{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JRTUYOF5ITSNIQUP5TEA22LJK3","short_pith_number":"pith:JRTUYOF5","canonical_record":{"source":{"id":"2405.20834","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-31T14:23:49Z","cross_cats_sorted":[],"title_canon_sha256":"88e6a4a31f11d7c31f2469dd90b12c37a29082942813fa8ead4209a332610fe1","abstract_canon_sha256":"4f46e61fa97d163c1b0b50c6106f456da0da2173a9430a853cb644376d2e0064"},"schema_version":"1.0"},"canonical_sha256":"4c674c38bd44e4d4428fecc80d696956d20db3706719caf35055c3038fd329a3","source":{"kind":"arxiv","id":"2405.20834","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20834","created_at":"2026-07-05T08:25:42Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20834v1","created_at":"2026-07-05T08:25:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20834","created_at":"2026-07-05T08:25:42Z"},{"alias_kind":"pith_short_12","alias_value":"JRTUYOF5ITSN","created_at":"2026-07-05T08:25:42Z"},{"alias_kind":"pith_short_16","alias_value":"JRTUYOF5ITSNIQUP","created_at":"2026-07-05T08:25:42Z"},{"alias_kind":"pith_short_8","alias_value":"JRTUYOF5","created_at":"2026-07-05T08:25:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JRTUYOF5ITSNIQUP5TEA22LJK3","target":"record","payload":{"canonical_record":{"source":{"id":"2405.20834","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-31T14:23:49Z","cross_cats_sorted":[],"title_canon_sha256":"88e6a4a31f11d7c31f2469dd90b12c37a29082942813fa8ead4209a332610fe1","abstract_canon_sha256":"4f46e61fa97d163c1b0b50c6106f456da0da2173a9430a853cb644376d2e0064"},"schema_version":"1.0"},"canonical_sha256":"4c674c38bd44e4d4428fecc80d696956d20db3706719caf35055c3038fd329a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:42.576971Z","signature_b64":"oiTXvgk1G19Mg9nCtgid+f8gwfWGPa6P9PM4gHpKPB02GHtcxN6JKpogilofqdopdyR8Ba0BAt4JImEJLQSFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c674c38bd44e4d4428fecc80d696956d20db3706719caf35055c3038fd329a3","last_reissued_at":"2026-07-05T08:25:42.576461Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:42.576461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.20834","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":"2026-07-05T08:25:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gPfcanpoUjuVKNDVPmXYBCmvvZAfTMfkAFqOZ9MqEO48FwXlKhUTYEbF/3ooLDDoT7bDKzKVmu8kH+pab2yECw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:28:50.030851Z"},"content_sha256":"6721db25023d37a968ffe6d678b9d5c86f9841d83dda5abf4fb2489948b94d35","schema_version":"1.0","event_id":"sha256:6721db25023d37a968ffe6d678b9d5c86f9841d83dda5abf4fb2489948b94d35"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JRTUYOF5ITSNIQUP5TEA22LJK3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bihui Yu, Cheng Tan, Jingxuan Wei, Linzhuang Sun, Ruifeng Guo, Siyuan Li, Stan Z. Li, Zhangyang Gao","submitted_at":"2024-05-31T14:23:49Z","abstract_excerpt":"Large language models equipped with retrieval-augmented generation (RAG) represent a burgeoning field aimed at enhancing answering capabilities by leveraging external knowledge bases. Although the application of RAG with language-only models has been extensively explored, its adaptation into multimodal vision-language models remains nascent. Going beyond mere answer generation, the primary goal of multimodal RAG is to cultivate the models' ability to reason in response to relevant queries. To this end, we introduce a novel multimodal RAG framework named RMR (Retrieval Meets Reasoning). The RMR"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20834","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/2405.20834/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":"2026-07-05T08:25:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2/x+pwXuIrVUXXxhOVR9tt0P+UIlhK2XQqJVGusPJsZfug6+2ZGZ4Ey4U39Pd+MnoG8FUj6EoizSUAbY85W9BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:28:50.031356Z"},"content_sha256":"dcf2b6903b74f87943163b7135160262b7be3c24dcea80d30e84fef4184a8a73","schema_version":"1.0","event_id":"sha256:dcf2b6903b74f87943163b7135160262b7be3c24dcea80d30e84fef4184a8a73"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JRTUYOF5ITSNIQUP5TEA22LJK3/bundle.json","state_url":"https://pith.science/pith/JRTUYOF5ITSNIQUP5TEA22LJK3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JRTUYOF5ITSNIQUP5TEA22LJK3/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":"2026-08-09T09:28:50Z","links":{"resolver":"https://pith.science/pith/JRTUYOF5ITSNIQUP5TEA22LJK3","bundle":"https://pith.science/pith/JRTUYOF5ITSNIQUP5TEA22LJK3/bundle.json","state":"https://pith.science/pith/JRTUYOF5ITSNIQUP5TEA22LJK3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JRTUYOF5ITSNIQUP5TEA22LJK3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JRTUYOF5ITSNIQUP5TEA22LJK3","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":"4f46e61fa97d163c1b0b50c6106f456da0da2173a9430a853cb644376d2e0064","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-31T14:23:49Z","title_canon_sha256":"88e6a4a31f11d7c31f2469dd90b12c37a29082942813fa8ead4209a332610fe1"},"schema_version":"1.0","source":{"id":"2405.20834","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20834","created_at":"2026-07-05T08:25:42Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20834v1","created_at":"2026-07-05T08:25:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20834","created_at":"2026-07-05T08:25:42Z"},{"alias_kind":"pith_short_12","alias_value":"JRTUYOF5ITSN","created_at":"2026-07-05T08:25:42Z"},{"alias_kind":"pith_short_16","alias_value":"JRTUYOF5ITSNIQUP","created_at":"2026-07-05T08:25:42Z"},{"alias_kind":"pith_short_8","alias_value":"JRTUYOF5","created_at":"2026-07-05T08:25:42Z"}],"graph_snapshots":[{"event_id":"sha256:dcf2b6903b74f87943163b7135160262b7be3c24dcea80d30e84fef4184a8a73","target":"graph","created_at":"2026-07-05T08:25:42Z","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/2405.20834/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models equipped with retrieval-augmented generation (RAG) represent a burgeoning field aimed at enhancing answering capabilities by leveraging external knowledge bases. Although the application of RAG with language-only models has been extensively explored, its adaptation into multimodal vision-language models remains nascent. Going beyond mere answer generation, the primary goal of multimodal RAG is to cultivate the models' ability to reason in response to relevant queries. To this end, we introduce a novel multimodal RAG framework named RMR (Retrieval Meets Reasoning). The RMR","authors_text":"Bihui Yu, Cheng Tan, Jingxuan Wei, Linzhuang Sun, Ruifeng Guo, Siyuan Li, Stan Z. Li, Zhangyang Gao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-31T14:23:49Z","title":"Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20834","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":"sha256:6721db25023d37a968ffe6d678b9d5c86f9841d83dda5abf4fb2489948b94d35","target":"record","created_at":"2026-07-05T08:25:42Z","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":"4f46e61fa97d163c1b0b50c6106f456da0da2173a9430a853cb644376d2e0064","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-31T14:23:49Z","title_canon_sha256":"88e6a4a31f11d7c31f2469dd90b12c37a29082942813fa8ead4209a332610fe1"},"schema_version":"1.0","source":{"id":"2405.20834","kind":"arxiv","version":1}},"canonical_sha256":"4c674c38bd44e4d4428fecc80d696956d20db3706719caf35055c3038fd329a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c674c38bd44e4d4428fecc80d696956d20db3706719caf35055c3038fd329a3","first_computed_at":"2026-07-05T08:25:42.576461Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:42.576461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oiTXvgk1G19Mg9nCtgid+f8gwfWGPa6P9PM4gHpKPB02GHtcxN6JKpogilofqdopdyR8Ba0BAt4JImEJLQSFDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:42.576971Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.20834","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6721db25023d37a968ffe6d678b9d5c86f9841d83dda5abf4fb2489948b94d35","sha256:dcf2b6903b74f87943163b7135160262b7be3c24dcea80d30e84fef4184a8a73"],"state_sha256":"2e5b0bdb043ed608255a841989a516fdfc6a45bebd8d4b7915c8cd01b312d544"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CDoag44ZZC+QX/bepEHTspqZLXPl+BD4qnM7T/DnV3AhlAoVXXgX2Q8QWLK1vovrrbpmFTl9J8S7/uSZCQbsAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T09:28:50.036389Z","bundle_sha256":"a4472a4f4cd3838ae46fc443b3cb725856d2707db11ebd01cb80de2863f33509"}}