{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:R2KX3EQMMCEHDOWQBKQDT7IXSB","short_pith_number":"pith:R2KX3EQM","schema_version":"1.0","canonical_sha256":"8e957d920c608871bad00aa039fd17907547f15ae05626bced9b138421aec357","source":{"kind":"arxiv","id":"2510.08945","version":3},"attestation_state":"computed","paper":{"title":"FATHOMS-RAG: A Framework for the Assessment of Thinking and Observation in Multimodal Systems that use Retrieval Augmented Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"(2) Oak Ridge National Lab, (3) University of Florida), Amir Sadovnik (2), Brandon Schreiber (2), Curtis Taylor (2), James M Ghawaly Jr (1), Kevin Kurian (3) ((1) Louisiana State University, Ryan Shivers (2), Samuel Hildebrand (1), Sean Oesch (2)","submitted_at":"2025-10-10T02:51:47Z","abstract_excerpt":"Retrieval-augmented generation (RAG) has emerged as a promising paradigm for improving factual accuracy in large language models (LLMs). We introduce a benchmark designed to evaluate RAG pipelines as a whole, evaluating a pipeline's ability to ingest, retrieve, and reason about several modalities of information, differentiating it from existing benchmarks that focus on particular aspects such as retrieval. We present (1) a small, human-created dataset of 93 questions designed to evaluate a pipeline's ability to ingest textual data, tables, images, and data spread across these modalities in one"},"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":"2510.08945","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-10-10T02:51:47Z","cross_cats_sorted":[],"title_canon_sha256":"11901bbd658cf1d481e119829d5976a422bba716d7cc81305248eb7de4d20f83","abstract_canon_sha256":"7bca95aca4ab476d69f77ed1efbb74b327dd5c84e588de2a4f24d5d32ddf4f64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:08.003403Z","signature_b64":"Vv4klrJYDQXWAzfBP834QjppC8uT0xsTN0ZhKdz0v37hKkztqiFN/atP5E3jR60sHnlr1Kd0HcPmyyg+7dFfCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e957d920c608871bad00aa039fd17907547f15ae05626bced9b138421aec357","last_reissued_at":"2026-05-25T02:01:08.002645Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:08.002645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FATHOMS-RAG: A Framework for the Assessment of Thinking and Observation in Multimodal Systems that use Retrieval Augmented Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"(2) Oak Ridge National Lab, (3) University of Florida), Amir Sadovnik (2), Brandon Schreiber (2), Curtis Taylor (2), James M Ghawaly Jr (1), Kevin Kurian (3) ((1) Louisiana State University, Ryan Shivers (2), Samuel Hildebrand (1), Sean Oesch (2)","submitted_at":"2025-10-10T02:51:47Z","abstract_excerpt":"Retrieval-augmented generation (RAG) has emerged as a promising paradigm for improving factual accuracy in large language models (LLMs). We introduce a benchmark designed to evaluate RAG pipelines as a whole, evaluating a pipeline's ability to ingest, retrieve, and reason about several modalities of information, differentiating it from existing benchmarks that focus on particular aspects such as retrieval. We present (1) a small, human-created dataset of 93 questions designed to evaluate a pipeline's ability to ingest textual data, tables, images, and data spread across these modalities in one"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.08945","kind":"arxiv","version":3},"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/2510.08945/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":"2510.08945","created_at":"2026-05-25T02:01:08.002723+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.08945v3","created_at":"2026-05-25T02:01:08.002723+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.08945","created_at":"2026-05-25T02:01:08.002723+00:00"},{"alias_kind":"pith_short_12","alias_value":"R2KX3EQMMCEH","created_at":"2026-05-25T02:01:08.002723+00:00"},{"alias_kind":"pith_short_16","alias_value":"R2KX3EQMMCEHDOWQ","created_at":"2026-05-25T02:01:08.002723+00:00"},{"alias_kind":"pith_short_8","alias_value":"R2KX3EQM","created_at":"2026-05-25T02:01:08.002723+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R2KX3EQMMCEHDOWQBKQDT7IXSB","json":"https://pith.science/pith/R2KX3EQMMCEHDOWQBKQDT7IXSB.json","graph_json":"https://pith.science/api/pith-number/R2KX3EQMMCEHDOWQBKQDT7IXSB/graph.json","events_json":"https://pith.science/api/pith-number/R2KX3EQMMCEHDOWQBKQDT7IXSB/events.json","paper":"https://pith.science/paper/R2KX3EQM"},"agent_actions":{"view_html":"https://pith.science/pith/R2KX3EQMMCEHDOWQBKQDT7IXSB","download_json":"https://pith.science/pith/R2KX3EQMMCEHDOWQBKQDT7IXSB.json","view_paper":"https://pith.science/paper/R2KX3EQM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.08945&json=true","fetch_graph":"https://pith.science/api/pith-number/R2KX3EQMMCEHDOWQBKQDT7IXSB/graph.json","fetch_events":"https://pith.science/api/pith-number/R2KX3EQMMCEHDOWQBKQDT7IXSB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R2KX3EQMMCEHDOWQBKQDT7IXSB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R2KX3EQMMCEHDOWQBKQDT7IXSB/action/storage_attestation","attest_author":"https://pith.science/pith/R2KX3EQMMCEHDOWQBKQDT7IXSB/action/author_attestation","sign_citation":"https://pith.science/pith/R2KX3EQMMCEHDOWQBKQDT7IXSB/action/citation_signature","submit_replication":"https://pith.science/pith/R2KX3EQMMCEHDOWQBKQDT7IXSB/action/replication_record"}},"created_at":"2026-05-25T02:01:08.002723+00:00","updated_at":"2026-05-25T02:01:08.002723+00:00"}