{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:S3IF2L46H32ZJXV2NVM22F76LZ","short_pith_number":"pith:S3IF2L46","canonical_record":{"source":{"id":"2609.04865","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-09-04T08:25:30Z","cross_cats_sorted":[],"title_canon_sha256":"8ddb2317ba73553584aca7a417620afa4dc848fa25f9ee945295959299f82fe8","abstract_canon_sha256":"cdf75bfbdab271b71a9e9d37392758fa359d0c04a72dd9338d39eafaa5898ae7"},"schema_version":"1.0"},"canonical_sha256":"96d05d2f9e3ef594deba6d59ad17fe5e79fecad7dedb65f5867b80c184933179","source":{"kind":"arxiv","id":"2609.04865","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2609.04865","created_at":"2026-09-07T01:11:14Z"},{"alias_kind":"arxiv_version","alias_value":"2609.04865v1","created_at":"2026-09-07T01:11:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2609.04865","created_at":"2026-09-07T01:11:14Z"},{"alias_kind":"pith_short_12","alias_value":"S3IF2L46H32Z","created_at":"2026-09-07T01:11:14Z"},{"alias_kind":"pith_short_16","alias_value":"S3IF2L46H32ZJXV2","created_at":"2026-09-07T01:11:14Z"},{"alias_kind":"pith_short_8","alias_value":"S3IF2L46","created_at":"2026-09-07T01:11:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:S3IF2L46H32ZJXV2NVM22F76LZ","target":"record","payload":{"canonical_record":{"source":{"id":"2609.04865","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-09-04T08:25:30Z","cross_cats_sorted":[],"title_canon_sha256":"8ddb2317ba73553584aca7a417620afa4dc848fa25f9ee945295959299f82fe8","abstract_canon_sha256":"cdf75bfbdab271b71a9e9d37392758fa359d0c04a72dd9338d39eafaa5898ae7"},"schema_version":"1.0"},"canonical_sha256":"96d05d2f9e3ef594deba6d59ad17fe5e79fecad7dedb65f5867b80c184933179","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-09-07T01:11:14.815363Z","signature_b64":"zPSUnbEfnw702dZ11YorTHlOyj+lX1D0cPio5hMGN9ogKHcg9DPJqsJik+ycrCIVkAib9WV0bLW4MLhZUKhPBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96d05d2f9e3ef594deba6d59ad17fe5e79fecad7dedb65f5867b80c184933179","last_reissued_at":"2026-09-07T01:11:14.813867Z","signature_status":"signed_v1","first_computed_at":"2026-09-07T01:11:14.813867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2609.04865","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":"2026-09-07T01:11:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AejZa531b1LGSfy+H9z6Awm0vRndGSHwzgEc2xXxmO7hkVhmJxMOeSG3KLA46B/o+E1UEIluH0luIZDWjDZNBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-11-22T02:06:07.452674Z"},"content_sha256":"ef2d5793b34aee870e79c10736969b69b07148431e33cf07affd5f098faa5a5d","schema_version":"1.0","event_id":"sha256:ef2d5793b34aee870e79c10736969b69b07148431e33cf07affd5f098faa5a5d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:S3IF2L46H32ZJXV2NVM22F76LZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CoSkill: Joint Reinforcement Learning of Reasoning and Meta-Skill Agents for Hierarchical Skill Evolution","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dongmin Li, Huimu Wang, Jinyuan Feng, Xing Chen, Yang Gao, Yiqun Chen, Zhiqiang Pu","submitted_at":"2026-09-04T08:25:30Z","abstract_excerpt":"Skill libraries improve the sample efficiency of agentic reinforcement learning (RL) by enabling large language model (LLM) agents to reuse procedural knowledge. Yet existing paradigms exhibit structural shortcomings: they either decouple skill evolution from policy optimization or instantiate meta-skills as fixed workflows. Both treat skills as passive objects to be managed, limiting the flexible evolution of skills and their co-adaptation with the reasoning agent. To address the limitations, we propose CoSkill, a unified multi-agent RL framework that recasts the static meta-skill workflow as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2609.04865","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/2609.04865/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"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":"2026-09-07T01:11:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NIYtAkW95zoPOeM1Rl9GfEO0aKMTlzaQd0HpP2wtr5iRPIlBd3idmzwvByqRwuOuHDy3B1DZ5AMhI2mSUPncBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-11-22T02:06:07.453107Z"},"content_sha256":"6a85044b61643edd54df87c37d979e97980600a3667a54fc804a7529758a3ad0","schema_version":"1.0","event_id":"sha256:6a85044b61643edd54df87c37d979e97980600a3667a54fc804a7529758a3ad0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S3IF2L46H32ZJXV2NVM22F76LZ/bundle.json","state_url":"https://pith.science/pith/S3IF2L46H32ZJXV2NVM22F76LZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S3IF2L46H32ZJXV2NVM22F76LZ/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":"2026-11-22T02:06:07Z","links":{"resolver":"https://pith.science/pith/S3IF2L46H32ZJXV2NVM22F76LZ","bundle":"https://pith.science/pith/S3IF2L46H32ZJXV2NVM22F76LZ/bundle.json","state":"https://pith.science/pith/S3IF2L46H32ZJXV2NVM22F76LZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S3IF2L46H32ZJXV2NVM22F76LZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:S3IF2L46H32ZJXV2NVM22F76LZ","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":"cdf75bfbdab271b71a9e9d37392758fa359d0c04a72dd9338d39eafaa5898ae7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-09-04T08:25:30Z","title_canon_sha256":"8ddb2317ba73553584aca7a417620afa4dc848fa25f9ee945295959299f82fe8"},"schema_version":"1.0","source":{"id":"2609.04865","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2609.04865","created_at":"2026-09-07T01:11:14Z"},{"alias_kind":"arxiv_version","alias_value":"2609.04865v1","created_at":"2026-09-07T01:11:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2609.04865","created_at":"2026-09-07T01:11:14Z"},{"alias_kind":"pith_short_12","alias_value":"S3IF2L46H32Z","created_at":"2026-09-07T01:11:14Z"},{"alias_kind":"pith_short_16","alias_value":"S3IF2L46H32ZJXV2","created_at":"2026-09-07T01:11:14Z"},{"alias_kind":"pith_short_8","alias_value":"S3IF2L46","created_at":"2026-09-07T01:11:14Z"}],"graph_snapshots":[{"event_id":"sha256:6a85044b61643edd54df87c37d979e97980600a3667a54fc804a7529758a3ad0","target":"graph","created_at":"2026-09-07T01:11:14Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2609.04865/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Skill libraries improve the sample efficiency of agentic reinforcement learning (RL) by enabling large language model (LLM) agents to reuse procedural knowledge. Yet existing paradigms exhibit structural shortcomings: they either decouple skill evolution from policy optimization or instantiate meta-skills as fixed workflows. Both treat skills as passive objects to be managed, limiting the flexible evolution of skills and their co-adaptation with the reasoning agent. To address the limitations, we propose CoSkill, a unified multi-agent RL framework that recasts the static meta-skill workflow as","authors_text":"Dongmin Li, Huimu Wang, Jinyuan Feng, Xing Chen, Yang Gao, Yiqun Chen, Zhiqiang Pu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-09-04T08:25:30Z","title":"CoSkill: Joint Reinforcement Learning of Reasoning and Meta-Skill Agents for Hierarchical Skill Evolution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2609.04865","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:ef2d5793b34aee870e79c10736969b69b07148431e33cf07affd5f098faa5a5d","target":"record","created_at":"2026-09-07T01:11:14Z","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":"cdf75bfbdab271b71a9e9d37392758fa359d0c04a72dd9338d39eafaa5898ae7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-09-04T08:25:30Z","title_canon_sha256":"8ddb2317ba73553584aca7a417620afa4dc848fa25f9ee945295959299f82fe8"},"schema_version":"1.0","source":{"id":"2609.04865","kind":"arxiv","version":1}},"canonical_sha256":"96d05d2f9e3ef594deba6d59ad17fe5e79fecad7dedb65f5867b80c184933179","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96d05d2f9e3ef594deba6d59ad17fe5e79fecad7dedb65f5867b80c184933179","first_computed_at":"2026-09-07T01:11:14.813867Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-09-07T01:11:14.813867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zPSUnbEfnw702dZ11YorTHlOyj+lX1D0cPio5hMGN9ogKHcg9DPJqsJik+ycrCIVkAib9WV0bLW4MLhZUKhPBA==","signature_status":"signed_v1","signed_at":"2026-09-07T01:11:14.815363Z","signed_message":"canonical_sha256_bytes"},"source_id":"2609.04865","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef2d5793b34aee870e79c10736969b69b07148431e33cf07affd5f098faa5a5d","sha256:6a85044b61643edd54df87c37d979e97980600a3667a54fc804a7529758a3ad0"],"state_sha256":"c763b64a1749ddead2cf2ab8b7871a1e874a50b8d786c3c44938cb8088cc4524"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5ijbxctTGsJnb9Oizqfz+6i1bnlw7z3utmphr51XUF3zuLo9mU7C4TMrGQDeDRp9JlYN3A4k6+ZSVY5iPLAQAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-11-22T02:06:07.459030Z","bundle_sha256":"9ba6521c47f0d3cd71ae188bb12fca937b3e11d61ae8918400ef8f43c3e80147"}}