{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:X46Y6ZSCF4HHQEOACYZPMREEYB","short_pith_number":"pith:X46Y6ZSC","schema_version":"1.0","canonical_sha256":"bf3d8f66422f0e7811c01632f64484c047063cc5d469af8dd4e9c97d35e7edf9","source":{"kind":"arxiv","id":"2306.11846","version":1},"attestation_state":"computed","paper":{"title":"Discovering Causality for Efficient Cooperation in Multi-Agent Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA","stat.ME"],"primary_cat":"cs.AI","authors_text":"Corentin Artaud, Rafael Pina, Varuna De Silva","submitted_at":"2023-06-20T18:56:25Z","abstract_excerpt":"In cooperative Multi-Agent Reinforcement Learning (MARL) agents are required to learn behaviours as a team to achieve a common goal. However, while learning a task, some agents may end up learning sub-optimal policies, not contributing to the objective of the team. Such agents are called lazy agents due to their non-cooperative behaviours that may arise from failing to understand whether they caused the rewards. As a consequence, we observe that the emergence of cooperative behaviours is not necessarily a byproduct of being able to solve a task as a team. In this paper, we investigate the appl"},"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":"2306.11846","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-06-20T18:56:25Z","cross_cats_sorted":["cs.LG","cs.MA","stat.ME"],"title_canon_sha256":"a496222811c400d35234ead2cd4fcabc3693f7b50f9f7822cebb21f1a26de0eb","abstract_canon_sha256":"7eb916a5340f8e4f50c43127ce26da20d0dd61b9367e4b3c616c22314787d819"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:23:07.505271Z","signature_b64":"5P3J/V5UOk2UnbKgRBLKafJI4y1VuHWcrfUDNMU7DEvYN5pt/sZ1cPBKphW6uS52jL76Dl5m7k71DNKCqCYFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf3d8f66422f0e7811c01632f64484c047063cc5d469af8dd4e9c97d35e7edf9","last_reissued_at":"2026-07-05T06:23:07.504930Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:23:07.504930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discovering Causality for Efficient Cooperation in Multi-Agent Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA","stat.ME"],"primary_cat":"cs.AI","authors_text":"Corentin Artaud, Rafael Pina, Varuna De Silva","submitted_at":"2023-06-20T18:56:25Z","abstract_excerpt":"In cooperative Multi-Agent Reinforcement Learning (MARL) agents are required to learn behaviours as a team to achieve a common goal. However, while learning a task, some agents may end up learning sub-optimal policies, not contributing to the objective of the team. Such agents are called lazy agents due to their non-cooperative behaviours that may arise from failing to understand whether they caused the rewards. As a consequence, we observe that the emergence of cooperative behaviours is not necessarily a byproduct of being able to solve a task as a team. In this paper, we investigate the appl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11846","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/2306.11846/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":"2306.11846","created_at":"2026-07-05T06:23:07.504983+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.11846v1","created_at":"2026-07-05T06:23:07.504983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11846","created_at":"2026-07-05T06:23:07.504983+00:00"},{"alias_kind":"pith_short_12","alias_value":"X46Y6ZSCF4HH","created_at":"2026-07-05T06:23:07.504983+00:00"},{"alias_kind":"pith_short_16","alias_value":"X46Y6ZSCF4HHQEOA","created_at":"2026-07-05T06:23:07.504983+00:00"},{"alias_kind":"pith_short_8","alias_value":"X46Y6ZSC","created_at":"2026-07-05T06:23:07.504983+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07398","citing_title":"G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X46Y6ZSCF4HHQEOACYZPMREEYB","json":"https://pith.science/pith/X46Y6ZSCF4HHQEOACYZPMREEYB.json","graph_json":"https://pith.science/api/pith-number/X46Y6ZSCF4HHQEOACYZPMREEYB/graph.json","events_json":"https://pith.science/api/pith-number/X46Y6ZSCF4HHQEOACYZPMREEYB/events.json","paper":"https://pith.science/paper/X46Y6ZSC"},"agent_actions":{"view_html":"https://pith.science/pith/X46Y6ZSCF4HHQEOACYZPMREEYB","download_json":"https://pith.science/pith/X46Y6ZSCF4HHQEOACYZPMREEYB.json","view_paper":"https://pith.science/paper/X46Y6ZSC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.11846&json=true","fetch_graph":"https://pith.science/api/pith-number/X46Y6ZSCF4HHQEOACYZPMREEYB/graph.json","fetch_events":"https://pith.science/api/pith-number/X46Y6ZSCF4HHQEOACYZPMREEYB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X46Y6ZSCF4HHQEOACYZPMREEYB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X46Y6ZSCF4HHQEOACYZPMREEYB/action/storage_attestation","attest_author":"https://pith.science/pith/X46Y6ZSCF4HHQEOACYZPMREEYB/action/author_attestation","sign_citation":"https://pith.science/pith/X46Y6ZSCF4HHQEOACYZPMREEYB/action/citation_signature","submit_replication":"https://pith.science/pith/X46Y6ZSCF4HHQEOACYZPMREEYB/action/replication_record"}},"created_at":"2026-07-05T06:23:07.504983+00:00","updated_at":"2026-07-05T06:23:07.504983+00:00"}