{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:II3TA3MRZFBELVRXASK7DFUVJW","short_pith_number":"pith:II3TA3MR","canonical_record":{"source":{"id":"2405.03329","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-06T10:09:35Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ae32e657f6d8ee1cd8962cd4591dc8253709f8cfbca99f5f78fccd63bf021340","abstract_canon_sha256":"1dd3dcb891675370870e9101cb6867e357af76d5c35f7b2a57f14fe938a196e1"},"schema_version":"1.0"},"canonical_sha256":"4237306d91c94245d6370495f196954da766ef90470862579129ffb818fc20b7","source":{"kind":"arxiv","id":"2405.03329","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.03329","created_at":"2026-07-05T09:06:59Z"},{"alias_kind":"arxiv_version","alias_value":"2405.03329v2","created_at":"2026-07-05T09:06:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03329","created_at":"2026-07-05T09:06:59Z"},{"alias_kind":"pith_short_12","alias_value":"II3TA3MRZFBE","created_at":"2026-07-05T09:06:59Z"},{"alias_kind":"pith_short_16","alias_value":"II3TA3MRZFBELVRX","created_at":"2026-07-05T09:06:59Z"},{"alias_kind":"pith_short_8","alias_value":"II3TA3MR","created_at":"2026-07-05T09:06:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:II3TA3MRZFBELVRXASK7DFUVJW","target":"record","payload":{"canonical_record":{"source":{"id":"2405.03329","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-06T10:09:35Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ae32e657f6d8ee1cd8962cd4591dc8253709f8cfbca99f5f78fccd63bf021340","abstract_canon_sha256":"1dd3dcb891675370870e9101cb6867e357af76d5c35f7b2a57f14fe938a196e1"},"schema_version":"1.0"},"canonical_sha256":"4237306d91c94245d6370495f196954da766ef90470862579129ffb818fc20b7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:59.415832Z","signature_b64":"t+BbbyFKZn9gffPkuY97+YZb10K4RPCjh8/0dkg/EMbWjmBmrIH0lhIqGaKDTtGgpPHV5LIJ3XNHj4vqSF/TBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4237306d91c94245d6370495f196954da766ef90470862579129ffb818fc20b7","last_reissued_at":"2026-07-05T09:06:59.415378Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:59.415378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.03329","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:06:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cdUQ4RO9o4dzLjAVwn3wtTllyy6lT04PBmXDuht9/9o51Th1tdvmNAiXln6vr2G2J4OWyRKFYXNTHv48QtSsAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T21:34:25.449167Z"},"content_sha256":"a7699b23e8a46386f34e47981385d2b773c4db65ed147732e3e287dc4e58f5a6","schema_version":"1.0","event_id":"sha256:a7699b23e8a46386f34e47981385d2b773c4db65ed147732e3e287dc4e58f5a6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:II3TA3MRZFBELVRXASK7DFUVJW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Policy Learning for Balancing Short-Term and Long-Term Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chunchen Liu, Feng Xie, Peng Wu, Yan Zeng, Zhongyao Wang, Ziyu Shen","submitted_at":"2024-05-06T10:09:35Z","abstract_excerpt":"Empirical researchers and decision-makers spanning various domains frequently seek profound insights into the long-term impacts of interventions. While the significance of long-term outcomes is undeniable, an overemphasis on them may inadvertently overshadow short-term gains. Motivated by this, this paper formalizes a new framework for learning the optimal policy that effectively balances both long-term and short-term rewards, where some long-term outcomes are allowed to be missing. In particular, we first present the identifiability of both rewards under mild assumptions. Next, we deduce the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03329","kind":"arxiv","version":2},"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/2405.03329/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":"2026-07-05T09:06:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I8CQ847PL9dbpu2vObmI3xoh4+pvOP8WxJdGAyUjlTOTmyh76weD7iCxk8688bMwhCBykUPIjbLyhynVIeHZCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T21:34:25.451451Z"},"content_sha256":"60c482e05457968d0a2fdf4bd2c3ef8b3c7c3a3c25627e7fddaa8d1304b2a8a7","schema_version":"1.0","event_id":"sha256:60c482e05457968d0a2fdf4bd2c3ef8b3c7c3a3c25627e7fddaa8d1304b2a8a7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/II3TA3MRZFBELVRXASK7DFUVJW/bundle.json","state_url":"https://pith.science/pith/II3TA3MRZFBELVRXASK7DFUVJW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/II3TA3MRZFBELVRXASK7DFUVJW/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":"2026-08-05T21:34:25Z","links":{"resolver":"https://pith.science/pith/II3TA3MRZFBELVRXASK7DFUVJW","bundle":"https://pith.science/pith/II3TA3MRZFBELVRXASK7DFUVJW/bundle.json","state":"https://pith.science/pith/II3TA3MRZFBELVRXASK7DFUVJW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/II3TA3MRZFBELVRXASK7DFUVJW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:II3TA3MRZFBELVRXASK7DFUVJW","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":"1dd3dcb891675370870e9101cb6867e357af76d5c35f7b2a57f14fe938a196e1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-06T10:09:35Z","title_canon_sha256":"ae32e657f6d8ee1cd8962cd4591dc8253709f8cfbca99f5f78fccd63bf021340"},"schema_version":"1.0","source":{"id":"2405.03329","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.03329","created_at":"2026-07-05T09:06:59Z"},{"alias_kind":"arxiv_version","alias_value":"2405.03329v2","created_at":"2026-07-05T09:06:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03329","created_at":"2026-07-05T09:06:59Z"},{"alias_kind":"pith_short_12","alias_value":"II3TA3MRZFBE","created_at":"2026-07-05T09:06:59Z"},{"alias_kind":"pith_short_16","alias_value":"II3TA3MRZFBELVRX","created_at":"2026-07-05T09:06:59Z"},{"alias_kind":"pith_short_8","alias_value":"II3TA3MR","created_at":"2026-07-05T09:06:59Z"}],"graph_snapshots":[{"event_id":"sha256:60c482e05457968d0a2fdf4bd2c3ef8b3c7c3a3c25627e7fddaa8d1304b2a8a7","target":"graph","created_at":"2026-07-05T09:06:59Z","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/2405.03329/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Empirical researchers and decision-makers spanning various domains frequently seek profound insights into the long-term impacts of interventions. While the significance of long-term outcomes is undeniable, an overemphasis on them may inadvertently overshadow short-term gains. Motivated by this, this paper formalizes a new framework for learning the optimal policy that effectively balances both long-term and short-term rewards, where some long-term outcomes are allowed to be missing. In particular, we first present the identifiability of both rewards under mild assumptions. Next, we deduce the ","authors_text":"Chunchen Liu, Feng Xie, Peng Wu, Yan Zeng, Zhongyao Wang, Ziyu Shen","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-06T10:09:35Z","title":"Policy Learning for Balancing Short-Term and Long-Term Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03329","kind":"arxiv","version":2},"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:a7699b23e8a46386f34e47981385d2b773c4db65ed147732e3e287dc4e58f5a6","target":"record","created_at":"2026-07-05T09:06:59Z","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":"1dd3dcb891675370870e9101cb6867e357af76d5c35f7b2a57f14fe938a196e1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-06T10:09:35Z","title_canon_sha256":"ae32e657f6d8ee1cd8962cd4591dc8253709f8cfbca99f5f78fccd63bf021340"},"schema_version":"1.0","source":{"id":"2405.03329","kind":"arxiv","version":2}},"canonical_sha256":"4237306d91c94245d6370495f196954da766ef90470862579129ffb818fc20b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4237306d91c94245d6370495f196954da766ef90470862579129ffb818fc20b7","first_computed_at":"2026-07-05T09:06:59.415378Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:06:59.415378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t+BbbyFKZn9gffPkuY97+YZb10K4RPCjh8/0dkg/EMbWjmBmrIH0lhIqGaKDTtGgpPHV5LIJ3XNHj4vqSF/TBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:06:59.415832Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.03329","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7699b23e8a46386f34e47981385d2b773c4db65ed147732e3e287dc4e58f5a6","sha256:60c482e05457968d0a2fdf4bd2c3ef8b3c7c3a3c25627e7fddaa8d1304b2a8a7"],"state_sha256":"94efbb7650d940eabd5f4b94ff5cd7213748cd053e983cf9a2e5c09bb01cace3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lIvDmpN333fWYzyszsVvK704QSf1EVRp04Td5Fit3WDMqvAqGtBOk93aQn7xpIZ7KKcazehl3AxizoAgIEgfBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T21:34:25.461565Z","bundle_sha256":"0e05b0632cbb8133c49bd1ae2e5176fba39e05b13df670d835d0fdaa9f1e1055"}}