{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GN4IHWQYLUK2JGLOG6XMLR43LY","short_pith_number":"pith:GN4IHWQY","canonical_record":{"source":{"id":"2501.08208","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T15:46:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2080b6f0f9bf5b834982df37122453013a9b4cd8cf6d1f25f84b7d37c95d78ac","abstract_canon_sha256":"48c61a69f3cd7793d5ef4c78f098948aa21117b28d9d6a107cfa44016e105de1"},"schema_version":"1.0"},"canonical_sha256":"337883da185d15a4996e37aec5c79b5e27af53b42856529acc66c6872e597c43","source":{"kind":"arxiv","id":"2501.08208","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.08208","created_at":"2026-07-05T11:39:06Z"},{"alias_kind":"arxiv_version","alias_value":"2501.08208v2","created_at":"2026-07-05T11:39:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08208","created_at":"2026-07-05T11:39:06Z"},{"alias_kind":"pith_short_12","alias_value":"GN4IHWQYLUK2","created_at":"2026-07-05T11:39:06Z"},{"alias_kind":"pith_short_16","alias_value":"GN4IHWQYLUK2JGLO","created_at":"2026-07-05T11:39:06Z"},{"alias_kind":"pith_short_8","alias_value":"GN4IHWQY","created_at":"2026-07-05T11:39:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GN4IHWQYLUK2JGLOG6XMLR43LY","target":"record","payload":{"canonical_record":{"source":{"id":"2501.08208","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T15:46:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2080b6f0f9bf5b834982df37122453013a9b4cd8cf6d1f25f84b7d37c95d78ac","abstract_canon_sha256":"48c61a69f3cd7793d5ef4c78f098948aa21117b28d9d6a107cfa44016e105de1"},"schema_version":"1.0"},"canonical_sha256":"337883da185d15a4996e37aec5c79b5e27af53b42856529acc66c6872e597c43","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:06.559461Z","signature_b64":"Ra43kw1lpMOMQSQgvfZki6N6l1rwN2M6puEovnluAdI7EeLnJGrEAybEqDzSobp/nYHEjbYq5HNjSewTbwqHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"337883da185d15a4996e37aec5c79b5e27af53b42856529acc66c6872e597c43","last_reissued_at":"2026-07-05T11:39:06.558873Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:06.558873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.08208","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":"2026-07-05T11:39:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r6f8WlOgzWJP3buSCeU+k3YOfXNZ4/MJ0wNur9WAtWWn1BPD7/VDqB96fO5yLi4SJqM76KykIJieA5aN/qWoCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T10:18:37.424813Z"},"content_sha256":"836f3183394940f5bc178d8a235234eb753624f18ff64cc623b7002b5762ac55","schema_version":"1.0","event_id":"sha256:836f3183394940f5bc178d8a235234eb753624f18ff64cc623b7002b5762ac55"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GN4IHWQYLUK2JGLOG6XMLR43LY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ASTRID -- An Automated and Scalable TRIaD for the Evaluation of RAG-based Clinical Question Answering Systems","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aisling Higham, Ernest Lim, Jared Joselowitz, Mohita Chowdhury, Yajie Vera He","submitted_at":"2025-01-14T15:46:39Z","abstract_excerpt":"Large Language Models (LLMs) have shown impressive potential in clinical question answering (QA), with Retrieval Augmented Generation (RAG) emerging as a leading approach for ensuring the factual accuracy of model responses. However, current automated RAG metrics perform poorly in clinical and conversational use cases. Using clinical human evaluations of responses is expensive, unscalable, and not conducive to the continuous iterative development of RAG systems. To address these challenges, we introduce ASTRID - an Automated and Scalable TRIaD for evaluating clinical QA systems leveraging RAG "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08208","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/2501.08208/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":"2026-07-05T11:39:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bOfwn15sYUBxuuDAC3N+4wQV+89lnt4L5TXEWCSzYHZOwf+DWgccIOP107sH6wtUerOv4XPmuOPIUqbSUQL5CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T10:18:37.425393Z"},"content_sha256":"1dc712b004324505fa8c8c99210a2179f0e1193effe71a65601c4221cc523a12","schema_version":"1.0","event_id":"sha256:1dc712b004324505fa8c8c99210a2179f0e1193effe71a65601c4221cc523a12"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GN4IHWQYLUK2JGLOG6XMLR43LY/bundle.json","state_url":"https://pith.science/pith/GN4IHWQYLUK2JGLOG6XMLR43LY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GN4IHWQYLUK2JGLOG6XMLR43LY/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":"2026-08-15T10:18:37Z","links":{"resolver":"https://pith.science/pith/GN4IHWQYLUK2JGLOG6XMLR43LY","bundle":"https://pith.science/pith/GN4IHWQYLUK2JGLOG6XMLR43LY/bundle.json","state":"https://pith.science/pith/GN4IHWQYLUK2JGLOG6XMLR43LY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GN4IHWQYLUK2JGLOG6XMLR43LY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GN4IHWQYLUK2JGLOG6XMLR43LY","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":"48c61a69f3cd7793d5ef4c78f098948aa21117b28d9d6a107cfa44016e105de1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T15:46:39Z","title_canon_sha256":"2080b6f0f9bf5b834982df37122453013a9b4cd8cf6d1f25f84b7d37c95d78ac"},"schema_version":"1.0","source":{"id":"2501.08208","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.08208","created_at":"2026-07-05T11:39:06Z"},{"alias_kind":"arxiv_version","alias_value":"2501.08208v2","created_at":"2026-07-05T11:39:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08208","created_at":"2026-07-05T11:39:06Z"},{"alias_kind":"pith_short_12","alias_value":"GN4IHWQYLUK2","created_at":"2026-07-05T11:39:06Z"},{"alias_kind":"pith_short_16","alias_value":"GN4IHWQYLUK2JGLO","created_at":"2026-07-05T11:39:06Z"},{"alias_kind":"pith_short_8","alias_value":"GN4IHWQY","created_at":"2026-07-05T11:39:06Z"}],"graph_snapshots":[{"event_id":"sha256:1dc712b004324505fa8c8c99210a2179f0e1193effe71a65601c4221cc523a12","target":"graph","created_at":"2026-07-05T11:39:06Z","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/2501.08208/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have shown impressive potential in clinical question answering (QA), with Retrieval Augmented Generation (RAG) emerging as a leading approach for ensuring the factual accuracy of model responses. However, current automated RAG metrics perform poorly in clinical and conversational use cases. Using clinical human evaluations of responses is expensive, unscalable, and not conducive to the continuous iterative development of RAG systems. To address these challenges, we introduce ASTRID - an Automated and Scalable TRIaD for evaluating clinical QA systems leveraging RAG ","authors_text":"Aisling Higham, Ernest Lim, Jared Joselowitz, Mohita Chowdhury, Yajie Vera He","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T15:46:39Z","title":"ASTRID -- An Automated and Scalable TRIaD for the Evaluation of RAG-based Clinical Question Answering Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08208","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":"sha256:836f3183394940f5bc178d8a235234eb753624f18ff64cc623b7002b5762ac55","target":"record","created_at":"2026-07-05T11:39:06Z","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":"48c61a69f3cd7793d5ef4c78f098948aa21117b28d9d6a107cfa44016e105de1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T15:46:39Z","title_canon_sha256":"2080b6f0f9bf5b834982df37122453013a9b4cd8cf6d1f25f84b7d37c95d78ac"},"schema_version":"1.0","source":{"id":"2501.08208","kind":"arxiv","version":2}},"canonical_sha256":"337883da185d15a4996e37aec5c79b5e27af53b42856529acc66c6872e597c43","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"337883da185d15a4996e37aec5c79b5e27af53b42856529acc66c6872e597c43","first_computed_at":"2026-07-05T11:39:06.558873Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:06.558873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ra43kw1lpMOMQSQgvfZki6N6l1rwN2M6puEovnluAdI7EeLnJGrEAybEqDzSobp/nYHEjbYq5HNjSewTbwqHAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:06.559461Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.08208","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:836f3183394940f5bc178d8a235234eb753624f18ff64cc623b7002b5762ac55","sha256:1dc712b004324505fa8c8c99210a2179f0e1193effe71a65601c4221cc523a12"],"state_sha256":"4c1d682a758d7d8f3cb822ec96c9fbc77df6e9883b1d2c9fca44f3465a6d2cbf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T3zwrUCyz5UowJvt3GOHg41TkfcCJdUq5gSIo44K03MU0LbjOnBZlAhgA/sNL02DmqquRRce1MnVEIc88ranAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T10:18:37.430343Z","bundle_sha256":"0bc2ee769b3bb24dbd37df5331b2982c3a9b273f1d5c50e8c2a39ba33268018a"}}