{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OPQDGLA54FNVYKMRJOD4AJ3TOD","short_pith_number":"pith:OPQDGLA5","canonical_record":{"source":{"id":"2501.03468","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-07T01:52:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2ac65033a53e3651bb367f2a2a7d3b45cf6b1e0dc99afd3f84b35b5fbdc3a560","abstract_canon_sha256":"a4005f0a95364b184c27bc59736b9ac08abf2a930f096693efd3a857f95ec7cc"},"schema_version":"1.0"},"canonical_sha256":"73e0332c1de15b5c29914b87c0277370fe0f1f3860f29825219eabe5358c44b6","source":{"kind":"arxiv","id":"2501.03468","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.03468","created_at":"2026-07-05T09:57:55Z"},{"alias_kind":"arxiv_version","alias_value":"2501.03468v1","created_at":"2026-07-05T09:57:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03468","created_at":"2026-07-05T09:57:55Z"},{"alias_kind":"pith_short_12","alias_value":"OPQDGLA54FNV","created_at":"2026-07-05T09:57:55Z"},{"alias_kind":"pith_short_16","alias_value":"OPQDGLA54FNVYKMR","created_at":"2026-07-05T09:57:55Z"},{"alias_kind":"pith_short_8","alias_value":"OPQDGLA5","created_at":"2026-07-05T09:57:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OPQDGLA54FNVYKMRJOD4AJ3TOD","target":"record","payload":{"canonical_record":{"source":{"id":"2501.03468","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-07T01:52:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2ac65033a53e3651bb367f2a2a7d3b45cf6b1e0dc99afd3f84b35b5fbdc3a560","abstract_canon_sha256":"a4005f0a95364b184c27bc59736b9ac08abf2a930f096693efd3a857f95ec7cc"},"schema_version":"1.0"},"canonical_sha256":"73e0332c1de15b5c29914b87c0277370fe0f1f3860f29825219eabe5358c44b6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:55.247797Z","signature_b64":"n37jBPR6+5YKoOJYs4uk61Xh7sH51ATJUbgW3S3xl6NgnXmXqr6wY4dAvcjwGCnpVuwqzwbJbJ9lqcALU/dLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73e0332c1de15b5c29914b87c0277370fe0f1f3860f29825219eabe5358c44b6","last_reissued_at":"2026-07-05T09:57:55.247285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:55.247285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.03468","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":"2026-07-05T09:57:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CtFEZeDlZBwnXAVCNASP4fh5zXsxqwFQJXI3AtW4v/uLd50nDyvZmX76n5trZk8DP4iHshh0eX+uFF4BAZJAAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T04:12:35.112924Z"},"content_sha256":"0a7005a35d29622368bd4617b0370d0ce3a031a0bb9162f14d6cb0dc257959da","schema_version":"1.0","event_id":"sha256:0a7005a35d29622368bd4617b0370d0ce3a031a0bb9162f14d6cb0dc257959da"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OPQDGLA54FNVYKMRJOD4AJ3TOD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MTRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systems","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chulaka Gunasekara, Danish Contractor, Huaiyu Zhu, Kshitij Fadnis, Lucian Popa, Marina Danilevsky, Sara Rosenthal, Vraj Shah, Yannis Katsis, Young-Suk Lee","submitted_at":"2025-01-07T01:52:56Z","abstract_excerpt":"Retrieval-augmented generation (RAG) has recently become a very popular task for Large Language Models (LLMs). Evaluating them on multi-turn RAG conversations, where the system is asked to generate a response to a question in the context of a preceding conversation is an important and often overlooked task with several additional challenges. We present MTRAG: an end-to-end human-generated multi-turn RAG benchmark that reflects several real-world properties across diverse dimensions for evaluating the full RAG pipeline. MTRAG contains 110 conversations averaging 7.7 turns each across four domai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03468","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/2501.03468/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":"2026-07-05T09:57:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"txyb9KjR+GKllm6P/xcUuBgtD5desKVfb2O5kIFMxPvR6K71VjKeLIMMUtnSYzGV3dazowlrATmyPKkITbaHDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T04:12:35.113348Z"},"content_sha256":"1270eb478ed53bc226c70f79f758b3c90268c3cb8a8f11ead8c5f0d3d1ce7a19","schema_version":"1.0","event_id":"sha256:1270eb478ed53bc226c70f79f758b3c90268c3cb8a8f11ead8c5f0d3d1ce7a19"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OPQDGLA54FNVYKMRJOD4AJ3TOD/bundle.json","state_url":"https://pith.science/pith/OPQDGLA54FNVYKMRJOD4AJ3TOD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OPQDGLA54FNVYKMRJOD4AJ3TOD/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":"2026-08-21T04:12:35Z","links":{"resolver":"https://pith.science/pith/OPQDGLA54FNVYKMRJOD4AJ3TOD","bundle":"https://pith.science/pith/OPQDGLA54FNVYKMRJOD4AJ3TOD/bundle.json","state":"https://pith.science/pith/OPQDGLA54FNVYKMRJOD4AJ3TOD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OPQDGLA54FNVYKMRJOD4AJ3TOD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OPQDGLA54FNVYKMRJOD4AJ3TOD","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":"a4005f0a95364b184c27bc59736b9ac08abf2a930f096693efd3a857f95ec7cc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-07T01:52:56Z","title_canon_sha256":"2ac65033a53e3651bb367f2a2a7d3b45cf6b1e0dc99afd3f84b35b5fbdc3a560"},"schema_version":"1.0","source":{"id":"2501.03468","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.03468","created_at":"2026-07-05T09:57:55Z"},{"alias_kind":"arxiv_version","alias_value":"2501.03468v1","created_at":"2026-07-05T09:57:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03468","created_at":"2026-07-05T09:57:55Z"},{"alias_kind":"pith_short_12","alias_value":"OPQDGLA54FNV","created_at":"2026-07-05T09:57:55Z"},{"alias_kind":"pith_short_16","alias_value":"OPQDGLA54FNVYKMR","created_at":"2026-07-05T09:57:55Z"},{"alias_kind":"pith_short_8","alias_value":"OPQDGLA5","created_at":"2026-07-05T09:57:55Z"}],"graph_snapshots":[{"event_id":"sha256:1270eb478ed53bc226c70f79f758b3c90268c3cb8a8f11ead8c5f0d3d1ce7a19","target":"graph","created_at":"2026-07-05T09:57:55Z","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/2501.03468/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-augmented generation (RAG) has recently become a very popular task for Large Language Models (LLMs). Evaluating them on multi-turn RAG conversations, where the system is asked to generate a response to a question in the context of a preceding conversation is an important and often overlooked task with several additional challenges. We present MTRAG: an end-to-end human-generated multi-turn RAG benchmark that reflects several real-world properties across diverse dimensions for evaluating the full RAG pipeline. MTRAG contains 110 conversations averaging 7.7 turns each across four domai","authors_text":"Chulaka Gunasekara, Danish Contractor, Huaiyu Zhu, Kshitij Fadnis, Lucian Popa, Marina Danilevsky, Sara Rosenthal, Vraj Shah, Yannis Katsis, Young-Suk Lee","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-07T01:52:56Z","title":"MTRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03468","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":"sha256:0a7005a35d29622368bd4617b0370d0ce3a031a0bb9162f14d6cb0dc257959da","target":"record","created_at":"2026-07-05T09:57:55Z","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":"a4005f0a95364b184c27bc59736b9ac08abf2a930f096693efd3a857f95ec7cc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-07T01:52:56Z","title_canon_sha256":"2ac65033a53e3651bb367f2a2a7d3b45cf6b1e0dc99afd3f84b35b5fbdc3a560"},"schema_version":"1.0","source":{"id":"2501.03468","kind":"arxiv","version":1}},"canonical_sha256":"73e0332c1de15b5c29914b87c0277370fe0f1f3860f29825219eabe5358c44b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73e0332c1de15b5c29914b87c0277370fe0f1f3860f29825219eabe5358c44b6","first_computed_at":"2026-07-05T09:57:55.247285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:57:55.247285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n37jBPR6+5YKoOJYs4uk61Xh7sH51ATJUbgW3S3xl6NgnXmXqr6wY4dAvcjwGCnpVuwqzwbJbJ9lqcALU/dLBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:57:55.247797Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.03468","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a7005a35d29622368bd4617b0370d0ce3a031a0bb9162f14d6cb0dc257959da","sha256:1270eb478ed53bc226c70f79f758b3c90268c3cb8a8f11ead8c5f0d3d1ce7a19"],"state_sha256":"94334a5a0e13131d9daa07607a62e0ed2c94c5e30c17b430005c43b447b91b70"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ecOrE0pFVHL1yuwBkG33zXmXXL68DVZeE3IuAWsr+Qw5L/NZdGw92fH5lKhiThgkQqBrn5Eu46VzUd3J/S7aAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T04:12:35.115644Z","bundle_sha256":"111db464495106a7b67b20b89ef101d7846d08f7896af2e42f609ada8dc15fbf"}}