{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:S6ICTCZTNGAF5JQCBNJWHBCFNE","short_pith_number":"pith:S6ICTCZT","canonical_record":{"source":{"id":"2503.21807","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-25T06:28:42Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"8b14562c8ab967332d019635fa418df5d88298f62d073c7cf378620609e69bf1","abstract_canon_sha256":"c62bbd7b51de56d5f7470b43c001a1879d9b6eac4b5e0c62fc9ba5ed1e9eb594"},"schema_version":"1.0"},"canonical_sha256":"9790298b3369805ea6020b536384456905e7b68f7ea1abd995bb514d02de5ff4","source":{"kind":"arxiv","id":"2503.21807","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.21807","created_at":"2026-07-05T10:40:42Z"},{"alias_kind":"arxiv_version","alias_value":"2503.21807v1","created_at":"2026-07-05T10:40:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.21807","created_at":"2026-07-05T10:40:42Z"},{"alias_kind":"pith_short_12","alias_value":"S6ICTCZTNGAF","created_at":"2026-07-05T10:40:42Z"},{"alias_kind":"pith_short_16","alias_value":"S6ICTCZTNGAF5JQC","created_at":"2026-07-05T10:40:42Z"},{"alias_kind":"pith_short_8","alias_value":"S6ICTCZT","created_at":"2026-07-05T10:40:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:S6ICTCZTNGAF5JQCBNJWHBCFNE","target":"record","payload":{"canonical_record":{"source":{"id":"2503.21807","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-25T06:28:42Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"8b14562c8ab967332d019635fa418df5d88298f62d073c7cf378620609e69bf1","abstract_canon_sha256":"c62bbd7b51de56d5f7470b43c001a1879d9b6eac4b5e0c62fc9ba5ed1e9eb594"},"schema_version":"1.0"},"canonical_sha256":"9790298b3369805ea6020b536384456905e7b68f7ea1abd995bb514d02de5ff4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:42.337120Z","signature_b64":"wf9Dep8z2JepIWpKLPqISTsoKxo/bIst7sf2JZMy2n5DuyOCfZ0F7+ciF32I/5xyIK4FIuURDAWcQW/DPw2LCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9790298b3369805ea6020b536384456905e7b68f7ea1abd995bb514d02de5ff4","last_reissued_at":"2026-07-05T10:40:42.336674Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:42.336674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.21807","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":"2026-07-05T10:40:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ltys3Mi+h+R4AvZ0PglfCGS2dx5hjZH/FvQ/V17UwgCSXsejgLjVPcPzURoGVYGqmtNsYd+hfKINJIgfXgaxBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T13:18:21.123401Z"},"content_sha256":"aa54e86debd1be762806d9bce651776bc269d51d9cbfd21c7dde53d5e6d3ce1c","schema_version":"1.0","event_id":"sha256:aa54e86debd1be762806d9bce651776bc269d51d9cbfd21c7dde53d5e6d3ce1c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:S6ICTCZTNGAF5JQCBNJWHBCFNE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LERO: LLM-driven Evolutionary framework with Hybrid Rewards and Enhanced Observation for Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Jianmin Li, Xiaohan Shan, Yuan Wei","submitted_at":"2025-03-25T06:28:42Z","abstract_excerpt":"Multi-agent reinforcement learning (MARL) faces two critical bottlenecks distinct from single-agent RL: credit assignment in cooperative tasks and partial observability of environmental states. We propose LERO, a framework integrating Large language models (LLMs) with evolutionary optimization to address these MARL-specific challenges. The solution centers on two LLM-generated components: a hybrid reward function that dynamically allocates individual credit through reward decomposition, and an observation enhancement function that augments partial observations with inferred environmental conte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.21807","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/2503.21807/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":"2026-07-05T10:40:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uit/L4Cpadpk5FJGYboTkw0snVNdfCuwS6E7bhpZaLXWWKr5IZjyog/R21kx7XyxsrdNI6TmI40/8Db3tBxmDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T13:18:21.123788Z"},"content_sha256":"4cb69ebf13ac434c42dce3f216e3b086588e0075c130213d426fc671a6612015","schema_version":"1.0","event_id":"sha256:4cb69ebf13ac434c42dce3f216e3b086588e0075c130213d426fc671a6612015"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S6ICTCZTNGAF5JQCBNJWHBCFNE/bundle.json","state_url":"https://pith.science/pith/S6ICTCZTNGAF5JQCBNJWHBCFNE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S6ICTCZTNGAF5JQCBNJWHBCFNE/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":"2026-07-27T13:18:21Z","links":{"resolver":"https://pith.science/pith/S6ICTCZTNGAF5JQCBNJWHBCFNE","bundle":"https://pith.science/pith/S6ICTCZTNGAF5JQCBNJWHBCFNE/bundle.json","state":"https://pith.science/pith/S6ICTCZTNGAF5JQCBNJWHBCFNE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S6ICTCZTNGAF5JQCBNJWHBCFNE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:S6ICTCZTNGAF5JQCBNJWHBCFNE","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":"c62bbd7b51de56d5f7470b43c001a1879d9b6eac4b5e0c62fc9ba5ed1e9eb594","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-25T06:28:42Z","title_canon_sha256":"8b14562c8ab967332d019635fa418df5d88298f62d073c7cf378620609e69bf1"},"schema_version":"1.0","source":{"id":"2503.21807","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.21807","created_at":"2026-07-05T10:40:42Z"},{"alias_kind":"arxiv_version","alias_value":"2503.21807v1","created_at":"2026-07-05T10:40:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.21807","created_at":"2026-07-05T10:40:42Z"},{"alias_kind":"pith_short_12","alias_value":"S6ICTCZTNGAF","created_at":"2026-07-05T10:40:42Z"},{"alias_kind":"pith_short_16","alias_value":"S6ICTCZTNGAF5JQC","created_at":"2026-07-05T10:40:42Z"},{"alias_kind":"pith_short_8","alias_value":"S6ICTCZT","created_at":"2026-07-05T10:40:42Z"}],"graph_snapshots":[{"event_id":"sha256:4cb69ebf13ac434c42dce3f216e3b086588e0075c130213d426fc671a6612015","target":"graph","created_at":"2026-07-05T10:40:42Z","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/2503.21807/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-agent reinforcement learning (MARL) faces two critical bottlenecks distinct from single-agent RL: credit assignment in cooperative tasks and partial observability of environmental states. We propose LERO, a framework integrating Large language models (LLMs) with evolutionary optimization to address these MARL-specific challenges. The solution centers on two LLM-generated components: a hybrid reward function that dynamically allocates individual credit through reward decomposition, and an observation enhancement function that augments partial observations with inferred environmental conte","authors_text":"Jianmin Li, Xiaohan Shan, Yuan Wei","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-25T06:28:42Z","title":"LERO: LLM-driven Evolutionary framework with Hybrid Rewards and Enhanced Observation for Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.21807","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:aa54e86debd1be762806d9bce651776bc269d51d9cbfd21c7dde53d5e6d3ce1c","target":"record","created_at":"2026-07-05T10:40:42Z","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":"c62bbd7b51de56d5f7470b43c001a1879d9b6eac4b5e0c62fc9ba5ed1e9eb594","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-25T06:28:42Z","title_canon_sha256":"8b14562c8ab967332d019635fa418df5d88298f62d073c7cf378620609e69bf1"},"schema_version":"1.0","source":{"id":"2503.21807","kind":"arxiv","version":1}},"canonical_sha256":"9790298b3369805ea6020b536384456905e7b68f7ea1abd995bb514d02de5ff4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9790298b3369805ea6020b536384456905e7b68f7ea1abd995bb514d02de5ff4","first_computed_at":"2026-07-05T10:40:42.336674Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:40:42.336674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wf9Dep8z2JepIWpKLPqISTsoKxo/bIst7sf2JZMy2n5DuyOCfZ0F7+ciF32I/5xyIK4FIuURDAWcQW/DPw2LCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:40:42.337120Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.21807","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa54e86debd1be762806d9bce651776bc269d51d9cbfd21c7dde53d5e6d3ce1c","sha256:4cb69ebf13ac434c42dce3f216e3b086588e0075c130213d426fc671a6612015"],"state_sha256":"f78a9dc773bbfe497247582e0573d7ab270540a97efc9c8ef627cb7bd2cc80c0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EGV8kyVzSHo+6pImLsTojqLunE4gEflfUsZhSma/mS6vJAIopi+IUE9lpns3ueb0pcp0S8ZDJ8H2kR9GaIzoAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-27T13:18:21.126337Z","bundle_sha256":"c597d7c9e5490a3cf4980afba03110f6d871f637c7dadd9232ba55e13fea1a16"}}