.0","event_id":"sha256:c33e2dd79edf801e83caa9f08596ec9c88d039be738c86ef662bd82b14d72999"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:T2CGGSQYQZDMYSOQLFFHZJ52PR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Infinite-Horizon Reinforcement Learning with Multinomial Logistic Function Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Dabeen Lee, Jaehyun Park, Junyeop Kwon","submitted_at":"2024-06-19T15:29:14Z","abstract_excerpt":"We study model-based reinforcement learning with non-linear function approximation where the transition function of the underlying Markov decision process (MDP) is given by a multinomial logistic (MNL) model. We develop a provably efficient discounted value iteration-based algorithm that works for both infinite-horizon average-reward and discounted-reward settings. For average-reward communicating MDPs, the algorithm guarantees a regret upper bound of $\\tilde{\\mathcal{O}}(dD\\sqrt{T})$ where $d$ is the dimension of feature mapping, $D$ is the diameter of the underlying MDP, and $T$ is the horiz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13633","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/2406.13633/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":"2026-07-05T09:19:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rXEbDXydd5W33w3MOGKpd/M1sDWPhaqcTJ2tYoqcIqPjBxRxhMVhIZl+7lnYqwi0/7uBv5MyAvGwy/2FlzVrAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:44:50.301531Z"},"content_sha256":"eca7c9a3196e5dcd66237b118a535dfbc4672eb0218fca62b718117e974c20f1","schema_version":"1.0","event_id":"sha256:eca7c9a3196e5dcd66237b118a535dfbc4672eb0218fca62b718117e974c20f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T2CGGSQYQZDMYSOQLFFHZJ52PR/bundle.json","state_url":"https://pith.science/pith/T2CGGSQYQZDMYSOQLFFHZJ52PR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T2CGGSQYQZDMYSOQLFFHZJ52PR/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":"2026-07-06T15:44:50Z","links":{"resolver":"https://pith.science/pith/T2CGGSQYQZDMYSOQLFFHZJ52PR","bundle":"https://pith.science/pith/T2CGGSQYQZDMYSOQLFFHZJ52PR/bundle.json","state":"https://pith.science/pith/T2CGGSQYQZDMYSOQLFFHZJ52PR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T2CGGSQYQZDMYSOQLFFHZJ52PR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:T2CGGSQYQZDMYSOQLFFHZJ52PR","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":"a4cff1852dfce6bc57361c00cc4582f5e02e3d6add67b3ed7c86db326b6a5d03","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-19T15:29:14Z","title_canon_sha256":"93f0ce35b246ebe07f2c210dbe0ef210f02c02b31ad0a7526eab3dc359506ad6"},"schema_version":"1.0","source":{"id":"2406.13633","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.13633","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"arxiv_version","alias_value":"2406.13633v3","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13633","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"pith_short_12","alias_value":"T2CGGSQYQZDM","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"pith_short_16","alias_value":"T2CGGSQYQZDMYSOQ","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"pith_short_8","alias_value":"T2CGGSQY","created_at":"2026-07-05T09:19:59Z"}],"graph_snapshots":[{"event_id":"sha256:eca7c9a3196e5dcd66237b118a535dfbc4672eb0218fca62b718117e974c20f1","target":"graph","created_at":"2026-07-05T09:19:59Z","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/2406.13633/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study model-based reinforcement learning with non-linear function approximation where the transition function of the underlying Markov decision process (MDP) is given by a multinomial logistic (MNL) model. We develop a provably efficient discounted value iteration-based algorithm that works for both infinite-horizon average-reward and discounted-reward settings. For average-reward communicating MDPs, the algorithm guarantees a regret upper bound of $\\tilde{\\mathcal{O}}(dD\\sqrt{T})$ where $d$ is the dimension of feature mapping, $D$ is the diameter of the underlying MDP, and $T$ is the horiz","authors_text":"Dabeen Lee, Jaehyun Park, Junyeop Kwon","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-19T15:29:14Z","title":"Infinite-Horizon Reinforcement Learning with Multinomial Logistic Function Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13633","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:c33e2dd79edf801e83caa9f08596ec9c88d039be738c86ef662bd82b14d72999","target":"record","created_at":"2026-07-05T09:19:59Z","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":"a4cff1852dfce6bc57361c00cc4582f5e02e3d6add67b3ed7c86db326b6a5d03","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-19T15:29:14Z","title_canon_sha256":"93f0ce35b246ebe07f2c210dbe0ef210f02c02b31ad0a7526eab3dc359506ad6"},"schema_version":"1.0","source":{"id":"2406.13633","kind":"arxiv","version":3}},"canonical_sha256":"9e84634a188646cc49d0594a7ca7ba7c6ac0f5fb9f07d4f597319791296de045","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e84634a188646cc49d0594a7ca7ba7c6ac0f5fb9f07d4f597319791296de045","first_computed_at":"2026-07-05T09:19:59.691994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:59.691994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eU1QdRBPrDnDTKV+sIevbvFVrFEix68yeiiMeXJmK3E/m2ada+BR4ZwG+2I9ZtMVx9TxaN2ySupcPCJL/6nrDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:59.692469Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.13633","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c33e2dd79edf801e83caa9f08596ec9c88d039be738c86ef662bd82b14d72999","sha256:eca7c9a3196e5dcd66237b118a535dfbc4672eb0218fca62b718117e974c20f1"],"state_sha256":"c010be2d871a395d70f1ee056a388ddf38cd6d8ecf3f939b74f50b38ae937c68"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EjigQv2YeJh5lv7rum/GY0oOMWodUR0tC9P119vJPjNi7zMZ5fovuXN9O/WT1kkvLtrlBylkkAzY6hHylhbJCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T15:44:50.303527Z","bundle_sha256":"fa976467f577f86b9c4916b4da0db6a00a4a7b5fa8474814dcb307b9fb5b8a79"}}