{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:26LJYCM6YB654LEKAV4GXA7NH2","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":"acf88f4ef6fdef2e6f20e6681c131d70425bc3af26f4d6f1b027c043d38606b0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T05:26:35Z","title_canon_sha256":"5baff2d0f8643ab8e2c222b207e04e2b26e719e35dc8da2c37dfd7b98875dca0"},"schema_version":"1.0","source":{"id":"2605.20729","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20729","created_at":"2026-05-21T01:04:51Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20729v1","created_at":"2026-05-21T01:04:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20729","created_at":"2026-05-21T01:04:51Z"},{"alias_kind":"pith_short_12","alias_value":"26LJYCM6YB65","created_at":"2026-05-21T01:04:51Z"},{"alias_kind":"pith_short_16","alias_value":"26LJYCM6YB654LEK","created_at":"2026-05-21T01:04:51Z"},{"alias_kind":"pith_short_8","alias_value":"26LJYCM6","created_at":"2026-05-21T01:04:51Z"}],"graph_snapshots":[{"event_id":"sha256:282ffade5b13abed40cdfbd223464c9b64c0002f2b73bb30145eb3c20fcfd76a","target":"graph","created_at":"2026-05-21T01:04:51Z","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/2605.20729/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Accurate evaluation of conversational retrieval is pivotal for advancing Retrieval-Augmented Generation (RAG) systems. However, existing conversational retrieval benchmarks suffer from costly, sparse human annotation or rigid, unnatural automated heuristics. To address these challenges, we introduce MTR-Suite, a unified framework for auditing, synthesizing, and benchmarking retrieval. It features: (1) MTR-Eval, an LLM-based auditor quantifying alignment gaps in previous benchmarks; (2) MTR-Pipeline, a multi-agent system using greedy traversal clustering to generate high-fidelity dialogues at 1","authors_text":"Abudukeyumu Abudula, Bei Li, Jingang Wang, Jingbo Zhu, Junhao Ruan, Kechen Jiao, Tong Xiao, Xin Chen, Xinyu Liu, Xunliang Cai, Yongjing Yin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T05:26:35Z","title":"MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20729","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:b45cbb60bf2d23e0ac0841b32850beb505e7f343ccf08e2d18887aa5fd1cb82b","target":"record","created_at":"2026-05-21T01:04:51Z","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":"acf88f4ef6fdef2e6f20e6681c131d70425bc3af26f4d6f1b027c043d38606b0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T05:26:35Z","title_canon_sha256":"5baff2d0f8643ab8e2c222b207e04e2b26e719e35dc8da2c37dfd7b98875dca0"},"schema_version":"1.0","source":{"id":"2605.20729","kind":"arxiv","version":1}},"canonical_sha256":"d7969c099ec07dde2c8a05786b83ed3e85c62ccdc5ac013f404b0136344d5110","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7969c099ec07dde2c8a05786b83ed3e85c62ccdc5ac013f404b0136344d5110","first_computed_at":"2026-05-21T01:04:51.152013Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:51.152013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GhgHtBzRZTqPUsqQrJD626hBG+k3YrsQfXviIAN34NPPNn1wDIg7KfnHQGYZwbfE6JzFcO7KhYXHZh9KlSH/Cw==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:51.152741Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20729","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b45cbb60bf2d23e0ac0841b32850beb505e7f343ccf08e2d18887aa5fd1cb82b","sha256:282ffade5b13abed40cdfbd223464c9b64c0002f2b73bb30145eb3c20fcfd76a"],"state_sha256":"4d5fb46428e8570a388f56d7f1ed51629c24ba3f4fc2d1abfd93e048c580ef64"}