{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JVV5I46QZX4DRX5M7AE6LGOQCW","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":"59d944544c50cd054ffd285f6445cc4bcab09b25a8a75918264e7e20e6562956","cross_cats_sorted":["cs.AI","cs.CL","cs.FL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-11-04T06:37:36Z","title_canon_sha256":"0f826d536b5932311ae34eb9e4dd258ad46518072aa96a7a3ff72d5906d38ef3"},"schema_version":"1.0","source":{"id":"2511.02304","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.02304","created_at":"2026-06-03T01:05:06Z"},{"alias_kind":"arxiv_version","alias_value":"2511.02304v2","created_at":"2026-06-03T01:05:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.02304","created_at":"2026-06-03T01:05:06Z"},{"alias_kind":"pith_short_12","alias_value":"JVV5I46QZX4D","created_at":"2026-06-03T01:05:06Z"},{"alias_kind":"pith_short_16","alias_value":"JVV5I46QZX4DRX5M","created_at":"2026-06-03T01:05:06Z"},{"alias_kind":"pith_short_8","alias_value":"JVV5I46Q","created_at":"2026-06-03T01:05:06Z"}],"graph_snapshots":[{"event_id":"sha256:8fb25cb8b4332977183fee07eca180cc43a23448426787e771645a5d42d0c840","target":"graph","created_at":"2026-06-03T01:05:06Z","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/2511.02304/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study learning multi-task, multi-agent policies for cooperative, temporal objectives, under centralized training, decentralized execution. In this setting, using automata to represent tasks assigned to agents enables breaking down a team-level objective into simpler, smaller sub-tasks. However, existing approaches remain sample-inefficient and are limited to the single-task case, requiring retraining policies for each new task. In this work, we present Automata-Conditioned Cooperative Multi-Agent Reinforcement Learning (ACC-MARL), a framework for learning task-conditioned, decentralized tea","authors_text":"Ameesh Shah, Beyazit Yalcinkaya, Hanna Krasowski, Marcell Vazquez-Chanlatte, Sanjit A. Seshia","cross_cats":["cs.AI","cs.CL","cs.FL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-11-04T06:37:36Z","title":"Automata-Conditioned Cooperative Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.02304","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":"sha256:34620d321082542e4d0d4cef704ed4c92bb0b08f5f4ff767a2ab84d195f25c30","target":"record","created_at":"2026-06-03T01:05:06Z","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":"59d944544c50cd054ffd285f6445cc4bcab09b25a8a75918264e7e20e6562956","cross_cats_sorted":["cs.AI","cs.CL","cs.FL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-11-04T06:37:36Z","title_canon_sha256":"0f826d536b5932311ae34eb9e4dd258ad46518072aa96a7a3ff72d5906d38ef3"},"schema_version":"1.0","source":{"id":"2511.02304","kind":"arxiv","version":2}},"canonical_sha256":"4d6bd473d0cdf838dfacf809e599d015b10ad9527b853859180ab3ea20622586","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d6bd473d0cdf838dfacf809e599d015b10ad9527b853859180ab3ea20622586","first_computed_at":"2026-06-03T01:05:06.975303Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:06.975303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DkiveO1R7LDc2PRqTkAdeBeGy/iT19cYpW5zziMkfV5nYUBErdWB109MG9OotB+JOI76itLFKqvRELad13uZDw==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:06.975822Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.02304","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34620d321082542e4d0d4cef704ed4c92bb0b08f5f4ff767a2ab84d195f25c30","sha256:8fb25cb8b4332977183fee07eca180cc43a23448426787e771645a5d42d0c840"],"state_sha256":"851606671bf09c188b9c0fea6ee495f68da1373cd130dd2b93ba2f01f1d31cf3"}