{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JJ4QLU5YY6T2AWPCEHW4WVO6NQ","short_pith_number":"pith:JJ4QLU5Y","canonical_record":{"source":{"id":"2606.05002","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T15:19:55Z","cross_cats_sorted":[],"title_canon_sha256":"9f0036cfdf56e983787f8c4be278fc888e1381d0a774838dfb039d62039272ac","abstract_canon_sha256":"fe4c0280d5a257450c2e19144519f75a4be9ebb9420fce89bd8d991bc05d7103"},"schema_version":"1.0"},"canonical_sha256":"4a7905d3b8c7a7a059e221edcb55de6c09c8d0f53264255b631d31ee78ea9ccd","source":{"kind":"arxiv","id":"2606.05002","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05002","created_at":"2026-06-04T01:10:00Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05002v1","created_at":"2026-06-04T01:10:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05002","created_at":"2026-06-04T01:10:00Z"},{"alias_kind":"pith_short_12","alias_value":"JJ4QLU5YY6T2","created_at":"2026-06-04T01:10:00Z"},{"alias_kind":"pith_short_16","alias_value":"JJ4QLU5YY6T2AWPC","created_at":"2026-06-04T01:10:00Z"},{"alias_kind":"pith_short_8","alias_value":"JJ4QLU5Y","created_at":"2026-06-04T01:10:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JJ4QLU5YY6T2AWPCEHW4WVO6NQ","target":"record","payload":{"canonical_record":{"source":{"id":"2606.05002","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T15:19:55Z","cross_cats_sorted":[],"title_canon_sha256":"9f0036cfdf56e983787f8c4be278fc888e1381d0a774838dfb039d62039272ac","abstract_canon_sha256":"fe4c0280d5a257450c2e19144519f75a4be9ebb9420fce89bd8d991bc05d7103"},"schema_version":"1.0"},"canonical_sha256":"4a7905d3b8c7a7a059e221edcb55de6c09c8d0f53264255b631d31ee78ea9ccd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:10:00.995129Z","signature_b64":"wRABr1e2GpvnoWPC0lIgkadseJiGp2wZI5bglhbTK6AbIqIAj5sZZp6i/Fpuwa/ejG7/8aXTTt1+oOGBDDSfBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a7905d3b8c7a7a059e221edcb55de6c09c8d0f53264255b631d31ee78ea9ccd","last_reissued_at":"2026-06-04T01:10:00.994332Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:10:00.994332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.05002","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":"2026-06-04T01:10:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UafLK/JqfwfUhyjJoHWmWIOY0KAF9EtcTqEzB+IOqkFSsiR4gDTiwn0kdSF9hjH7IZbvHU7R1oYK4H3AgvWWCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T02:42:05.260868Z"},"content_sha256":"00dea8f3a44758064adc6fbb7907cd5d75a065fea8448092bade89d73e438e62","schema_version":"1.0","event_id":"sha256:00dea8f3a44758064adc6fbb7907cd5d75a065fea8448092bade89d73e438e62"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JJ4QLU5YY6T2AWPCEHW4WVO6NQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GARL: Game-Theoretic Reinforcement Learning for Multi-Agent Strategic Prioritisation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huiyuan Xie, Yiwen Zhang, Yuqin Huang, Yuxiao Ye, Zhiyuan Liu","submitted_at":"2026-06-03T15:19:55Z","abstract_excerpt":"LLM-based multi-agent systems are increasingly used for strategic decision-making tasks. In such settings, performance depends not only on individual model capabilities, but also on the policies by which agents interact and adapt. Multi-agent reinforcement learning can optimise these interaction policies, but its reward design often remains task-specific and weakly grounded in interaction structure. To address this gap, we propose GARL, a GAme-theoretic Reinforcement Learning framework for multi-agent strategic prioritisation. GARL formalises strategic prioritisation as a two-stage game: compe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05002","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/2606.05002/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":"2026-06-04T01:10:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EIb7M+Wq5qy/jg39KJjhNz6ZZ6yCD7LxWPX5X1j1a/IhR+WbY2a2Kcro4mZdiuwJFsK3kocbw24nVsXLgyu8BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T02:42:05.261238Z"},"content_sha256":"ed43cc23116fd49741e4a17670ce635668b9fd410379b545a9db7c0baf82d42a","schema_version":"1.0","event_id":"sha256:ed43cc23116fd49741e4a17670ce635668b9fd410379b545a9db7c0baf82d42a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JJ4QLU5YY6T2AWPCEHW4WVO6NQ/bundle.json","state_url":"https://pith.science/pith/JJ4QLU5YY6T2AWPCEHW4WVO6NQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JJ4QLU5YY6T2AWPCEHW4WVO6NQ/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":"2026-06-05T02:42:05Z","links":{"resolver":"https://pith.science/pith/JJ4QLU5YY6T2AWPCEHW4WVO6NQ","bundle":"https://pith.science/pith/JJ4QLU5YY6T2AWPCEHW4WVO6NQ/bundle.json","state":"https://pith.science/pith/JJ4QLU5YY6T2AWPCEHW4WVO6NQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JJ4QLU5YY6T2AWPCEHW4WVO6NQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JJ4QLU5YY6T2AWPCEHW4WVO6NQ","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":"fe4c0280d5a257450c2e19144519f75a4be9ebb9420fce89bd8d991bc05d7103","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T15:19:55Z","title_canon_sha256":"9f0036cfdf56e983787f8c4be278fc888e1381d0a774838dfb039d62039272ac"},"schema_version":"1.0","source":{"id":"2606.05002","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05002","created_at":"2026-06-04T01:10:00Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05002v1","created_at":"2026-06-04T01:10:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05002","created_at":"2026-06-04T01:10:00Z"},{"alias_kind":"pith_short_12","alias_value":"JJ4QLU5YY6T2","created_at":"2026-06-04T01:10:00Z"},{"alias_kind":"pith_short_16","alias_value":"JJ4QLU5YY6T2AWPC","created_at":"2026-06-04T01:10:00Z"},{"alias_kind":"pith_short_8","alias_value":"JJ4QLU5Y","created_at":"2026-06-04T01:10:00Z"}],"graph_snapshots":[{"event_id":"sha256:ed43cc23116fd49741e4a17670ce635668b9fd410379b545a9db7c0baf82d42a","target":"graph","created_at":"2026-06-04T01:10:00Z","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/2606.05002/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM-based multi-agent systems are increasingly used for strategic decision-making tasks. In such settings, performance depends not only on individual model capabilities, but also on the policies by which agents interact and adapt. Multi-agent reinforcement learning can optimise these interaction policies, but its reward design often remains task-specific and weakly grounded in interaction structure. To address this gap, we propose GARL, a GAme-theoretic Reinforcement Learning framework for multi-agent strategic prioritisation. GARL formalises strategic prioritisation as a two-stage game: compe","authors_text":"Huiyuan Xie, Yiwen Zhang, Yuqin Huang, Yuxiao Ye, Zhiyuan Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T15:19:55Z","title":"GARL: Game-Theoretic Reinforcement Learning for Multi-Agent Strategic Prioritisation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05002","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":"sha256:00dea8f3a44758064adc6fbb7907cd5d75a065fea8448092bade89d73e438e62","target":"record","created_at":"2026-06-04T01:10:00Z","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":"fe4c0280d5a257450c2e19144519f75a4be9ebb9420fce89bd8d991bc05d7103","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T15:19:55Z","title_canon_sha256":"9f0036cfdf56e983787f8c4be278fc888e1381d0a774838dfb039d62039272ac"},"schema_version":"1.0","source":{"id":"2606.05002","kind":"arxiv","version":1}},"canonical_sha256":"4a7905d3b8c7a7a059e221edcb55de6c09c8d0f53264255b631d31ee78ea9ccd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a7905d3b8c7a7a059e221edcb55de6c09c8d0f53264255b631d31ee78ea9ccd","first_computed_at":"2026-06-04T01:10:00.994332Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:10:00.994332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wRABr1e2GpvnoWPC0lIgkadseJiGp2wZI5bglhbTK6AbIqIAj5sZZp6i/Fpuwa/ejG7/8aXTTt1+oOGBDDSfBA==","signature_status":"signed_v1","signed_at":"2026-06-04T01:10:00.995129Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05002","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00dea8f3a44758064adc6fbb7907cd5d75a065fea8448092bade89d73e438e62","sha256:ed43cc23116fd49741e4a17670ce635668b9fd410379b545a9db7c0baf82d42a"],"state_sha256":"cc5c7d439651e465611ddd05af9496ec32931ada4521334a935880b2def6479c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MOmKN7eX7V77PVBLRngkaR92tfcU9Y6kprPyplzzEY7+zm0tvdQc+tMhkLp836Ry7BlWhXywEtiM+VgfB1LkCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T02:42:05.263379Z","bundle_sha256":"30db5d5c7bb94547bbd15c88aaf66cc91c9f7019ee668ffa63007ec5df5477c4"}}