{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YWXEGX6GG76TK7D36TSACVQZON","short_pith_number":"pith:YWXEGX6G","schema_version":"1.0","canonical_sha256":"c5ae435fc637fd357c7bf4e40156197364081b822d52c395ec9ed6f9f00a03f1","source":{"kind":"arxiv","id":"2312.08468","version":1},"attestation_state":"computed","paper":{"title":"On Diagnostics for Understanding Agent Training Behaviour in Cooperative MARL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Abidine Vall, Arnu Pretorius, Omayma Mahjoub, Rihab Gorsane, Ruan de Kock, Siddarth Singh, Wiem Khlifi","submitted_at":"2023-12-13T19:10:10Z","abstract_excerpt":"Cooperative multi-agent reinforcement learning (MARL) has made substantial strides in addressing the distributed decision-making challenges. However, as multi-agent systems grow in complexity, gaining a comprehensive understanding of their behaviour becomes increasingly challenging. Conventionally, tracking team rewards over time has served as a pragmatic measure to gauge the effectiveness of agents in learning optimal policies. Nevertheless, we argue that relying solely on the empirical returns may obscure crucial insights into agent behaviour. In this paper, we explore the application of exp"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2312.08468","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-13T19:10:10Z","cross_cats_sorted":[],"title_canon_sha256":"ba0b09dd99f01bd7bb757946035675cd492e9f2353464f7b394d7eb6d263998e","abstract_canon_sha256":"fa5ff3ac062e0028c021d1feaecfc27e6702ffceb323a3ad865000d8b6c37875"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:04.943494Z","signature_b64":"pcCiat/Mqnu1+g6hgYtiNevhmwZyjOiruR0a8EhmzukC2BrXr0ax0shuZvmKYZeMCs99P0lJuyuv2z9aeQTUAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5ae435fc637fd357c7bf4e40156197364081b822d52c395ec9ed6f9f00a03f1","last_reissued_at":"2026-07-05T07:24:04.943008Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:04.943008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Diagnostics for Understanding Agent Training Behaviour in Cooperative MARL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Abidine Vall, Arnu Pretorius, Omayma Mahjoub, Rihab Gorsane, Ruan de Kock, Siddarth Singh, Wiem Khlifi","submitted_at":"2023-12-13T19:10:10Z","abstract_excerpt":"Cooperative multi-agent reinforcement learning (MARL) has made substantial strides in addressing the distributed decision-making challenges. However, as multi-agent systems grow in complexity, gaining a comprehensive understanding of their behaviour becomes increasingly challenging. Conventionally, tracking team rewards over time has served as a pragmatic measure to gauge the effectiveness of agents in learning optimal policies. Nevertheless, we argue that relying solely on the empirical returns may obscure crucial insights into agent behaviour. In this paper, we explore the application of exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08468","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/2312.08468/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2312.08468","created_at":"2026-07-05T07:24:04.943070+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.08468v1","created_at":"2026-07-05T07:24:04.943070+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08468","created_at":"2026-07-05T07:24:04.943070+00:00"},{"alias_kind":"pith_short_12","alias_value":"YWXEGX6GG76T","created_at":"2026-07-05T07:24:04.943070+00:00"},{"alias_kind":"pith_short_16","alias_value":"YWXEGX6GG76TK7D3","created_at":"2026-07-05T07:24:04.943070+00:00"},{"alias_kind":"pith_short_8","alias_value":"YWXEGX6G","created_at":"2026-07-05T07:24:04.943070+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YWXEGX6GG76TK7D36TSACVQZON","json":"https://pith.science/pith/YWXEGX6GG76TK7D36TSACVQZON.json","graph_json":"https://pith.science/api/pith-number/YWXEGX6GG76TK7D36TSACVQZON/graph.json","events_json":"https://pith.science/api/pith-number/YWXEGX6GG76TK7D36TSACVQZON/events.json","paper":"https://pith.science/paper/YWXEGX6G"},"agent_actions":{"view_html":"https://pith.science/pith/YWXEGX6GG76TK7D36TSACVQZON","download_json":"https://pith.science/pith/YWXEGX6GG76TK7D36TSACVQZON.json","view_paper":"https://pith.science/paper/YWXEGX6G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.08468&json=true","fetch_graph":"https://pith.science/api/pith-number/YWXEGX6GG76TK7D36TSACVQZON/graph.json","fetch_events":"https://pith.science/api/pith-number/YWXEGX6GG76TK7D36TSACVQZON/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YWXEGX6GG76TK7D36TSACVQZON/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YWXEGX6GG76TK7D36TSACVQZON/action/storage_attestation","attest_author":"https://pith.science/pith/YWXEGX6GG76TK7D36TSACVQZON/action/author_attestation","sign_citation":"https://pith.science/pith/YWXEGX6GG76TK7D36TSACVQZON/action/citation_signature","submit_replication":"https://pith.science/pith/YWXEGX6GG76TK7D36TSACVQZON/action/replication_record"}},"created_at":"2026-07-05T07:24:04.943070+00:00","updated_at":"2026-07-05T07:24:04.943070+00:00"}