{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JVV5I46QZX4DRX5M7AE6LGOQCW","short_pith_number":"pith:JVV5I46Q","canonical_record":{"source":{"id":"2511.02304","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-11-04T06:37:36Z","cross_cats_sorted":["cs.AI","cs.CL","cs.FL","cs.LG"],"title_canon_sha256":"0f826d536b5932311ae34eb9e4dd258ad46518072aa96a7a3ff72d5906d38ef3","abstract_canon_sha256":"59d944544c50cd054ffd285f6445cc4bcab09b25a8a75918264e7e20e6562956"},"schema_version":"1.0"},"canonical_sha256":"4d6bd473d0cdf838dfacf809e599d015b10ad9527b853859180ab3ea20622586","source":{"kind":"arxiv","id":"2511.02304","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JVV5I46QZX4DRX5M7AE6LGOQCW","target":"record","payload":{"canonical_record":{"source":{"id":"2511.02304","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-11-04T06:37:36Z","cross_cats_sorted":["cs.AI","cs.CL","cs.FL","cs.LG"],"title_canon_sha256":"0f826d536b5932311ae34eb9e4dd258ad46518072aa96a7a3ff72d5906d38ef3","abstract_canon_sha256":"59d944544c50cd054ffd285f6445cc4bcab09b25a8a75918264e7e20e6562956"},"schema_version":"1.0"},"canonical_sha256":"4d6bd473d0cdf838dfacf809e599d015b10ad9527b853859180ab3ea20622586","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:06.975822Z","signature_b64":"DkiveO1R7LDc2PRqTkAdeBeGy/iT19cYpW5zziMkfV5nYUBErdWB109MG9OotB+JOI76itLFKqvRELad13uZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d6bd473d0cdf838dfacf809e599d015b10ad9527b853859180ab3ea20622586","last_reissued_at":"2026-06-03T01:05:06.975303Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:06.975303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2511.02304","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-03T01:05:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qYFBRygGMcXenBjqJVxUy9baB5xqpO4z/gHhpReYnhUmKZISFZAQg/JXXRPOru+Fm/5DJpCoTTL1jtNJqT/wCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T00:29:23.867743Z"},"content_sha256":"34620d321082542e4d0d4cef704ed4c92bb0b08f5f4ff767a2ab84d195f25c30","schema_version":"1.0","event_id":"sha256:34620d321082542e4d0d4cef704ed4c92bb0b08f5f4ff767a2ab84d195f25c30"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JVV5I46QZX4DRX5M7AE6LGOQCW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automata-Conditioned Cooperative Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.FL","cs.LG"],"primary_cat":"cs.MA","authors_text":"Ameesh Shah, Beyazit Yalcinkaya, Hanna Krasowski, Marcell Vazquez-Chanlatte, Sanjit A. Seshia","submitted_at":"2025-11-04T06:37:36Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.02304","kind":"arxiv","version":2},"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/2511.02304/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":"2026-06-03T01:05:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BZdhzXzXsKuEXSnIsXP1jTSS5wadXusdhGOghr5T1DlCqzhw/BrxYVgTRIZQOmBJUxacpZFbYCfUonaxmWOaBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T00:29:23.868123Z"},"content_sha256":"8fb25cb8b4332977183fee07eca180cc43a23448426787e771645a5d42d0c840","schema_version":"1.0","event_id":"sha256:8fb25cb8b4332977183fee07eca180cc43a23448426787e771645a5d42d0c840"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JVV5I46QZX4DRX5M7AE6LGOQCW/bundle.json","state_url":"https://pith.science/pith/JVV5I46QZX4DRX5M7AE6LGOQCW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JVV5I46QZX4DRX5M7AE6LGOQCW/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":"2026-06-04T00:29:23Z","links":{"resolver":"https://pith.science/pith/JVV5I46QZX4DRX5M7AE6LGOQCW","bundle":"https://pith.science/pith/JVV5I46QZX4DRX5M7AE6LGOQCW/bundle.json","state":"https://pith.science/pith/JVV5I46QZX4DRX5M7AE6LGOQCW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JVV5I46QZX4DRX5M7AE6LGOQCW/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eWcWZ2jNkhjczFwvqHXc9tF4pOKYxhQ6J8SyG2VHcQfV8TKW6Z4FQZG22xmwzO3HpKqLgR8FqQWnjMDDPTA8Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T00:29:23.870190Z","bundle_sha256":"f2153a611c2fc53fbde173c3aaf86092276322c859440a0e118ab29ad028cfa9"}}