{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JKVHLQFT3VDZWDNFANRSFRIVJW","short_pith_number":"pith:JKVHLQFT","canonical_record":{"source":{"id":"2509.26383","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-30T15:14:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0d185836e147897652eb84614d8c2b0b83b8195eeb2dd06db6150dfc9d17b5ba","abstract_canon_sha256":"207c499e1fc43db6f3ab25fdb41882540cc723f6c4788a3f5fcfe1d7d106c78e"},"schema_version":"1.0"},"canonical_sha256":"4aaa75c0b3dd479b0da5036322c5154d965e8f6894b3c24f4204210b5c67a99c","source":{"kind":"arxiv","id":"2509.26383","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.26383","created_at":"2026-05-25T02:01:07Z"},{"alias_kind":"arxiv_version","alias_value":"2509.26383v5","created_at":"2026-05-25T02:01:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.26383","created_at":"2026-05-25T02:01:07Z"},{"alias_kind":"pith_short_12","alias_value":"JKVHLQFT3VDZ","created_at":"2026-05-25T02:01:07Z"},{"alias_kind":"pith_short_16","alias_value":"JKVHLQFT3VDZWDNF","created_at":"2026-05-25T02:01:07Z"},{"alias_kind":"pith_short_8","alias_value":"JKVHLQFT","created_at":"2026-05-25T02:01:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JKVHLQFT3VDZWDNFANRSFRIVJW","target":"record","payload":{"canonical_record":{"source":{"id":"2509.26383","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-30T15:14:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0d185836e147897652eb84614d8c2b0b83b8195eeb2dd06db6150dfc9d17b5ba","abstract_canon_sha256":"207c499e1fc43db6f3ab25fdb41882540cc723f6c4788a3f5fcfe1d7d106c78e"},"schema_version":"1.0"},"canonical_sha256":"4aaa75c0b3dd479b0da5036322c5154d965e8f6894b3c24f4204210b5c67a99c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:07.568824Z","signature_b64":"UpBOsVyLH9UvgvO4338iGxCITRezeK7bT1FpF0yrTVg/ZxYIpBDOdQMAC2IZYz17/IjSStJihB+7Va5un41TAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4aaa75c0b3dd479b0da5036322c5154d965e8f6894b3c24f4204210b5c67a99c","last_reissued_at":"2026-05-25T02:01:07.568013Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:07.568013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.26383","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-25T02:01:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VS7otCm4eoSyuYgFETf6PX9LGV1giSOcdvR6YHwuuM71bmLbCGP/6WqeSi3kxwJoPeusynPvkCOZIL1BWi5KAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T09:09:35.788847Z"},"content_sha256":"6da240cdd4a09d193e5b4f9cc2d20d2baf92e7ba9cf3b382b90c5930403c4e1e","schema_version":"1.0","event_id":"sha256:6da240cdd4a09d193e5b4f9cc2d20d2baf92e7ba9cf3b382b90c5930403c4e1e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JKVHLQFT3VDZWDNFANRSFRIVJW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jinyeop Song, Julian Shun, Junhong Lin, Shicheng Liu, Song Wang, Yada Zhu","submitted_at":"2025-09-30T15:14:24Z","abstract_excerpt":"Knowledge-graph retrieval-augmented generation (KG-RAG) couples large language models (LLMs) with structured, verifiable knowledge graphs (KGs) to reduce hallucination and provide reasoning traces. However, current KG-RAG systems often rely on fixed pipelines of multiple LLM modules (e.g., planning, reasoning, and responding), which inflate inference costs and tie performance to specific graph schemas. To address this, we introduce KG-R1, an agentic framework that optimizes KG-RAG through reinforcement learning (RL). Unlike modular workflows, KG-R1 uses a single agent that interacts with KGs a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.26383","kind":"arxiv","version":5},"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/2509.26383/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":"2026-05-25T02:01:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YMk6bFqTRWX7t9vAis3SzQuJqBy7bv5mK1/8kGWCcRW0Ze2MqBwv6ntSKdExZ+E3eGvAzc0sk3ctFXxCee4uBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T09:09:35.789566Z"},"content_sha256":"77f4ae20eea8a050741a1741601111f10a8a2fe4f022c3f9dcd7fa63eec0c218","schema_version":"1.0","event_id":"sha256:77f4ae20eea8a050741a1741601111f10a8a2fe4f022c3f9dcd7fa63eec0c218"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JKVHLQFT3VDZWDNFANRSFRIVJW/bundle.json","state_url":"https://pith.science/pith/JKVHLQFT3VDZWDNFANRSFRIVJW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JKVHLQFT3VDZWDNFANRSFRIVJW/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":"2026-05-27T09:09:35Z","links":{"resolver":"https://pith.science/pith/JKVHLQFT3VDZWDNFANRSFRIVJW","bundle":"https://pith.science/pith/JKVHLQFT3VDZWDNFANRSFRIVJW/bundle.json","state":"https://pith.science/pith/JKVHLQFT3VDZWDNFANRSFRIVJW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JKVHLQFT3VDZWDNFANRSFRIVJW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JKVHLQFT3VDZWDNFANRSFRIVJW","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":"207c499e1fc43db6f3ab25fdb41882540cc723f6c4788a3f5fcfe1d7d106c78e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-30T15:14:24Z","title_canon_sha256":"0d185836e147897652eb84614d8c2b0b83b8195eeb2dd06db6150dfc9d17b5ba"},"schema_version":"1.0","source":{"id":"2509.26383","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.26383","created_at":"2026-05-25T02:01:07Z"},{"alias_kind":"arxiv_version","alias_value":"2509.26383v5","created_at":"2026-05-25T02:01:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.26383","created_at":"2026-05-25T02:01:07Z"},{"alias_kind":"pith_short_12","alias_value":"JKVHLQFT3VDZ","created_at":"2026-05-25T02:01:07Z"},{"alias_kind":"pith_short_16","alias_value":"JKVHLQFT3VDZWDNF","created_at":"2026-05-25T02:01:07Z"},{"alias_kind":"pith_short_8","alias_value":"JKVHLQFT","created_at":"2026-05-25T02:01:07Z"}],"graph_snapshots":[{"event_id":"sha256:77f4ae20eea8a050741a1741601111f10a8a2fe4f022c3f9dcd7fa63eec0c218","target":"graph","created_at":"2026-05-25T02:01:07Z","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/2509.26383/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Knowledge-graph retrieval-augmented generation (KG-RAG) couples large language models (LLMs) with structured, verifiable knowledge graphs (KGs) to reduce hallucination and provide reasoning traces. However, current KG-RAG systems often rely on fixed pipelines of multiple LLM modules (e.g., planning, reasoning, and responding), which inflate inference costs and tie performance to specific graph schemas. To address this, we introduce KG-R1, an agentic framework that optimizes KG-RAG through reinforcement learning (RL). Unlike modular workflows, KG-R1 uses a single agent that interacts with KGs a","authors_text":"Jinyeop Song, Julian Shun, Junhong Lin, Shicheng Liu, Song Wang, Yada Zhu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-30T15:14:24Z","title":"Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.26383","kind":"arxiv","version":5},"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":"sha256:6da240cdd4a09d193e5b4f9cc2d20d2baf92e7ba9cf3b382b90c5930403c4e1e","target":"record","created_at":"2026-05-25T02:01:07Z","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":"207c499e1fc43db6f3ab25fdb41882540cc723f6c4788a3f5fcfe1d7d106c78e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-30T15:14:24Z","title_canon_sha256":"0d185836e147897652eb84614d8c2b0b83b8195eeb2dd06db6150dfc9d17b5ba"},"schema_version":"1.0","source":{"id":"2509.26383","kind":"arxiv","version":5}},"canonical_sha256":"4aaa75c0b3dd479b0da5036322c5154d965e8f6894b3c24f4204210b5c67a99c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4aaa75c0b3dd479b0da5036322c5154d965e8f6894b3c24f4204210b5c67a99c","first_computed_at":"2026-05-25T02:01:07.568013Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:07.568013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UpBOsVyLH9UvgvO4338iGxCITRezeK7bT1FpF0yrTVg/ZxYIpBDOdQMAC2IZYz17/IjSStJihB+7Va5un41TAQ==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:07.568824Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.26383","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6da240cdd4a09d193e5b4f9cc2d20d2baf92e7ba9cf3b382b90c5930403c4e1e","sha256:77f4ae20eea8a050741a1741601111f10a8a2fe4f022c3f9dcd7fa63eec0c218"],"state_sha256":"8744c8d7bd0719834c426aeaf852483cecc0800c0203f211501a10917b7e9def"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HlqCFj5/HFgbiLN5WaqbAcYkW9fRyGT+jeIWDj5mP8/4QOcI1NVn59sLx0NYsnJI7rXnBre5/K4K+mSSUYGNBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T09:09:35.792995Z","bundle_sha256":"59ccaf31e42458f829ba7cd0dc9e22681925b818a44475ba7863d244edf09c0e"}}