{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MIWQIA5PVY47E3BIW4KWPZ42UK","short_pith_number":"pith:MIWQIA5P","canonical_record":{"source":{"id":"2506.06873","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-07T17:37:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4afc54c56643e895b57a522de221aa13a49ac726de2f30e7ac81f006ca0b5ee6","abstract_canon_sha256":"159280e510060505fa5a4e7d2d97a8e0cb8a8f8fc6a26e1f3a7a175523b9a55a"},"schema_version":"1.0"},"canonical_sha256":"622d0403afae39f26c28b71567e79aa299560fc0311c5fea8076d3258d9069f8","source":{"kind":"arxiv","id":"2506.06873","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06873","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06873v1","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06873","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"pith_short_12","alias_value":"MIWQIA5PVY47","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"pith_short_16","alias_value":"MIWQIA5PVY47E3BI","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"pith_short_8","alias_value":"MIWQIA5P","created_at":"2026-07-05T11:17:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MIWQIA5PVY47E3BIW4KWPZ42UK","target":"record","payload":{"canonical_record":{"source":{"id":"2506.06873","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-07T17:37:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4afc54c56643e895b57a522de221aa13a49ac726de2f30e7ac81f006ca0b5ee6","abstract_canon_sha256":"159280e510060505fa5a4e7d2d97a8e0cb8a8f8fc6a26e1f3a7a175523b9a55a"},"schema_version":"1.0"},"canonical_sha256":"622d0403afae39f26c28b71567e79aa299560fc0311c5fea8076d3258d9069f8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:57.297557Z","signature_b64":"pg13t3bKeHzYRC4jjuPDDZhsMhfoofbnOODDbDvuw+N63p96TXXd6xypo4q6S2ujHQp5/I9Rmym1pIExSHl/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"622d0403afae39f26c28b71567e79aa299560fc0311c5fea8076d3258d9069f8","last_reissued_at":"2026-07-05T11:17:57.296963Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:57.296963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.06873","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":"2026-07-05T11:17:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DtxG328tjhlo9pNEV9L7nvjRsre9uot0ua+d3++48dLmIZXLqebaDbSrDfl51RTuBqs8KX+FCcKLzhVcKJbHAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T16:14:45.776846Z"},"content_sha256":"c2ad2a64a0c932a4326f4625c04a4c5023c17fe1f714e3ef94a47ef0fde80c37","schema_version":"1.0","event_id":"sha256:c2ad2a64a0c932a4326f4625c04a4c5023c17fe1f714e3ef94a47ef0fde80c37"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MIWQIA5PVY47E3BIW4KWPZ42UK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Log-Sum-Exponential Estimator for Off-Policy Evaluation and Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alireza Aghaei, Armin Behnamnia, Chengchun Shi, Gholamali Aminian, Hamid R. Rabiee, Vincent Y. F. Tan","submitted_at":"2025-06-07T17:37:10Z","abstract_excerpt":"Off-policy learning and evaluation leverage logged bandit feedback datasets, which contain context, action, propensity score, and feedback for each data point. These scenarios face significant challenges due to high variance and poor performance with low-quality propensity scores and heavy-tailed reward distributions. We address these issues by introducing a novel estimator based on the log-sum-exponential (LSE) operator, which outperforms traditional inverse propensity score estimators. Our LSE estimator demonstrates variance reduction and robustness under heavy-tailed conditions. For off-pol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06873","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/2506.06873/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":"2026-07-05T11:17:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JzG3+I+pQ3RU+Z+nib7vDXmyWowXTAz11BElyYVAvVFpjOBU1ahjEwNyGAkJ6rJX98k2stS1i7bynhTvO9d2DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T16:14:45.777466Z"},"content_sha256":"2cf98026343702ebd67b6529fa9134a073f7161220ae60520a6fc2ec6afbbb59","schema_version":"1.0","event_id":"sha256:2cf98026343702ebd67b6529fa9134a073f7161220ae60520a6fc2ec6afbbb59"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MIWQIA5PVY47E3BIW4KWPZ42UK/bundle.json","state_url":"https://pith.science/pith/MIWQIA5PVY47E3BIW4KWPZ42UK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MIWQIA5PVY47E3BIW4KWPZ42UK/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":"2026-08-17T16:14:45Z","links":{"resolver":"https://pith.science/pith/MIWQIA5PVY47E3BIW4KWPZ42UK","bundle":"https://pith.science/pith/MIWQIA5PVY47E3BIW4KWPZ42UK/bundle.json","state":"https://pith.science/pith/MIWQIA5PVY47E3BIW4KWPZ42UK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MIWQIA5PVY47E3BIW4KWPZ42UK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MIWQIA5PVY47E3BIW4KWPZ42UK","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":"159280e510060505fa5a4e7d2d97a8e0cb8a8f8fc6a26e1f3a7a175523b9a55a","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-07T17:37:10Z","title_canon_sha256":"4afc54c56643e895b57a522de221aa13a49ac726de2f30e7ac81f006ca0b5ee6"},"schema_version":"1.0","source":{"id":"2506.06873","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06873","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06873v1","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06873","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"pith_short_12","alias_value":"MIWQIA5PVY47","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"pith_short_16","alias_value":"MIWQIA5PVY47E3BI","created_at":"2026-07-05T11:17:57Z"},{"alias_kind":"pith_short_8","alias_value":"MIWQIA5P","created_at":"2026-07-05T11:17:57Z"}],"graph_snapshots":[{"event_id":"sha256:2cf98026343702ebd67b6529fa9134a073f7161220ae60520a6fc2ec6afbbb59","target":"graph","created_at":"2026-07-05T11:17:57Z","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/2506.06873/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Off-policy learning and evaluation leverage logged bandit feedback datasets, which contain context, action, propensity score, and feedback for each data point. These scenarios face significant challenges due to high variance and poor performance with low-quality propensity scores and heavy-tailed reward distributions. We address these issues by introducing a novel estimator based on the log-sum-exponential (LSE) operator, which outperforms traditional inverse propensity score estimators. Our LSE estimator demonstrates variance reduction and robustness under heavy-tailed conditions. For off-pol","authors_text":"Alireza Aghaei, Armin Behnamnia, Chengchun Shi, Gholamali Aminian, Hamid R. Rabiee, Vincent Y. F. Tan","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-07T17:37:10Z","title":"Log-Sum-Exponential Estimator for Off-Policy Evaluation and Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06873","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:c2ad2a64a0c932a4326f4625c04a4c5023c17fe1f714e3ef94a47ef0fde80c37","target":"record","created_at":"2026-07-05T11:17:57Z","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":"159280e510060505fa5a4e7d2d97a8e0cb8a8f8fc6a26e1f3a7a175523b9a55a","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-07T17:37:10Z","title_canon_sha256":"4afc54c56643e895b57a522de221aa13a49ac726de2f30e7ac81f006ca0b5ee6"},"schema_version":"1.0","source":{"id":"2506.06873","kind":"arxiv","version":1}},"canonical_sha256":"622d0403afae39f26c28b71567e79aa299560fc0311c5fea8076d3258d9069f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"622d0403afae39f26c28b71567e79aa299560fc0311c5fea8076d3258d9069f8","first_computed_at":"2026-07-05T11:17:57.296963Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:57.296963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pg13t3bKeHzYRC4jjuPDDZhsMhfoofbnOODDbDvuw+N63p96TXXd6xypo4q6S2ujHQp5/I9Rmym1pIExSHl/CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:57.297557Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.06873","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2ad2a64a0c932a4326f4625c04a4c5023c17fe1f714e3ef94a47ef0fde80c37","sha256:2cf98026343702ebd67b6529fa9134a073f7161220ae60520a6fc2ec6afbbb59"],"state_sha256":"2487b5ccb3a804184ce658cdaeb2710ec3d8979a06e4bea1b13205fd2259b645"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zhJAQvFlLrDTJiYhdY5OQB96lOJHGEr3xxpEFKmPJNeE0BmtVSxkJr5xAZ0RmqgeubEE1m5QeyaG+Mqh/+TVAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T16:14:45.780641Z","bundle_sha256":"508892429874ca06281788112e57b37cb0d22be9ed2d8039dd6e931fc93722a7"}}