{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EQIHOD3X5UJ5LL6VGI6NFJUPPW","short_pith_number":"pith:EQIHOD3X","schema_version":"1.0","canonical_sha256":"2410770f77ed13d5afd5323cd2a68f7db3ac1ba82cb1ec9b6eaf3c5e473d1c3d","source":{"kind":"arxiv","id":"2602.19127","version":2},"attestation_state":"computed","paper":{"title":"AgenticRAGTracer: A Hop-Aware Benchmark for Diagnosing Multi-Step Retrieval Reasoning in Agentic RAG","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Qijie You, Wenkai Yu, Wentao Zhang","submitted_at":"2026-02-22T10:55:21Z","abstract_excerpt":"With the rapid advancement of agent-based methods in recent years, Agentic RAG has undoubtedly become an important research direction. Multi-hop reasoning, which requires models to engage in deliberate thinking and multi-step interaction, serves as a critical testbed for assessing such capabilities. However, existing benchmarks typically provide only final questions and answers, while lacking the intermediate hop-level questions that gradually connect atomic questions to the final multi-hop query. This limitation prevents researchers from analyzing at which step an agent fails and restricts mo"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2602.19127","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-22T10:55:21Z","cross_cats_sorted":[],"title_canon_sha256":"3c5ff9982830f31bba0f902ff6a7b61bf3cf2936035f767de5b852d599d36fe2","abstract_canon_sha256":"e73b7e1a1813d7e85575426d63f88c0ebf35674918ca0e2f76db1b32f606a985"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:17.854959Z","signature_b64":"4oY/orWDdHq0yQouz+biKl+jlbi7Ok3nircKPT99klFoWcfGQzoUyAOC6fC/m4xrOUatnhiTjOEvsB2zktRCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2410770f77ed13d5afd5323cd2a68f7db3ac1ba82cb1ec9b6eaf3c5e473d1c3d","last_reissued_at":"2026-07-03T01:17:17.854435Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:17.854435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AgenticRAGTracer: A Hop-Aware Benchmark for Diagnosing Multi-Step Retrieval Reasoning in Agentic RAG","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Qijie You, Wenkai Yu, Wentao Zhang","submitted_at":"2026-02-22T10:55:21Z","abstract_excerpt":"With the rapid advancement of agent-based methods in recent years, Agentic RAG has undoubtedly become an important research direction. Multi-hop reasoning, which requires models to engage in deliberate thinking and multi-step interaction, serves as a critical testbed for assessing such capabilities. However, existing benchmarks typically provide only final questions and answers, while lacking the intermediate hop-level questions that gradually connect atomic questions to the final multi-hop query. This limitation prevents researchers from analyzing at which step an agent fails and restricts mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.19127","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/2602.19127/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2602.19127","created_at":"2026-07-03T01:17:17.854492+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.19127v2","created_at":"2026-07-03T01:17:17.854492+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.19127","created_at":"2026-07-03T01:17:17.854492+00:00"},{"alias_kind":"pith_short_12","alias_value":"EQIHOD3X5UJ5","created_at":"2026-07-03T01:17:17.854492+00:00"},{"alias_kind":"pith_short_16","alias_value":"EQIHOD3X5UJ5LL6V","created_at":"2026-07-03T01:17:17.854492+00:00"},{"alias_kind":"pith_short_8","alias_value":"EQIHOD3X","created_at":"2026-07-03T01:17:17.854492+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.31238","citing_title":"Scaling Multi-Hop Training Data via Graph-Constrained Path Selection","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EQIHOD3X5UJ5LL6VGI6NFJUPPW","json":"https://pith.science/pith/EQIHOD3X5UJ5LL6VGI6NFJUPPW.json","graph_json":"https://pith.science/api/pith-number/EQIHOD3X5UJ5LL6VGI6NFJUPPW/graph.json","events_json":"https://pith.science/api/pith-number/EQIHOD3X5UJ5LL6VGI6NFJUPPW/events.json","paper":"https://pith.science/paper/EQIHOD3X"},"agent_actions":{"view_html":"https://pith.science/pith/EQIHOD3X5UJ5LL6VGI6NFJUPPW","download_json":"https://pith.science/pith/EQIHOD3X5UJ5LL6VGI6NFJUPPW.json","view_paper":"https://pith.science/paper/EQIHOD3X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.19127&json=true","fetch_graph":"https://pith.science/api/pith-number/EQIHOD3X5UJ5LL6VGI6NFJUPPW/graph.json","fetch_events":"https://pith.science/api/pith-number/EQIHOD3X5UJ5LL6VGI6NFJUPPW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EQIHOD3X5UJ5LL6VGI6NFJUPPW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EQIHOD3X5UJ5LL6VGI6NFJUPPW/action/storage_attestation","attest_author":"https://pith.science/pith/EQIHOD3X5UJ5LL6VGI6NFJUPPW/action/author_attestation","sign_citation":"https://pith.science/pith/EQIHOD3X5UJ5LL6VGI6NFJUPPW/action/citation_signature","submit_replication":"https://pith.science/pith/EQIHOD3X5UJ5LL6VGI6NFJUPPW/action/replication_record"}},"created_at":"2026-07-03T01:17:17.854492+00:00","updated_at":"2026-07-03T01:17:17.854492+00:00"}