{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZP3SUSNYWLBLN5RQFWV4X7HZ4Q","short_pith_number":"pith:ZP3SUSNY","canonical_record":{"source":{"id":"2409.11741","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-18T06:54:36Z","cross_cats_sorted":["cs.AI","cs.HC","cs.MA"],"title_canon_sha256":"590f89ebeb63f181ed4da4530ca4a85642e377c09c2f659044f6d29f7d342693","abstract_canon_sha256":"2db59e051b2febbba57f51460a3040c30d217029c901639c79dfc253680dd96f"},"schema_version":"1.0"},"canonical_sha256":"cbf72a49b8b2c2b6f6302dabcbfcf9e438f0b36832e0d8456d9ac5a65321d23b","source":{"kind":"arxiv","id":"2409.11741","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.11741","created_at":"2026-07-05T09:08:36Z"},{"alias_kind":"arxiv_version","alias_value":"2409.11741v1","created_at":"2026-07-05T09:08:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11741","created_at":"2026-07-05T09:08:36Z"},{"alias_kind":"pith_short_12","alias_value":"ZP3SUSNYWLBL","created_at":"2026-07-05T09:08:36Z"},{"alias_kind":"pith_short_16","alias_value":"ZP3SUSNYWLBLN5RQ","created_at":"2026-07-05T09:08:36Z"},{"alias_kind":"pith_short_8","alias_value":"ZP3SUSNY","created_at":"2026-07-05T09:08:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZP3SUSNYWLBLN5RQFWV4X7HZ4Q","target":"record","payload":{"canonical_record":{"source":{"id":"2409.11741","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-18T06:54:36Z","cross_cats_sorted":["cs.AI","cs.HC","cs.MA"],"title_canon_sha256":"590f89ebeb63f181ed4da4530ca4a85642e377c09c2f659044f6d29f7d342693","abstract_canon_sha256":"2db59e051b2febbba57f51460a3040c30d217029c901639c79dfc253680dd96f"},"schema_version":"1.0"},"canonical_sha256":"cbf72a49b8b2c2b6f6302dabcbfcf9e438f0b36832e0d8456d9ac5a65321d23b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:36.911608Z","signature_b64":"RzC9tz3g82fpIfr8zKh6o78pavNmq2tReHru6ETx7NSj9kJkfErbNs2u6xiio40coJsIEAPplgPWSvpkRN8oDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbf72a49b8b2c2b6f6302dabcbfcf9e438f0b36832e0d8456d9ac5a65321d23b","last_reissued_at":"2026-07-05T09:08:36.911137Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:36.911137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.11741","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":"2026-07-05T09:08:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9do491SmalvwxDB11dv9wy+8AVKwlTfVTzIGavV6EWBnW6euT73RSvBQf1FJOXflg5hvWthWKdxYLwvUghu0AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T10:53:46.940858Z"},"content_sha256":"f3c57b5425cd047fd6084b76e76def2e91fe1a3a501fdb7e9a9d9ceee978b04f","schema_version":"1.0","event_id":"sha256:f3c57b5425cd047fd6084b76e76def2e91fe1a3a501fdb7e9a9d9ceee978b04f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZP3SUSNYWLBLN5RQFWV4X7HZ4Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HARP: Human-Assisted Regrouping with Permutation Invariant Critic for Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.MA"],"primary_cat":"cs.LG","authors_text":"Chenxi Yue, Enze Shi, Huawen Hu, Shuocun Yang, Shu Zhang, Tianming Liu, Tianyang Zhong, Tuo Zhang, Yiwei Li, Zihao Wu","submitted_at":"2024-09-18T06:54:36Z","abstract_excerpt":"Human-in-the-loop reinforcement learning integrates human expertise to accelerate agent learning and provide critical guidance and feedback in complex fields. However, many existing approaches focus on single-agent tasks and require continuous human involvement during the training process, significantly increasing the human workload and limiting scalability. In this paper, we propose HARP (Human-Assisted Regrouping with Permutation Invariant Critic), a multi-agent reinforcement learning framework designed for group-oriented tasks. HARP integrates automatic agent regrouping with strategic human"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11741","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/2409.11741/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":"2026-07-05T09:08:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZZcLAjq6fB2PWrk5i6KQwMvttWKdL84T3pFHTJEy2q/OBHYkuLwQGyPcBEYhwH6GSoQ3GoQktNunse2AZvrWAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T10:53:46.941354Z"},"content_sha256":"df02b1e0190b4a076a751fb2d6670c4786d83d2bb899ab4380f2e8f1fc387bf9","schema_version":"1.0","event_id":"sha256:df02b1e0190b4a076a751fb2d6670c4786d83d2bb899ab4380f2e8f1fc387bf9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZP3SUSNYWLBLN5RQFWV4X7HZ4Q/bundle.json","state_url":"https://pith.science/pith/ZP3SUSNYWLBLN5RQFWV4X7HZ4Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZP3SUSNYWLBLN5RQFWV4X7HZ4Q/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":"2026-08-23T10:53:46Z","links":{"resolver":"https://pith.science/pith/ZP3SUSNYWLBLN5RQFWV4X7HZ4Q","bundle":"https://pith.science/pith/ZP3SUSNYWLBLN5RQFWV4X7HZ4Q/bundle.json","state":"https://pith.science/pith/ZP3SUSNYWLBLN5RQFWV4X7HZ4Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZP3SUSNYWLBLN5RQFWV4X7HZ4Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZP3SUSNYWLBLN5RQFWV4X7HZ4Q","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":"2db59e051b2febbba57f51460a3040c30d217029c901639c79dfc253680dd96f","cross_cats_sorted":["cs.AI","cs.HC","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-18T06:54:36Z","title_canon_sha256":"590f89ebeb63f181ed4da4530ca4a85642e377c09c2f659044f6d29f7d342693"},"schema_version":"1.0","source":{"id":"2409.11741","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.11741","created_at":"2026-07-05T09:08:36Z"},{"alias_kind":"arxiv_version","alias_value":"2409.11741v1","created_at":"2026-07-05T09:08:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11741","created_at":"2026-07-05T09:08:36Z"},{"alias_kind":"pith_short_12","alias_value":"ZP3SUSNYWLBL","created_at":"2026-07-05T09:08:36Z"},{"alias_kind":"pith_short_16","alias_value":"ZP3SUSNYWLBLN5RQ","created_at":"2026-07-05T09:08:36Z"},{"alias_kind":"pith_short_8","alias_value":"ZP3SUSNY","created_at":"2026-07-05T09:08:36Z"}],"graph_snapshots":[{"event_id":"sha256:df02b1e0190b4a076a751fb2d6670c4786d83d2bb899ab4380f2e8f1fc387bf9","target":"graph","created_at":"2026-07-05T09:08:36Z","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/2409.11741/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human-in-the-loop reinforcement learning integrates human expertise to accelerate agent learning and provide critical guidance and feedback in complex fields. However, many existing approaches focus on single-agent tasks and require continuous human involvement during the training process, significantly increasing the human workload and limiting scalability. In this paper, we propose HARP (Human-Assisted Regrouping with Permutation Invariant Critic), a multi-agent reinforcement learning framework designed for group-oriented tasks. HARP integrates automatic agent regrouping with strategic human","authors_text":"Chenxi Yue, Enze Shi, Huawen Hu, Shuocun Yang, Shu Zhang, Tianming Liu, Tianyang Zhong, Tuo Zhang, Yiwei Li, Zihao Wu","cross_cats":["cs.AI","cs.HC","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-18T06:54:36Z","title":"HARP: Human-Assisted Regrouping with Permutation Invariant Critic for Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11741","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:f3c57b5425cd047fd6084b76e76def2e91fe1a3a501fdb7e9a9d9ceee978b04f","target":"record","created_at":"2026-07-05T09:08:36Z","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":"2db59e051b2febbba57f51460a3040c30d217029c901639c79dfc253680dd96f","cross_cats_sorted":["cs.AI","cs.HC","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-18T06:54:36Z","title_canon_sha256":"590f89ebeb63f181ed4da4530ca4a85642e377c09c2f659044f6d29f7d342693"},"schema_version":"1.0","source":{"id":"2409.11741","kind":"arxiv","version":1}},"canonical_sha256":"cbf72a49b8b2c2b6f6302dabcbfcf9e438f0b36832e0d8456d9ac5a65321d23b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cbf72a49b8b2c2b6f6302dabcbfcf9e438f0b36832e0d8456d9ac5a65321d23b","first_computed_at":"2026-07-05T09:08:36.911137Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:08:36.911137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RzC9tz3g82fpIfr8zKh6o78pavNmq2tReHru6ETx7NSj9kJkfErbNs2u6xiio40coJsIEAPplgPWSvpkRN8oDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:08:36.911608Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.11741","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3c57b5425cd047fd6084b76e76def2e91fe1a3a501fdb7e9a9d9ceee978b04f","sha256:df02b1e0190b4a076a751fb2d6670c4786d83d2bb899ab4380f2e8f1fc387bf9"],"state_sha256":"086c98f7f102086d3302c870748267d2174e95844a492fe0ac9d75d846c4c818"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k/wy7DoxUFy7FAgDchilnBgd4oxKxVwayCwNoSNUXzw440nGYRH2gtVZFRySt7vFoYiPbc3ye3xlSKdeTyRZAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T10:53:46.945778Z","bundle_sha256":"9ffd28e8bd9d35a5740e5cb7e7e69d9c493ae9d7579f09fee7043441b6cf1575"}}