{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5FHTK76A65MCSDPKW6HDNXWIAG","short_pith_number":"pith:5FHTK76A","canonical_record":{"source":{"id":"2506.14439","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T11:58:11Z","cross_cats_sorted":[],"title_canon_sha256":"ee3b0811269c8ae32e5f41dc307bbb506abd60b189fab3a4c3c937e3f0632b3b","abstract_canon_sha256":"1666f898e031c5cc9bb0dacf030b12dd3fb9925e51b108df8284e2da68fe47d7"},"schema_version":"1.0"},"canonical_sha256":"e94f357fc0f758290deab78e36dec801bbc1c84eabe3810b4b6aba6da87fddff","source":{"kind":"arxiv","id":"2506.14439","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14439","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14439v1","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14439","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"pith_short_12","alias_value":"5FHTK76A65MC","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"pith_short_16","alias_value":"5FHTK76A65MCSDPK","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"pith_short_8","alias_value":"5FHTK76A","created_at":"2026-07-05T11:22:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5FHTK76A65MCSDPKW6HDNXWIAG","target":"record","payload":{"canonical_record":{"source":{"id":"2506.14439","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T11:58:11Z","cross_cats_sorted":[],"title_canon_sha256":"ee3b0811269c8ae32e5f41dc307bbb506abd60b189fab3a4c3c937e3f0632b3b","abstract_canon_sha256":"1666f898e031c5cc9bb0dacf030b12dd3fb9925e51b108df8284e2da68fe47d7"},"schema_version":"1.0"},"canonical_sha256":"e94f357fc0f758290deab78e36dec801bbc1c84eabe3810b4b6aba6da87fddff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:56.568543Z","signature_b64":"VWjVSdC/j04JiEi8DOuJvMJDIPkesuB/r+5rU54/ZHyHaM3LR7yWMb/CO4RlSAIgLzGZe+jkm2k5dPDXWP0cAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e94f357fc0f758290deab78e36dec801bbc1c84eabe3810b4b6aba6da87fddff","last_reissued_at":"2026-07-05T11:22:56.568128Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:56.568128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.14439","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":"2026-07-05T11:22:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"29S6ZeZBjJoYD/I0sCvMmGxEW4dXbHCsa0VzPnIgIu8UGo3UTgeab9M5u6qTT+3awScOHYPn82gPNEyDAB8mAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T12:22:08.086733Z"},"content_sha256":"da1bc7cd3120f504a58f5268838abdc7d79bd52b49674aa967583661305a6c79","schema_version":"1.0","event_id":"sha256:da1bc7cd3120f504a58f5268838abdc7d79bd52b49674aa967583661305a6c79"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5FHTK76A65MCSDPKW6HDNXWIAG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A General Framework for Off-Policy Learning with Partially-Observed Reward","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kosuke Kawakami, Masahiro Asami, Rikiya Takehi, Yuta Saito","submitted_at":"2025-06-17T11:58:11Z","abstract_excerpt":"Off-policy learning (OPL) in contextual bandits aims to learn a decision-making policy that maximizes the target rewards by using only historical interaction data collected under previously developed policies. Unfortunately, when rewards are only partially observed, the effectiveness of OPL degrades severely. Well-known examples of such partial rewards include explicit ratings in content recommendations, conversion signals on e-commerce platforms that are partial due to delay, and the issue of censoring in medical problems. One possible solution to deal with such partial rewards is to use seco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14439","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/2506.14439/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":"2026-07-05T11:22:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nYKcO992HUKu28txvUkiHJ9s294L8ONmU0Tsrw+4x8y9r9ugTUDqpg5yGwXnCcd3ERKtraWDOWXV1oDzwe93Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T12:22:08.087113Z"},"content_sha256":"0e0968bfb8360771ba580041ca279168ad28ac7f4224188e32a32623af85fe0e","schema_version":"1.0","event_id":"sha256:0e0968bfb8360771ba580041ca279168ad28ac7f4224188e32a32623af85fe0e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5FHTK76A65MCSDPKW6HDNXWIAG/bundle.json","state_url":"https://pith.science/pith/5FHTK76A65MCSDPKW6HDNXWIAG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5FHTK76A65MCSDPKW6HDNXWIAG/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":"2026-07-06T12:22:08Z","links":{"resolver":"https://pith.science/pith/5FHTK76A65MCSDPKW6HDNXWIAG","bundle":"https://pith.science/pith/5FHTK76A65MCSDPKW6HDNXWIAG/bundle.json","state":"https://pith.science/pith/5FHTK76A65MCSDPKW6HDNXWIAG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5FHTK76A65MCSDPKW6HDNXWIAG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5FHTK76A65MCSDPKW6HDNXWIAG","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":"1666f898e031c5cc9bb0dacf030b12dd3fb9925e51b108df8284e2da68fe47d7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T11:58:11Z","title_canon_sha256":"ee3b0811269c8ae32e5f41dc307bbb506abd60b189fab3a4c3c937e3f0632b3b"},"schema_version":"1.0","source":{"id":"2506.14439","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14439","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14439v1","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14439","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"pith_short_12","alias_value":"5FHTK76A65MC","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"pith_short_16","alias_value":"5FHTK76A65MCSDPK","created_at":"2026-07-05T11:22:56Z"},{"alias_kind":"pith_short_8","alias_value":"5FHTK76A","created_at":"2026-07-05T11:22:56Z"}],"graph_snapshots":[{"event_id":"sha256:0e0968bfb8360771ba580041ca279168ad28ac7f4224188e32a32623af85fe0e","target":"graph","created_at":"2026-07-05T11:22:56Z","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/2506.14439/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Off-policy learning (OPL) in contextual bandits aims to learn a decision-making policy that maximizes the target rewards by using only historical interaction data collected under previously developed policies. Unfortunately, when rewards are only partially observed, the effectiveness of OPL degrades severely. Well-known examples of such partial rewards include explicit ratings in content recommendations, conversion signals on e-commerce platforms that are partial due to delay, and the issue of censoring in medical problems. One possible solution to deal with such partial rewards is to use seco","authors_text":"Kosuke Kawakami, Masahiro Asami, Rikiya Takehi, Yuta Saito","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T11:58:11Z","title":"A General Framework for Off-Policy Learning with Partially-Observed Reward"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14439","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:da1bc7cd3120f504a58f5268838abdc7d79bd52b49674aa967583661305a6c79","target":"record","created_at":"2026-07-05T11:22:56Z","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":"1666f898e031c5cc9bb0dacf030b12dd3fb9925e51b108df8284e2da68fe47d7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T11:58:11Z","title_canon_sha256":"ee3b0811269c8ae32e5f41dc307bbb506abd60b189fab3a4c3c937e3f0632b3b"},"schema_version":"1.0","source":{"id":"2506.14439","kind":"arxiv","version":1}},"canonical_sha256":"e94f357fc0f758290deab78e36dec801bbc1c84eabe3810b4b6aba6da87fddff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e94f357fc0f758290deab78e36dec801bbc1c84eabe3810b4b6aba6da87fddff","first_computed_at":"2026-07-05T11:22:56.568128Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:56.568128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VWjVSdC/j04JiEi8DOuJvMJDIPkesuB/r+5rU54/ZHyHaM3LR7yWMb/CO4RlSAIgLzGZe+jkm2k5dPDXWP0cAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:56.568543Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.14439","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da1bc7cd3120f504a58f5268838abdc7d79bd52b49674aa967583661305a6c79","sha256:0e0968bfb8360771ba580041ca279168ad28ac7f4224188e32a32623af85fe0e"],"state_sha256":"18e3c160ee40e045eb03d99b642251405b1c380b7c97662b3f986a4386859623"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TvhSRLEh47Gw7v3BEoYq+yiMuRlkcvqwzKZjdey77RHUDVAPmR4QyXz5tjdRZR93TfTM8IMpBQBwqIELQ3Y1Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T12:22:08.089323Z","bundle_sha256":"a659f1e6324018554c7bc34558913b0c65cebf02d1f5d3cf75be277455a2ed37"}}