{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EF3YWF7VLDRLDEPCZJ7HWY5J4J","short_pith_number":"pith:EF3YWF7V","canonical_record":{"source":{"id":"2412.11120","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-15T08:51:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6313e2595a5f3c188e919906efd4ce2eec10a7114ad8d139aae52ce03fddb69b","abstract_canon_sha256":"52400f9c83abe0a85b2bbed2a93140f5a7f49957b0b38f0b1f84de9ecc600c7d"},"schema_version":"1.0"},"canonical_sha256":"21778b17f558e2b191e2ca7e7b63a9e2416b89a68bd60d7cd28f18166adc36d3","source":{"kind":"arxiv","id":"2412.11120","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11120","created_at":"2026-07-05T09:59:01Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11120v2","created_at":"2026-07-05T09:59:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11120","created_at":"2026-07-05T09:59:01Z"},{"alias_kind":"pith_short_12","alias_value":"EF3YWF7VLDRL","created_at":"2026-07-05T09:59:01Z"},{"alias_kind":"pith_short_16","alias_value":"EF3YWF7VLDRLDEPC","created_at":"2026-07-05T09:59:01Z"},{"alias_kind":"pith_short_8","alias_value":"EF3YWF7V","created_at":"2026-07-05T09:59:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EF3YWF7VLDRLDEPCZJ7HWY5J4J","target":"record","payload":{"canonical_record":{"source":{"id":"2412.11120","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-15T08:51:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6313e2595a5f3c188e919906efd4ce2eec10a7114ad8d139aae52ce03fddb69b","abstract_canon_sha256":"52400f9c83abe0a85b2bbed2a93140f5a7f49957b0b38f0b1f84de9ecc600c7d"},"schema_version":"1.0"},"canonical_sha256":"21778b17f558e2b191e2ca7e7b63a9e2416b89a68bd60d7cd28f18166adc36d3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:01.686992Z","signature_b64":"jdEfeM3JAipOe9p+kerJIFBKleg2Y47qDkbcr+IeMtiT+vYPuT+ngIZvaWjlxJyaV2z4i6YDOQbvvrB+ilb6Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21778b17f558e2b191e2ca7e7b63a9e2416b89a68bd60d7cd28f18166adc36d3","last_reissued_at":"2026-07-05T09:59:01.686532Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:01.686532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.11120","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":"2026-07-05T09:59:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nK8f45yr+Apxsds9muvbbN6Z4sfsslJKvdTcSzYPyxoWhY8unlZjJ8qjbAffnmDFY3114NNQ/N5rgfGQq3fQAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:53:57.336413Z"},"content_sha256":"d8ef2dfb21d90e82be5a673a180edf9fa5b9ef91f154be13bce9b8898dd32525","schema_version":"1.0","event_id":"sha256:d8ef2dfb21d90e82be5a673a180edf9fa5b9ef91f154be13bce9b8898dd32525"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EF3YWF7VLDRLDEPCZJ7HWY5J4J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Boyuan Wang, Chang Liu, Cheems Wang, Xiangyang Ji, Yixiu Mao, Yuhang Jiang, Yun Qu","submitted_at":"2024-12-15T08:51:14Z","abstract_excerpt":"Reinforcement learning (RL) often encounters delayed and sparse feedback in real-world applications, even with only episodic rewards. Previous approaches have made some progress in reward redistribution for credit assignment but still face challenges, including training difficulties due to redundancy and ambiguous attributions stemming from overlooking the multifaceted nature of mission performance evaluation. Hopefully, Large Language Model (LLM) encompasses fruitful decision-making knowledge and provides a plausible tool for reward redistribution. Even so, deploying LLM in this case is non-t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11120","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/2412.11120/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":"2026-07-05T09:59:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5fbQcOnHjNThSI96+A4CznZ3SSiQ9rB1+dbkssauTB5f4ZSaYKgxN/PVO5aBb3ta1bwBCHbMeL1OAqhBIK9oCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:53:57.337342Z"},"content_sha256":"267c32c1aca99392dfd83302880b69c928f7349f14684ee349a1662189c76633","schema_version":"1.0","event_id":"sha256:267c32c1aca99392dfd83302880b69c928f7349f14684ee349a1662189c76633"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EF3YWF7VLDRLDEPCZJ7HWY5J4J/bundle.json","state_url":"https://pith.science/pith/EF3YWF7VLDRLDEPCZJ7HWY5J4J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EF3YWF7VLDRLDEPCZJ7HWY5J4J/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":"2026-08-04T04:53:57Z","links":{"resolver":"https://pith.science/pith/EF3YWF7VLDRLDEPCZJ7HWY5J4J","bundle":"https://pith.science/pith/EF3YWF7VLDRLDEPCZJ7HWY5J4J/bundle.json","state":"https://pith.science/pith/EF3YWF7VLDRLDEPCZJ7HWY5J4J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EF3YWF7VLDRLDEPCZJ7HWY5J4J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EF3YWF7VLDRLDEPCZJ7HWY5J4J","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":"52400f9c83abe0a85b2bbed2a93140f5a7f49957b0b38f0b1f84de9ecc600c7d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-15T08:51:14Z","title_canon_sha256":"6313e2595a5f3c188e919906efd4ce2eec10a7114ad8d139aae52ce03fddb69b"},"schema_version":"1.0","source":{"id":"2412.11120","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11120","created_at":"2026-07-05T09:59:01Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11120v2","created_at":"2026-07-05T09:59:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11120","created_at":"2026-07-05T09:59:01Z"},{"alias_kind":"pith_short_12","alias_value":"EF3YWF7VLDRL","created_at":"2026-07-05T09:59:01Z"},{"alias_kind":"pith_short_16","alias_value":"EF3YWF7VLDRLDEPC","created_at":"2026-07-05T09:59:01Z"},{"alias_kind":"pith_short_8","alias_value":"EF3YWF7V","created_at":"2026-07-05T09:59:01Z"}],"graph_snapshots":[{"event_id":"sha256:267c32c1aca99392dfd83302880b69c928f7349f14684ee349a1662189c76633","target":"graph","created_at":"2026-07-05T09:59:01Z","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/2412.11120/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) often encounters delayed and sparse feedback in real-world applications, even with only episodic rewards. Previous approaches have made some progress in reward redistribution for credit assignment but still face challenges, including training difficulties due to redundancy and ambiguous attributions stemming from overlooking the multifaceted nature of mission performance evaluation. Hopefully, Large Language Model (LLM) encompasses fruitful decision-making knowledge and provides a plausible tool for reward redistribution. Even so, deploying LLM in this case is non-t","authors_text":"Boyuan Wang, Chang Liu, Cheems Wang, Xiangyang Ji, Yixiu Mao, Yuhang Jiang, Yun Qu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-15T08:51:14Z","title":"Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11120","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:d8ef2dfb21d90e82be5a673a180edf9fa5b9ef91f154be13bce9b8898dd32525","target":"record","created_at":"2026-07-05T09:59:01Z","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":"52400f9c83abe0a85b2bbed2a93140f5a7f49957b0b38f0b1f84de9ecc600c7d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-15T08:51:14Z","title_canon_sha256":"6313e2595a5f3c188e919906efd4ce2eec10a7114ad8d139aae52ce03fddb69b"},"schema_version":"1.0","source":{"id":"2412.11120","kind":"arxiv","version":2}},"canonical_sha256":"21778b17f558e2b191e2ca7e7b63a9e2416b89a68bd60d7cd28f18166adc36d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21778b17f558e2b191e2ca7e7b63a9e2416b89a68bd60d7cd28f18166adc36d3","first_computed_at":"2026-07-05T09:59:01.686532Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:59:01.686532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jdEfeM3JAipOe9p+kerJIFBKleg2Y47qDkbcr+IeMtiT+vYPuT+ngIZvaWjlxJyaV2z4i6YDOQbvvrB+ilb6Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:59:01.686992Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.11120","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d8ef2dfb21d90e82be5a673a180edf9fa5b9ef91f154be13bce9b8898dd32525","sha256:267c32c1aca99392dfd83302880b69c928f7349f14684ee349a1662189c76633"],"state_sha256":"8ffb2223db9549d4d1302222233921813ab99496c08930e4aeedf047b8acb7ee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m1FMu7H6LVajjf/HjM2htMXI6YR0Ka33jUWIdKkADNwbt9N4GnOCbrDfspIrIpLMyRBucsDbzBNkz47ivDKiCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T04:53:57.366052Z","bundle_sha256":"23026ab3268ff61eedc736e8bbbdeaf326bee743538365d7a90031f64a47b687"}}