{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BWNDAHRFM6IICG2IVCYWU2XXLA","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":"52d133a2568fdfdbea238813750530f1fd8fb38eb6b923f0d0bfedbd66f310e8","cross_cats_sorted":["cs.IT","cs.LG","cs.MA","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-21T15:35:59Z","title_canon_sha256":"b01fdfaf8a4f074ad2fde4c6c0008ec9f3c019a10f13d27d4a2d8fcb1e7ef5ab"},"schema_version":"1.0","source":{"id":"2508.15652","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.15652","created_at":"2026-07-05T11:57:59Z"},{"alias_kind":"arxiv_version","alias_value":"2508.15652v2","created_at":"2026-07-05T11:57:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.15652","created_at":"2026-07-05T11:57:59Z"},{"alias_kind":"pith_short_12","alias_value":"BWNDAHRFM6II","created_at":"2026-07-05T11:57:59Z"},{"alias_kind":"pith_short_16","alias_value":"BWNDAHRFM6IICG2I","created_at":"2026-07-05T11:57:59Z"},{"alias_kind":"pith_short_8","alias_value":"BWNDAHRF","created_at":"2026-07-05T11:57:59Z"}],"graph_snapshots":[{"event_id":"sha256:419b2430ee294fd90747a4c50ccb7d510739a9b07a062fe088419d448bc8e3c3","target":"graph","created_at":"2026-07-05T11:57:59Z","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/2508.15652/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To reliably deploy Multi-Agent Reinforcement Learning (MARL) systems, it is crucial to understand individual agent behaviors. While prior work typically evaluates overall team performance based on explicit reward signals, it is unclear how to infer agent contributions in the absence of any value feedback. In this work, we investigate whether meaningful insights into agent behaviors can be extracted solely by analyzing the policy distribution. Inspired by the phenomenon that intelligent agents tend to pursue convergent instrumental values, we introduce Intended Cooperation Values (ICVs), a meth","authors_text":"Alessandro Antonucci, Ardian Selmonaj, Miroslav Strupl, Oleg Szehr","cross_cats":["cs.IT","cs.LG","cs.MA","math.IT"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-21T15:35:59Z","title":"Understanding Action Effects through Instrumental Empowerment in Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.15652","kind":"arxiv","version":2},"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":"sha256:2b0e92ecff7fa5b057e833dd15468e537ee0f4ae9d7e3f529fc39b426d652e3a","target":"record","created_at":"2026-07-05T11:57:59Z","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":"52d133a2568fdfdbea238813750530f1fd8fb38eb6b923f0d0bfedbd66f310e8","cross_cats_sorted":["cs.IT","cs.LG","cs.MA","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-21T15:35:59Z","title_canon_sha256":"b01fdfaf8a4f074ad2fde4c6c0008ec9f3c019a10f13d27d4a2d8fcb1e7ef5ab"},"schema_version":"1.0","source":{"id":"2508.15652","kind":"arxiv","version":2}},"canonical_sha256":"0d9a301e256790811b48a8b16a6af7581fe7e9f6b9af7896b01dd580173670e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d9a301e256790811b48a8b16a6af7581fe7e9f6b9af7896b01dd580173670e0","first_computed_at":"2026-07-05T11:57:59.526512Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:57:59.526512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g5Q8WgHBeWobZvHXFrhVWNg5FESdLkNvIKR+77WWifVDOITMFDMnRvEsh3ZoeNjpo8CKiAp8fQ8y12+0osfWDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:57:59.527009Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.15652","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b0e92ecff7fa5b057e833dd15468e537ee0f4ae9d7e3f529fc39b426d652e3a","sha256:419b2430ee294fd90747a4c50ccb7d510739a9b07a062fe088419d448bc8e3c3"],"state_sha256":"d99b0802d87dd6164a5cac9122bd020f93ff8be25d63b830c201b39e4ab0dbe9"}