{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OF4HVW2CGHDKSY33OQ6NVUDCRF","short_pith_number":"pith:OF4HVW2C","canonical_record":{"source":{"id":"2505.19637","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-05-26T07:54:58Z","cross_cats_sorted":[],"title_canon_sha256":"571d5b1b3e1ce660cc75661fa57d5d4a559d44bd22f27f88bc3af7303689794f","abstract_canon_sha256":"1e7444cac7fb8b9e15d8e4b4ab97fb23b67d0ae91be1d0bcabd029093cb949a8"},"schema_version":"1.0"},"canonical_sha256":"71787adb4231c6a9637b743cdad062895c61a69aa9550c6c9aaa0e8768cb52d2","source":{"kind":"arxiv","id":"2505.19637","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19637","created_at":"2026-07-05T11:09:33Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19637v1","created_at":"2026-07-05T11:09:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19637","created_at":"2026-07-05T11:09:33Z"},{"alias_kind":"pith_short_12","alias_value":"OF4HVW2CGHDK","created_at":"2026-07-05T11:09:33Z"},{"alias_kind":"pith_short_16","alias_value":"OF4HVW2CGHDKSY33","created_at":"2026-07-05T11:09:33Z"},{"alias_kind":"pith_short_8","alias_value":"OF4HVW2C","created_at":"2026-07-05T11:09:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OF4HVW2CGHDKSY33OQ6NVUDCRF","target":"record","payload":{"canonical_record":{"source":{"id":"2505.19637","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-05-26T07:54:58Z","cross_cats_sorted":[],"title_canon_sha256":"571d5b1b3e1ce660cc75661fa57d5d4a559d44bd22f27f88bc3af7303689794f","abstract_canon_sha256":"1e7444cac7fb8b9e15d8e4b4ab97fb23b67d0ae91be1d0bcabd029093cb949a8"},"schema_version":"1.0"},"canonical_sha256":"71787adb4231c6a9637b743cdad062895c61a69aa9550c6c9aaa0e8768cb52d2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:33.850638Z","signature_b64":"TivGNBYGnsu011vfw40XVj/0mKj//zh6S+yH56pEIz0IeWSQ7lEVRMj2+PG2h2VYo7LuXHvLCupeXzg0sYgUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71787adb4231c6a9637b743cdad062895c61a69aa9550c6c9aaa0e8768cb52d2","last_reissued_at":"2026-07-05T11:09:33.850139Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:33.850139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.19637","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":"2026-07-05T11:09:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u3yDqCErSGUhZFX5/cYiG1OO3Aa5LxCY37ufnXDorT0VQQiNer4EDmdEGpWN5DzznytKVmuU5sGfCuLzuR4IAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:14:04.945418Z"},"content_sha256":"e3940dd9117567869b86e4ace286c13f1a7145612655eb66e8ae175c4d245328","schema_version":"1.0","event_id":"sha256:e3940dd9117567869b86e4ace286c13f1a7145612655eb66e8ae175c4d245328"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OF4HVW2CGHDKSY33OQ6NVUDCRF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive Episode Length Adjustment for Multi-agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Byunghyun Yoo, Euisok Chung, Hyunwoo Kim, Jeongmin Yang, Younghwan Shin","submitted_at":"2025-05-26T07:54:58Z","abstract_excerpt":"In standard reinforcement learning, an episode is defined as a sequence of interactions between agents and the environment, which terminates upon reaching a terminal state or a pre-defined episode length. Setting a shorter episode length enables the generation of multiple episodes with the same number of data samples, thereby facilitating an exploration of diverse states. While shorter episodes may limit the collection of long-term interactions, they may offer significant advantages when properly managed. For example, trajectory truncation in single-agent reinforcement learning has shown how t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19637","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/2505.19637/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":"2026-07-05T11:09:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ieTGIE3fe2+sX5U8Ml/b7JbP8cvzSl65X2S0GqGfOH/RcK8+tGmCPRKoMfI+OnXgpQYZ7CJ3zn+TmeVTxWIvCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:14:04.945904Z"},"content_sha256":"99babc0972e883987d7887adadeeb5d10c9e4724bbed7ced90f17475c75569a3","schema_version":"1.0","event_id":"sha256:99babc0972e883987d7887adadeeb5d10c9e4724bbed7ced90f17475c75569a3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OF4HVW2CGHDKSY33OQ6NVUDCRF/bundle.json","state_url":"https://pith.science/pith/OF4HVW2CGHDKSY33OQ6NVUDCRF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OF4HVW2CGHDKSY33OQ6NVUDCRF/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":"2026-08-09T01:14:04Z","links":{"resolver":"https://pith.science/pith/OF4HVW2CGHDKSY33OQ6NVUDCRF","bundle":"https://pith.science/pith/OF4HVW2CGHDKSY33OQ6NVUDCRF/bundle.json","state":"https://pith.science/pith/OF4HVW2CGHDKSY33OQ6NVUDCRF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OF4HVW2CGHDKSY33OQ6NVUDCRF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OF4HVW2CGHDKSY33OQ6NVUDCRF","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":"1e7444cac7fb8b9e15d8e4b4ab97fb23b67d0ae91be1d0bcabd029093cb949a8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-05-26T07:54:58Z","title_canon_sha256":"571d5b1b3e1ce660cc75661fa57d5d4a559d44bd22f27f88bc3af7303689794f"},"schema_version":"1.0","source":{"id":"2505.19637","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19637","created_at":"2026-07-05T11:09:33Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19637v1","created_at":"2026-07-05T11:09:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19637","created_at":"2026-07-05T11:09:33Z"},{"alias_kind":"pith_short_12","alias_value":"OF4HVW2CGHDK","created_at":"2026-07-05T11:09:33Z"},{"alias_kind":"pith_short_16","alias_value":"OF4HVW2CGHDKSY33","created_at":"2026-07-05T11:09:33Z"},{"alias_kind":"pith_short_8","alias_value":"OF4HVW2C","created_at":"2026-07-05T11:09:33Z"}],"graph_snapshots":[{"event_id":"sha256:99babc0972e883987d7887adadeeb5d10c9e4724bbed7ced90f17475c75569a3","target":"graph","created_at":"2026-07-05T11:09:33Z","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/2505.19637/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In standard reinforcement learning, an episode is defined as a sequence of interactions between agents and the environment, which terminates upon reaching a terminal state or a pre-defined episode length. Setting a shorter episode length enables the generation of multiple episodes with the same number of data samples, thereby facilitating an exploration of diverse states. While shorter episodes may limit the collection of long-term interactions, they may offer significant advantages when properly managed. For example, trajectory truncation in single-agent reinforcement learning has shown how t","authors_text":"Byunghyun Yoo, Euisok Chung, Hyunwoo Kim, Jeongmin Yang, Younghwan Shin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-05-26T07:54:58Z","title":"Adaptive Episode Length Adjustment for Multi-agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19637","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:e3940dd9117567869b86e4ace286c13f1a7145612655eb66e8ae175c4d245328","target":"record","created_at":"2026-07-05T11:09:33Z","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":"1e7444cac7fb8b9e15d8e4b4ab97fb23b67d0ae91be1d0bcabd029093cb949a8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-05-26T07:54:58Z","title_canon_sha256":"571d5b1b3e1ce660cc75661fa57d5d4a559d44bd22f27f88bc3af7303689794f"},"schema_version":"1.0","source":{"id":"2505.19637","kind":"arxiv","version":1}},"canonical_sha256":"71787adb4231c6a9637b743cdad062895c61a69aa9550c6c9aaa0e8768cb52d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71787adb4231c6a9637b743cdad062895c61a69aa9550c6c9aaa0e8768cb52d2","first_computed_at":"2026-07-05T11:09:33.850139Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:33.850139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TivGNBYGnsu011vfw40XVj/0mKj//zh6S+yH56pEIz0IeWSQ7lEVRMj2+PG2h2VYo7LuXHvLCupeXzg0sYgUAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:33.850638Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19637","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3940dd9117567869b86e4ace286c13f1a7145612655eb66e8ae175c4d245328","sha256:99babc0972e883987d7887adadeeb5d10c9e4724bbed7ced90f17475c75569a3"],"state_sha256":"9d7f1530151aab899acd14bc0bb2ccb397e7bb734bfbaf5b87903302200a121d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VoMa4TGg44j7TYA3LIkf1QriGN4UjXdIITBMXCtAZupP0hRENtWNtfbrKF8avCs2AAgE0pUDlqa1wP7gkczfDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T01:14:04.949392Z","bundle_sha256":"8d376910d2e9e743627c780778578c4ab11a4e2d34548dbf379813244bbc2f6e"}}