{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RO5YYREMDKZMC2R4MGBHCXPBC7","short_pith_number":"pith:RO5YYREM","canonical_record":{"source":{"id":"2501.03995","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-07T18:52:05Z","cross_cats_sorted":["cs.CV","cs.IR","cs.IT","math.IT"],"title_canon_sha256":"4df4b3f5e33d2ed6542f03373a8c43356835c22245fd0662fe64bd9cc3e3dc83","abstract_canon_sha256":"504ba3a01791a8e7b3dc343b17a0ee0071f9cb6d1478216270750f7aa6312023"},"schema_version":"1.0"},"canonical_sha256":"8bbb8c448c1ab2c16a3c6182715de117ca49990e30703e282ff58dfa040d5c9a","source":{"kind":"arxiv","id":"2501.03995","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.03995","created_at":"2026-07-05T09:58:14Z"},{"alias_kind":"arxiv_version","alias_value":"2501.03995v1","created_at":"2026-07-05T09:58:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03995","created_at":"2026-07-05T09:58:14Z"},{"alias_kind":"pith_short_12","alias_value":"RO5YYREMDKZM","created_at":"2026-07-05T09:58:14Z"},{"alias_kind":"pith_short_16","alias_value":"RO5YYREMDKZMC2R4","created_at":"2026-07-05T09:58:14Z"},{"alias_kind":"pith_short_8","alias_value":"RO5YYREM","created_at":"2026-07-05T09:58:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RO5YYREMDKZMC2R4MGBHCXPBC7","target":"record","payload":{"canonical_record":{"source":{"id":"2501.03995","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-07T18:52:05Z","cross_cats_sorted":["cs.CV","cs.IR","cs.IT","math.IT"],"title_canon_sha256":"4df4b3f5e33d2ed6542f03373a8c43356835c22245fd0662fe64bd9cc3e3dc83","abstract_canon_sha256":"504ba3a01791a8e7b3dc343b17a0ee0071f9cb6d1478216270750f7aa6312023"},"schema_version":"1.0"},"canonical_sha256":"8bbb8c448c1ab2c16a3c6182715de117ca49990e30703e282ff58dfa040d5c9a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:14.117227Z","signature_b64":"F24KEkc5eujjApvOLWSvVfjppEvJBWcjKp4V34IEoHkzPDj+7IX+EHR5FfXIfVD3na8CKRftKsXagVHfMpHBDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bbb8c448c1ab2c16a3c6182715de117ca49990e30703e282ff58dfa040d5c9a","last_reissued_at":"2026-07-05T09:58:14.116734Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:14.116734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.03995","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":"2026-07-05T09:58:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"csuxCZ/C4GEjuT+7KmVwe6/e7WqHi7M7e3gU7Svl94LQ/Amrm/7amoE5PA8Ura97+E5P8w8QSJWbdZA3hzj2Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T00:58:49.174502Z"},"content_sha256":"503eeeba6a020c61a87594b0f261b15e848ec092c2aa451629c611d529b6124b","schema_version":"1.0","event_id":"sha256:503eeeba6a020c61a87594b0f261b15e848ec092c2aa451629c611d529b6124b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RO5YYREMDKZMC2R4MGBHCXPBC7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RAG-Check: Evaluating Multimodal Retrieval Augmented Generation Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.IR","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Matin Mortaheb, Mohammad A. Amir Khojastepour, Sennur Ulukus, Srimat T. Chakradhar","submitted_at":"2025-01-07T18:52:05Z","abstract_excerpt":"Retrieval-augmented generation (RAG) improves large language models (LLMs) by using external knowledge to guide response generation, reducing hallucinations. However, RAG, particularly multi-modal RAG, can introduce new hallucination sources: (i) the retrieval process may select irrelevant pieces (e.g., documents, images) as raw context from the database, and (ii) retrieved images are processed into text-based context via vision-language models (VLMs) or directly used by multi-modal language models (MLLMs) like GPT-4o, which may hallucinate. To address this, we propose a novel framework to eva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03995","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/2501.03995/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":"2026-07-05T09:58:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ph/6bDVFxYHvgJCm3lD/lHQLtheyiAncxNTbld6K6dN7LRE6WlEAb5397h2hd2yv6H0viCn2Z+y0Jbx9TmnXBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T00:58:49.174915Z"},"content_sha256":"8c9efc6608250e6d494011f33ed50f39cf3e0cf7916cc613db3f6cff520e1a8e","schema_version":"1.0","event_id":"sha256:8c9efc6608250e6d494011f33ed50f39cf3e0cf7916cc613db3f6cff520e1a8e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RO5YYREMDKZMC2R4MGBHCXPBC7/bundle.json","state_url":"https://pith.science/pith/RO5YYREMDKZMC2R4MGBHCXPBC7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RO5YYREMDKZMC2R4MGBHCXPBC7/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":"2026-07-16T00:58:49Z","links":{"resolver":"https://pith.science/pith/RO5YYREMDKZMC2R4MGBHCXPBC7","bundle":"https://pith.science/pith/RO5YYREMDKZMC2R4MGBHCXPBC7/bundle.json","state":"https://pith.science/pith/RO5YYREMDKZMC2R4MGBHCXPBC7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RO5YYREMDKZMC2R4MGBHCXPBC7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RO5YYREMDKZMC2R4MGBHCXPBC7","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":"504ba3a01791a8e7b3dc343b17a0ee0071f9cb6d1478216270750f7aa6312023","cross_cats_sorted":["cs.CV","cs.IR","cs.IT","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-07T18:52:05Z","title_canon_sha256":"4df4b3f5e33d2ed6542f03373a8c43356835c22245fd0662fe64bd9cc3e3dc83"},"schema_version":"1.0","source":{"id":"2501.03995","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.03995","created_at":"2026-07-05T09:58:14Z"},{"alias_kind":"arxiv_version","alias_value":"2501.03995v1","created_at":"2026-07-05T09:58:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03995","created_at":"2026-07-05T09:58:14Z"},{"alias_kind":"pith_short_12","alias_value":"RO5YYREMDKZM","created_at":"2026-07-05T09:58:14Z"},{"alias_kind":"pith_short_16","alias_value":"RO5YYREMDKZMC2R4","created_at":"2026-07-05T09:58:14Z"},{"alias_kind":"pith_short_8","alias_value":"RO5YYREM","created_at":"2026-07-05T09:58:14Z"}],"graph_snapshots":[{"event_id":"sha256:8c9efc6608250e6d494011f33ed50f39cf3e0cf7916cc613db3f6cff520e1a8e","target":"graph","created_at":"2026-07-05T09:58:14Z","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/2501.03995/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-augmented generation (RAG) improves large language models (LLMs) by using external knowledge to guide response generation, reducing hallucinations. However, RAG, particularly multi-modal RAG, can introduce new hallucination sources: (i) the retrieval process may select irrelevant pieces (e.g., documents, images) as raw context from the database, and (ii) retrieved images are processed into text-based context via vision-language models (VLMs) or directly used by multi-modal language models (MLLMs) like GPT-4o, which may hallucinate. To address this, we propose a novel framework to eva","authors_text":"Matin Mortaheb, Mohammad A. Amir Khojastepour, Sennur Ulukus, Srimat T. Chakradhar","cross_cats":["cs.CV","cs.IR","cs.IT","math.IT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-07T18:52:05Z","title":"RAG-Check: Evaluating Multimodal Retrieval Augmented Generation Performance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03995","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":"sha256:503eeeba6a020c61a87594b0f261b15e848ec092c2aa451629c611d529b6124b","target":"record","created_at":"2026-07-05T09:58:14Z","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":"504ba3a01791a8e7b3dc343b17a0ee0071f9cb6d1478216270750f7aa6312023","cross_cats_sorted":["cs.CV","cs.IR","cs.IT","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-07T18:52:05Z","title_canon_sha256":"4df4b3f5e33d2ed6542f03373a8c43356835c22245fd0662fe64bd9cc3e3dc83"},"schema_version":"1.0","source":{"id":"2501.03995","kind":"arxiv","version":1}},"canonical_sha256":"8bbb8c448c1ab2c16a3c6182715de117ca49990e30703e282ff58dfa040d5c9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8bbb8c448c1ab2c16a3c6182715de117ca49990e30703e282ff58dfa040d5c9a","first_computed_at":"2026-07-05T09:58:14.116734Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:58:14.116734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F24KEkc5eujjApvOLWSvVfjppEvJBWcjKp4V34IEoHkzPDj+7IX+EHR5FfXIfVD3na8CKRftKsXagVHfMpHBDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:58:14.117227Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.03995","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:503eeeba6a020c61a87594b0f261b15e848ec092c2aa451629c611d529b6124b","sha256:8c9efc6608250e6d494011f33ed50f39cf3e0cf7916cc613db3f6cff520e1a8e"],"state_sha256":"994f6965ee98784583ad5f02d89248e3d0f3c3c1fc2528d149a1cff51a198a45"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0dOiT/b/Tcz6aAg0XOXbHMHiK4eVTNe4EXsedmT5Vsm1bLVodePS0gaZrUgzKhMq5pfjkZREoy4aJlj0S7ptAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T00:58:49.178538Z","bundle_sha256":"b2d8b13c8c15d4387a3940965ebbbeb3a5f15d7f3fd332388a71c241a096c197"}}