{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WBUUEF4CSA7JKTXM46DFCEIEDS","short_pith_number":"pith:WBUUEF4C","canonical_record":{"source":{"id":"2606.21085","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T04:18:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cc10293833686278dfbc78dc4a70898035fdb0e4a7d0ecf6d8006328f9d3dfb3","abstract_canon_sha256":"fd0fb2f4bba393397bbfcd0394e9ee8947eeea96a6f027a7b2e80c9f7f3eb8f7"},"schema_version":"1.0"},"canonical_sha256":"b069421782903e954eece7865111041cb74a01641c9693d1559e428a9853d68e","source":{"kind":"arxiv","id":"2606.21085","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21085","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21085v1","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21085","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"pith_short_12","alias_value":"WBUUEF4CSA7J","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"pith_short_16","alias_value":"WBUUEF4CSA7JKTXM","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"pith_short_8","alias_value":"WBUUEF4C","created_at":"2026-06-23T01:12:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WBUUEF4CSA7JKTXM46DFCEIEDS","target":"record","payload":{"canonical_record":{"source":{"id":"2606.21085","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T04:18:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cc10293833686278dfbc78dc4a70898035fdb0e4a7d0ecf6d8006328f9d3dfb3","abstract_canon_sha256":"fd0fb2f4bba393397bbfcd0394e9ee8947eeea96a6f027a7b2e80c9f7f3eb8f7"},"schema_version":"1.0"},"canonical_sha256":"b069421782903e954eece7865111041cb74a01641c9693d1559e428a9853d68e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:29.312021Z","signature_b64":"wVuQLwitZ3oXSRZ6lcmuCGgXRA+uv1gJjQlaoHRPGRiXVRllNSv9SIc0Z/x23BEonwdTaC+nkwvL9AOHrX1jBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b069421782903e954eece7865111041cb74a01641c9693d1559e428a9853d68e","last_reissued_at":"2026-06-23T01:12:29.311593Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:29.311593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.21085","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":"2026-06-23T01:12:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mAUPOfBuVeEVHqXxAtNSz9p2AhDXdzV6sW4MItAWOU4UAzk+IHvETWAZJLZaBhFdskj5U0L7OsGbjhBNk1H8BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T23:34:11.730084Z"},"content_sha256":"b177486ccc21f515442bd145711ee8504799c4bcb50744f5795e0abb3ba37d0b","schema_version":"1.0","event_id":"sha256:b177486ccc21f515442bd145711ee8504799c4bcb50744f5795e0abb3ba37d0b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WBUUEF4CSA7JKTXM46DFCEIEDS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sim2O: Efficient Offline-to-Online MARL via Joint Action Composition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bingchang Song, Yiqin Yang","submitted_at":"2026-06-19T04:18:51Z","abstract_excerpt":"Offline-to-online adaptation serves as a pivotal paradigm for mitigating the prohibitive cost of online exploration by bootstrapping reinforcement learning from offline datasets. While this paradigm has been extensively studied in single-agent settings, its extension to Multi-Agent Reinforcement Learning (MARL) remains largely unexplored, despite its critical relevance to complex coordinated decision-making. To bridge this gap, we introduce Sim2O, an elegant and minimalist framework for offline-to-online MARL. Rather than treating adaptation as a monolithic joint decision, Sim2O conceptualizes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21085","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/2606.21085/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":"2026-06-23T01:12:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l6VbSShhPt/+7miIwheKC6tB6L3RNpVYAVjg2D1NSLtSF09eCVLsb3Vq8oAWU+qqqroebiyc+jbbjRDwbiEUBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T23:34:11.730467Z"},"content_sha256":"738f5a1229a294147dc801bd209d44c2b43796033c016aea67c2b45a6df64364","schema_version":"1.0","event_id":"sha256:738f5a1229a294147dc801bd209d44c2b43796033c016aea67c2b45a6df64364"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WBUUEF4CSA7JKTXM46DFCEIEDS/bundle.json","state_url":"https://pith.science/pith/WBUUEF4CSA7JKTXM46DFCEIEDS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WBUUEF4CSA7JKTXM46DFCEIEDS/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":"2026-07-16T23:34:11Z","links":{"resolver":"https://pith.science/pith/WBUUEF4CSA7JKTXM46DFCEIEDS","bundle":"https://pith.science/pith/WBUUEF4CSA7JKTXM46DFCEIEDS/bundle.json","state":"https://pith.science/pith/WBUUEF4CSA7JKTXM46DFCEIEDS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WBUUEF4CSA7JKTXM46DFCEIEDS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WBUUEF4CSA7JKTXM46DFCEIEDS","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":"fd0fb2f4bba393397bbfcd0394e9ee8947eeea96a6f027a7b2e80c9f7f3eb8f7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T04:18:51Z","title_canon_sha256":"cc10293833686278dfbc78dc4a70898035fdb0e4a7d0ecf6d8006328f9d3dfb3"},"schema_version":"1.0","source":{"id":"2606.21085","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21085","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21085v1","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21085","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"pith_short_12","alias_value":"WBUUEF4CSA7J","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"pith_short_16","alias_value":"WBUUEF4CSA7JKTXM","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"pith_short_8","alias_value":"WBUUEF4C","created_at":"2026-06-23T01:12:29Z"}],"graph_snapshots":[{"event_id":"sha256:738f5a1229a294147dc801bd209d44c2b43796033c016aea67c2b45a6df64364","target":"graph","created_at":"2026-06-23T01:12:29Z","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/2606.21085/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline-to-online adaptation serves as a pivotal paradigm for mitigating the prohibitive cost of online exploration by bootstrapping reinforcement learning from offline datasets. While this paradigm has been extensively studied in single-agent settings, its extension to Multi-Agent Reinforcement Learning (MARL) remains largely unexplored, despite its critical relevance to complex coordinated decision-making. To bridge this gap, we introduce Sim2O, an elegant and minimalist framework for offline-to-online MARL. Rather than treating adaptation as a monolithic joint decision, Sim2O conceptualizes","authors_text":"Bingchang Song, Yiqin Yang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T04:18:51Z","title":"Sim2O: Efficient Offline-to-Online MARL via Joint Action Composition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21085","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:b177486ccc21f515442bd145711ee8504799c4bcb50744f5795e0abb3ba37d0b","target":"record","created_at":"2026-06-23T01:12:29Z","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":"fd0fb2f4bba393397bbfcd0394e9ee8947eeea96a6f027a7b2e80c9f7f3eb8f7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T04:18:51Z","title_canon_sha256":"cc10293833686278dfbc78dc4a70898035fdb0e4a7d0ecf6d8006328f9d3dfb3"},"schema_version":"1.0","source":{"id":"2606.21085","kind":"arxiv","version":1}},"canonical_sha256":"b069421782903e954eece7865111041cb74a01641c9693d1559e428a9853d68e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b069421782903e954eece7865111041cb74a01641c9693d1559e428a9853d68e","first_computed_at":"2026-06-23T01:12:29.311593Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:12:29.311593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wVuQLwitZ3oXSRZ6lcmuCGgXRA+uv1gJjQlaoHRPGRiXVRllNSv9SIc0Z/x23BEonwdTaC+nkwvL9AOHrX1jBw==","signature_status":"signed_v1","signed_at":"2026-06-23T01:12:29.312021Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.21085","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b177486ccc21f515442bd145711ee8504799c4bcb50744f5795e0abb3ba37d0b","sha256:738f5a1229a294147dc801bd209d44c2b43796033c016aea67c2b45a6df64364"],"state_sha256":"88cb254fd711da796264287d76a9f8ee014076d3e29bf7ee7b3ae0f318208f37"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4jH76G2EgEwnrjkSHGIicnW0kyHjkMk415jMpOz59BrjM5F4l0SCPsL/zgARN73EhNPRXWoQpj/BdFv28eBqBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T23:34:11.732755Z","bundle_sha256":"5175bcb2fa03edae13371e9459fcac6cbba6a83ff3b3184f2281e7b7012b941f"}}