{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NXZMCAF3TLZYUHHMSKK47QYGNO","short_pith_number":"pith:NXZMCAF3","canonical_record":{"source":{"id":"2503.02735","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-04T15:55:55Z","cross_cats_sorted":[],"title_canon_sha256":"c2cd5c5bacc0733dd6d27dba856d71711d266bce0c130ee93dc60db92f99290c","abstract_canon_sha256":"b4b0bb731bd8d67ea2f51c5c0a1b63707e1df15b4d4bad07126fe3772e9059aa"},"schema_version":"1.0"},"canonical_sha256":"6df2c100bb9af38a1cec9295cfc3066b86b560775c9d46fc967e5c82caa74ea8","source":{"kind":"arxiv","id":"2503.02735","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.02735","created_at":"2026-07-05T10:24:12Z"},{"alias_kind":"arxiv_version","alias_value":"2503.02735v1","created_at":"2026-07-05T10:24:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02735","created_at":"2026-07-05T10:24:12Z"},{"alias_kind":"pith_short_12","alias_value":"NXZMCAF3TLZY","created_at":"2026-07-05T10:24:12Z"},{"alias_kind":"pith_short_16","alias_value":"NXZMCAF3TLZYUHHM","created_at":"2026-07-05T10:24:12Z"},{"alias_kind":"pith_short_8","alias_value":"NXZMCAF3","created_at":"2026-07-05T10:24:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NXZMCAF3TLZYUHHMSKK47QYGNO","target":"record","payload":{"canonical_record":{"source":{"id":"2503.02735","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-04T15:55:55Z","cross_cats_sorted":[],"title_canon_sha256":"c2cd5c5bacc0733dd6d27dba856d71711d266bce0c130ee93dc60db92f99290c","abstract_canon_sha256":"b4b0bb731bd8d67ea2f51c5c0a1b63707e1df15b4d4bad07126fe3772e9059aa"},"schema_version":"1.0"},"canonical_sha256":"6df2c100bb9af38a1cec9295cfc3066b86b560775c9d46fc967e5c82caa74ea8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:12.828167Z","signature_b64":"V7MFvRwluWdo/GyJQFzkJlUjedo0Hy8UayZQefyaIGafadFQNTJhBs77OPrFeZnqcfu7FpQQegt9u30TwQfdBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6df2c100bb9af38a1cec9295cfc3066b86b560775c9d46fc967e5c82caa74ea8","last_reissued_at":"2026-07-05T10:24:12.827179Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:12.827179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.02735","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":"2026-07-05T10:24:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qgVuJTDGrevH62aPl6uj2omt9635ryswY6OBoE4IJR4C9yzaIq45m4ACqvq2tS3He80mS7Y6Br0piAFzn93FBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T18:57:01.284488Z"},"content_sha256":"da6a5550c8545e21df898d0d5532b5871d28c8a14735ced55b9a74eeb46506ad","schema_version":"1.0","event_id":"sha256:da6a5550c8545e21df898d0d5532b5871d28c8a14735ced55b9a74eeb46506ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NXZMCAF3TLZYUHHMSKK47QYGNO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Clustered KL-barycenter design for policy evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Claire Vernade, Giorgia Ramponi, Leif D\\\"oring, Simon Weissmann, Till Freihaut","submitted_at":"2025-03-04T15:55:55Z","abstract_excerpt":"In the context of stochastic bandit models, this article examines how to design sample-efficient behavior policies for the importance sampling evaluation of multiple target policies. From importance sampling theory, it is well established that sample efficiency is highly sensitive to the KL divergence between the target and importance sampling distributions. We first analyze a single behavior policy defined as the KL-barycenter of the target policies. Then, we refine this approach by clustering the target policies into groups with small KL divergences and assigning each cluster its own KL-bary"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02735","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/2503.02735/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":"2026-07-05T10:24:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g1Mv5nV/j73mQtgrlfii0vZCANKZlKJR2Uu0OgMCt4ql8bkGoU9PCeeP5rW/sdhCOHaQno4JFHJxe5qNhSWiDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T18:57:01.285106Z"},"content_sha256":"0d5d750ed6c601fd136be8958f6195187e1336e31b6006e328541d640dfc252c","schema_version":"1.0","event_id":"sha256:0d5d750ed6c601fd136be8958f6195187e1336e31b6006e328541d640dfc252c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NXZMCAF3TLZYUHHMSKK47QYGNO/bundle.json","state_url":"https://pith.science/pith/NXZMCAF3TLZYUHHMSKK47QYGNO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NXZMCAF3TLZYUHHMSKK47QYGNO/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":"2026-08-13T18:57:01Z","links":{"resolver":"https://pith.science/pith/NXZMCAF3TLZYUHHMSKK47QYGNO","bundle":"https://pith.science/pith/NXZMCAF3TLZYUHHMSKK47QYGNO/bundle.json","state":"https://pith.science/pith/NXZMCAF3TLZYUHHMSKK47QYGNO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NXZMCAF3TLZYUHHMSKK47QYGNO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NXZMCAF3TLZYUHHMSKK47QYGNO","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":"b4b0bb731bd8d67ea2f51c5c0a1b63707e1df15b4d4bad07126fe3772e9059aa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-04T15:55:55Z","title_canon_sha256":"c2cd5c5bacc0733dd6d27dba856d71711d266bce0c130ee93dc60db92f99290c"},"schema_version":"1.0","source":{"id":"2503.02735","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.02735","created_at":"2026-07-05T10:24:12Z"},{"alias_kind":"arxiv_version","alias_value":"2503.02735v1","created_at":"2026-07-05T10:24:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02735","created_at":"2026-07-05T10:24:12Z"},{"alias_kind":"pith_short_12","alias_value":"NXZMCAF3TLZY","created_at":"2026-07-05T10:24:12Z"},{"alias_kind":"pith_short_16","alias_value":"NXZMCAF3TLZYUHHM","created_at":"2026-07-05T10:24:12Z"},{"alias_kind":"pith_short_8","alias_value":"NXZMCAF3","created_at":"2026-07-05T10:24:12Z"}],"graph_snapshots":[{"event_id":"sha256:0d5d750ed6c601fd136be8958f6195187e1336e31b6006e328541d640dfc252c","target":"graph","created_at":"2026-07-05T10:24:12Z","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/2503.02735/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the context of stochastic bandit models, this article examines how to design sample-efficient behavior policies for the importance sampling evaluation of multiple target policies. From importance sampling theory, it is well established that sample efficiency is highly sensitive to the KL divergence between the target and importance sampling distributions. We first analyze a single behavior policy defined as the KL-barycenter of the target policies. Then, we refine this approach by clustering the target policies into groups with small KL divergences and assigning each cluster its own KL-bary","authors_text":"Claire Vernade, Giorgia Ramponi, Leif D\\\"oring, Simon Weissmann, Till Freihaut","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-04T15:55:55Z","title":"Clustered KL-barycenter design for policy evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02735","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:da6a5550c8545e21df898d0d5532b5871d28c8a14735ced55b9a74eeb46506ad","target":"record","created_at":"2026-07-05T10:24:12Z","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":"b4b0bb731bd8d67ea2f51c5c0a1b63707e1df15b4d4bad07126fe3772e9059aa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-04T15:55:55Z","title_canon_sha256":"c2cd5c5bacc0733dd6d27dba856d71711d266bce0c130ee93dc60db92f99290c"},"schema_version":"1.0","source":{"id":"2503.02735","kind":"arxiv","version":1}},"canonical_sha256":"6df2c100bb9af38a1cec9295cfc3066b86b560775c9d46fc967e5c82caa74ea8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6df2c100bb9af38a1cec9295cfc3066b86b560775c9d46fc967e5c82caa74ea8","first_computed_at":"2026-07-05T10:24:12.827179Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:24:12.827179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V7MFvRwluWdo/GyJQFzkJlUjedo0Hy8UayZQefyaIGafadFQNTJhBs77OPrFeZnqcfu7FpQQegt9u30TwQfdBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:24:12.828167Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.02735","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da6a5550c8545e21df898d0d5532b5871d28c8a14735ced55b9a74eeb46506ad","sha256:0d5d750ed6c601fd136be8958f6195187e1336e31b6006e328541d640dfc252c"],"state_sha256":"e2ba74c75e8c6ed504ab1bbc7cc9e087f72f282d712a5e8bdcf8b92468256c24"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Io1C+LKVA7L5+7JPZQ/yJf3h+RT7V06rLsI7y/bG04ca8Y1tnc/3Hj9tBOyldimJN2S8PXVIbZAqm9EZQBFiCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T18:57:01.289086Z","bundle_sha256":"42e1a4d385641014c844c10ba91bc8dfb9ecaaf2f92a977f6bab17a6c23b0bbd"}}