{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:W2PSSXHXNSL4VTKRJNKTY5THN6","short_pith_number":"pith:W2PSSXHX","canonical_record":{"source":{"id":"2503.02077","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-03-03T21:58:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1d73d7e7339b405b6e14fa470580167910f7a712b5a8f2cf436dbfa10580fcfe","abstract_canon_sha256":"d44237d5fae8585e1e568b828c10e510b99a229e1b65a022cc0b2976a5eec507"},"schema_version":"1.0"},"canonical_sha256":"b69f295cf76c97cacd514b553c76676f9f1a18f1af58c0d10e1c1c2499a729de","source":{"kind":"arxiv","id":"2503.02077","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.02077","created_at":"2026-07-05T11:15:19Z"},{"alias_kind":"arxiv_version","alias_value":"2503.02077v3","created_at":"2026-07-05T11:15:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02077","created_at":"2026-07-05T11:15:19Z"},{"alias_kind":"pith_short_12","alias_value":"W2PSSXHXNSL4","created_at":"2026-07-05T11:15:19Z"},{"alias_kind":"pith_short_16","alias_value":"W2PSSXHXNSL4VTKR","created_at":"2026-07-05T11:15:19Z"},{"alias_kind":"pith_short_8","alias_value":"W2PSSXHX","created_at":"2026-07-05T11:15:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:W2PSSXHXNSL4VTKRJNKTY5THN6","target":"record","payload":{"canonical_record":{"source":{"id":"2503.02077","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-03-03T21:58:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1d73d7e7339b405b6e14fa470580167910f7a712b5a8f2cf436dbfa10580fcfe","abstract_canon_sha256":"d44237d5fae8585e1e568b828c10e510b99a229e1b65a022cc0b2976a5eec507"},"schema_version":"1.0"},"canonical_sha256":"b69f295cf76c97cacd514b553c76676f9f1a18f1af58c0d10e1c1c2499a729de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:19.877948Z","signature_b64":"hRqM9iDmS4lGs+419V9rvBBapsS7UwGfDP/fljRAvORYvB0q66Nqji0Vwza3E3SjgnbFKUIoB39G5pzpke8rCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b69f295cf76c97cacd514b553c76676f9f1a18f1af58c0d10e1c1c2499a729de","last_reissued_at":"2026-07-05T11:15:19.877473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:19.877473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.02077","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:15:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V0zlvqysQrodr2bAntHI/E4xJ95pv0UeUDS3uhzOdAWfe6rqozjBdBAKfU/oWokb7x5ba6TTxnBJxBfCjE+HCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:36:07.189334Z"},"content_sha256":"1842f63cd2f0243fca99e4bac5cc592c82ea97a037693314deaef63e6d435591","schema_version":"1.0","event_id":"sha256:1842f63cd2f0243fca99e4bac5cc592c82ea97a037693314deaef63e6d435591"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:W2PSSXHXNSL4VTKRJNKTY5THN6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"M3HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.MA","authors_text":"Fei Fang, Yali Du, Zhicheng Zhang, Ziyan Wang","submitted_at":"2025-03-03T21:58:10Z","abstract_excerpt":"Designing effective reward functions in multi-agent reinforcement learning (MARL) is a significant challenge, often leading to suboptimal or misaligned behaviors in complex, coordinated environments. We introduce Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality ($\\text{M}^3\\text{HF}$), a novel framework that integrates multi-phase human feedback of mixed quality into the MARL training process. By involving humans with diverse expertise levels to provide iterative guidance, $\\text{M}^3\\text{HF}$ leverages both expert and non-expert feedback to continuously ref"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02077","kind":"arxiv","version":3},"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/2503.02077/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":"2026-07-05T11:15:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x/DVpo8emLkZUDMjISLdVCstcP/OTzu26I43HDHNHBdiGGfQhtVsFJTY81R/HJkNtemLFq5zlm7hcOw8tltMAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:36:07.190390Z"},"content_sha256":"d81de20b787bf6556915c503dddce86d5285f8a13c4e57f95c4ba89a081aa38d","schema_version":"1.0","event_id":"sha256:d81de20b787bf6556915c503dddce86d5285f8a13c4e57f95c4ba89a081aa38d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W2PSSXHXNSL4VTKRJNKTY5THN6/bundle.json","state_url":"https://pith.science/pith/W2PSSXHXNSL4VTKRJNKTY5THN6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W2PSSXHXNSL4VTKRJNKTY5THN6/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":"2026-08-07T10:36:07Z","links":{"resolver":"https://pith.science/pith/W2PSSXHXNSL4VTKRJNKTY5THN6","bundle":"https://pith.science/pith/W2PSSXHXNSL4VTKRJNKTY5THN6/bundle.json","state":"https://pith.science/pith/W2PSSXHXNSL4VTKRJNKTY5THN6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W2PSSXHXNSL4VTKRJNKTY5THN6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:W2PSSXHXNSL4VTKRJNKTY5THN6","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":"d44237d5fae8585e1e568b828c10e510b99a229e1b65a022cc0b2976a5eec507","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-03-03T21:58:10Z","title_canon_sha256":"1d73d7e7339b405b6e14fa470580167910f7a712b5a8f2cf436dbfa10580fcfe"},"schema_version":"1.0","source":{"id":"2503.02077","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.02077","created_at":"2026-07-05T11:15:19Z"},{"alias_kind":"arxiv_version","alias_value":"2503.02077v3","created_at":"2026-07-05T11:15:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02077","created_at":"2026-07-05T11:15:19Z"},{"alias_kind":"pith_short_12","alias_value":"W2PSSXHXNSL4","created_at":"2026-07-05T11:15:19Z"},{"alias_kind":"pith_short_16","alias_value":"W2PSSXHXNSL4VTKR","created_at":"2026-07-05T11:15:19Z"},{"alias_kind":"pith_short_8","alias_value":"W2PSSXHX","created_at":"2026-07-05T11:15:19Z"}],"graph_snapshots":[{"event_id":"sha256:d81de20b787bf6556915c503dddce86d5285f8a13c4e57f95c4ba89a081aa38d","target":"graph","created_at":"2026-07-05T11:15:19Z","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/2503.02077/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Designing effective reward functions in multi-agent reinforcement learning (MARL) is a significant challenge, often leading to suboptimal or misaligned behaviors in complex, coordinated environments. We introduce Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality ($\\text{M}^3\\text{HF}$), a novel framework that integrates multi-phase human feedback of mixed quality into the MARL training process. By involving humans with diverse expertise levels to provide iterative guidance, $\\text{M}^3\\text{HF}$ leverages both expert and non-expert feedback to continuously ref","authors_text":"Fei Fang, Yali Du, Zhicheng Zhang, Ziyan Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-03-03T21:58:10Z","title":"M3HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02077","kind":"arxiv","version":3},"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":"sha256:1842f63cd2f0243fca99e4bac5cc592c82ea97a037693314deaef63e6d435591","target":"record","created_at":"2026-07-05T11:15:19Z","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":"d44237d5fae8585e1e568b828c10e510b99a229e1b65a022cc0b2976a5eec507","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-03-03T21:58:10Z","title_canon_sha256":"1d73d7e7339b405b6e14fa470580167910f7a712b5a8f2cf436dbfa10580fcfe"},"schema_version":"1.0","source":{"id":"2503.02077","kind":"arxiv","version":3}},"canonical_sha256":"b69f295cf76c97cacd514b553c76676f9f1a18f1af58c0d10e1c1c2499a729de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b69f295cf76c97cacd514b553c76676f9f1a18f1af58c0d10e1c1c2499a729de","first_computed_at":"2026-07-05T11:15:19.877473Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:19.877473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hRqM9iDmS4lGs+419V9rvBBapsS7UwGfDP/fljRAvORYvB0q66Nqji0Vwza3E3SjgnbFKUIoB39G5pzpke8rCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:19.877948Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.02077","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1842f63cd2f0243fca99e4bac5cc592c82ea97a037693314deaef63e6d435591","sha256:d81de20b787bf6556915c503dddce86d5285f8a13c4e57f95c4ba89a081aa38d"],"state_sha256":"459a1686f99cc59b7a91db4035bc2e29fe5350e39daa5298e244bc9a5354ba92"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1T66IHzILEBgJ/Q5gsneuKGL6MgX0kjxWjBhpk7c5bLnLMoklhSCD+BVvfd6G1vtiz+Ygaj1fOfgwX98u4c5Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T10:36:07.196849Z","bundle_sha256":"0fa4b1c94a5b0c00a2049e141d32c37b2c5b56cedefeca91b4e04cef2302ef99"}}