{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NY6BQTSM4BPHZPY5LGLHW27DVB","short_pith_number":"pith:NY6BQTSM","canonical_record":{"source":{"id":"2510.13910","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-15T04:13:00Z","cross_cats_sorted":[],"title_canon_sha256":"bfb48cabf0281f2aa3eb5876d24e2055dde0f6d55249eb54c2a202029f701cfb","abstract_canon_sha256":"3ab4e99e17bd352cbb30a07aaf4deba49d95a4def72b46f17056a48079884cea"},"schema_version":"1.0"},"canonical_sha256":"6e3c184e4ce05e7cbf1d59967b6be3a84e88027483025c82cdf41c38124ef8e2","source":{"kind":"arxiv","id":"2510.13910","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.13910","created_at":"2026-05-22T02:04:37Z"},{"alias_kind":"arxiv_version","alias_value":"2510.13910v2","created_at":"2026-05-22T02:04:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.13910","created_at":"2026-05-22T02:04:37Z"},{"alias_kind":"pith_short_12","alias_value":"NY6BQTSM4BPH","created_at":"2026-05-22T02:04:37Z"},{"alias_kind":"pith_short_16","alias_value":"NY6BQTSM4BPHZPY5","created_at":"2026-05-22T02:04:37Z"},{"alias_kind":"pith_short_8","alias_value":"NY6BQTSM","created_at":"2026-05-22T02:04:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NY6BQTSM4BPHZPY5LGLHW27DVB","target":"record","payload":{"canonical_record":{"source":{"id":"2510.13910","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-15T04:13:00Z","cross_cats_sorted":[],"title_canon_sha256":"bfb48cabf0281f2aa3eb5876d24e2055dde0f6d55249eb54c2a202029f701cfb","abstract_canon_sha256":"3ab4e99e17bd352cbb30a07aaf4deba49d95a4def72b46f17056a48079884cea"},"schema_version":"1.0"},"canonical_sha256":"6e3c184e4ce05e7cbf1d59967b6be3a84e88027483025c82cdf41c38124ef8e2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T02:04:37.207125Z","signature_b64":"EQ+tO7deZyjKWrT4ZYHN+dwVdCNdO0KxuGy+ppzmRLM124d/UwoSZFiHsXZaMMGPULyAfrZOqaR08oZMwY1DCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e3c184e4ce05e7cbf1d59967b6be3a84e88027483025c82cdf41c38124ef8e2","last_reissued_at":"2026-05-22T02:04:37.205996Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T02:04:37.205996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.13910","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":"2026-05-22T02:04:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tMCa0ExHKfhYBR5R9ZhdtPbMwWuAIBoLLacYtDKiUkPScXCFt+oo+QtUqFVvixpUGQntiTplolf4fjTyQe/EDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T03:21:55.927574Z"},"content_sha256":"7707b18f4463b895762327437f1cc7bdaee30ed751970b0d4310faf7f0a04176","schema_version":"1.0","event_id":"sha256:7707b18f4463b895762327437f1cc7bdaee30ed751970b0d4310faf7f0a04176"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NY6BQTSM4BPHZPY5LGLHW27DVB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RAGCap-Bench: Benchmarking Capabilities of LLMs in Agentic Retrieval Augmented Generation Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Zhang, Haizhou Li, Jingru Lin, Stephen Y. Liu","submitted_at":"2025-10-15T04:13:00Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) mitigates key limitations of Large Language Models (LLMs)-such as factual errors, outdated knowledge, and hallucinations-by dynamically retrieving external information. Recent work extends this paradigm through agentic RAG systems, where LLMs act as agents to iteratively plan, retrieve, and reason over complex queries. However, these systems still struggle with challenging multi-hop questions, and their intermediate reasoning capabilities remain underexplored. To address this, we propose RAGCap-Bench, a capability-oriented benchmark for fine-grained evaluat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.13910","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/2510.13910/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":"2026-05-22T02:04:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1vBLNNfjPtXxtD5lrnnpiqdTWa2MErsA73nus1vt5bCTtjFXZ/eXf7HdYRYXSGjzPiM+IA+pXNP9s3vrbxiBDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T03:21:55.928097Z"},"content_sha256":"153022c837da45464f75dcd45a4fd34aa2ca71414e997c801fb161174771f4cd","schema_version":"1.0","event_id":"sha256:153022c837da45464f75dcd45a4fd34aa2ca71414e997c801fb161174771f4cd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NY6BQTSM4BPHZPY5LGLHW27DVB/bundle.json","state_url":"https://pith.science/pith/NY6BQTSM4BPHZPY5LGLHW27DVB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NY6BQTSM4BPHZPY5LGLHW27DVB/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":"2026-08-24T03:21:55Z","links":{"resolver":"https://pith.science/pith/NY6BQTSM4BPHZPY5LGLHW27DVB","bundle":"https://pith.science/pith/NY6BQTSM4BPHZPY5LGLHW27DVB/bundle.json","state":"https://pith.science/pith/NY6BQTSM4BPHZPY5LGLHW27DVB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NY6BQTSM4BPHZPY5LGLHW27DVB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NY6BQTSM4BPHZPY5LGLHW27DVB","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":"3ab4e99e17bd352cbb30a07aaf4deba49d95a4def72b46f17056a48079884cea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-15T04:13:00Z","title_canon_sha256":"bfb48cabf0281f2aa3eb5876d24e2055dde0f6d55249eb54c2a202029f701cfb"},"schema_version":"1.0","source":{"id":"2510.13910","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.13910","created_at":"2026-05-22T02:04:37Z"},{"alias_kind":"arxiv_version","alias_value":"2510.13910v2","created_at":"2026-05-22T02:04:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.13910","created_at":"2026-05-22T02:04:37Z"},{"alias_kind":"pith_short_12","alias_value":"NY6BQTSM4BPH","created_at":"2026-05-22T02:04:37Z"},{"alias_kind":"pith_short_16","alias_value":"NY6BQTSM4BPHZPY5","created_at":"2026-05-22T02:04:37Z"},{"alias_kind":"pith_short_8","alias_value":"NY6BQTSM","created_at":"2026-05-22T02:04:37Z"}],"graph_snapshots":[{"event_id":"sha256:153022c837da45464f75dcd45a4fd34aa2ca71414e997c801fb161174771f4cd","target":"graph","created_at":"2026-05-22T02:04:37Z","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/2510.13910/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-Augmented Generation (RAG) mitigates key limitations of Large Language Models (LLMs)-such as factual errors, outdated knowledge, and hallucinations-by dynamically retrieving external information. Recent work extends this paradigm through agentic RAG systems, where LLMs act as agents to iteratively plan, retrieve, and reason over complex queries. However, these systems still struggle with challenging multi-hop questions, and their intermediate reasoning capabilities remain underexplored. To address this, we propose RAGCap-Bench, a capability-oriented benchmark for fine-grained evaluat","authors_text":"Chen Zhang, Haizhou Li, Jingru Lin, Stephen Y. Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-15T04:13:00Z","title":"RAGCap-Bench: Benchmarking Capabilities of LLMs in Agentic Retrieval Augmented Generation Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.13910","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":"sha256:7707b18f4463b895762327437f1cc7bdaee30ed751970b0d4310faf7f0a04176","target":"record","created_at":"2026-05-22T02:04:37Z","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":"3ab4e99e17bd352cbb30a07aaf4deba49d95a4def72b46f17056a48079884cea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-15T04:13:00Z","title_canon_sha256":"bfb48cabf0281f2aa3eb5876d24e2055dde0f6d55249eb54c2a202029f701cfb"},"schema_version":"1.0","source":{"id":"2510.13910","kind":"arxiv","version":2}},"canonical_sha256":"6e3c184e4ce05e7cbf1d59967b6be3a84e88027483025c82cdf41c38124ef8e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e3c184e4ce05e7cbf1d59967b6be3a84e88027483025c82cdf41c38124ef8e2","first_computed_at":"2026-05-22T02:04:37.205996Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T02:04:37.205996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EQ+tO7deZyjKWrT4ZYHN+dwVdCNdO0KxuGy+ppzmRLM124d/UwoSZFiHsXZaMMGPULyAfrZOqaR08oZMwY1DCA==","signature_status":"signed_v1","signed_at":"2026-05-22T02:04:37.207125Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.13910","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7707b18f4463b895762327437f1cc7bdaee30ed751970b0d4310faf7f0a04176","sha256:153022c837da45464f75dcd45a4fd34aa2ca71414e997c801fb161174771f4cd"],"state_sha256":"26f0389d17b9eec755ae7dfff446d69c78ede665fc12b4e4fafc4aa2fe1cb821"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uBgL23X7D9zJXJUv07XyrGbHirH4miSDNuiPqOqL6trCEcQ1e7165OLpHC9UEGf2UIUlc+sTEL0IJnxwOOJACA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-24T03:21:55.934024Z","bundle_sha256":"49ae35b9ab71fb4e36c88bca9302f7583b618ac5344cf25844a74088a5fc46e4"}}