{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YL5FFR52KQHA7Z2LY7W2UMM6UH","short_pith_number":"pith:YL5FFR52","canonical_record":{"source":{"id":"2407.12735","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T16:55:42Z","cross_cats_sorted":[],"title_canon_sha256":"6ac67e5ef8846f5c1abbb7c558cfd1b8c3b8db089024b0493c1883887977cf9a","abstract_canon_sha256":"f714754acf693b6654cad64a33a7690062eae9df8d1db6a15d77a08283f16b38"},"schema_version":"1.0"},"canonical_sha256":"c2fa52c7ba540e0fe74bc7edaa319ea1d60077dbc79a5c84effed31c0aaf7e2d","source":{"kind":"arxiv","id":"2407.12735","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12735","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12735v4","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12735","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"pith_short_12","alias_value":"YL5FFR52KQHA","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"pith_short_16","alias_value":"YL5FFR52KQHA7Z2L","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"pith_short_8","alias_value":"YL5FFR52","created_at":"2026-07-05T09:42:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YL5FFR52KQHA7Z2LY7W2UMM6UH","target":"record","payload":{"canonical_record":{"source":{"id":"2407.12735","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T16:55:42Z","cross_cats_sorted":[],"title_canon_sha256":"6ac67e5ef8846f5c1abbb7c558cfd1b8c3b8db089024b0493c1883887977cf9a","abstract_canon_sha256":"f714754acf693b6654cad64a33a7690062eae9df8d1db6a15d77a08283f16b38"},"schema_version":"1.0"},"canonical_sha256":"c2fa52c7ba540e0fe74bc7edaa319ea1d60077dbc79a5c84effed31c0aaf7e2d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:28.069509Z","signature_b64":"V9M1/0sZ47g6k/34y9hCGUGp6h3lEQjM4WidnnDgUrqVVVqTVQ89BoKIFRbK8UFhRxDqlGikEE1KbJyeoMtIBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2fa52c7ba540e0fe74bc7edaa319ea1d60077dbc79a5c84effed31c0aaf7e2d","last_reissued_at":"2026-07-05T09:42:28.069036Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:28.069036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.12735","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:42:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fw/A/kI09Cnt0zaU3DJMeylv1yxzAqIW6/uPglWN69dMkhDAg/SQpwm9nG9C45jpV5HjlIrximxza7IPcX+UCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:32:46.780757Z"},"content_sha256":"7187a3bf09cf3252e461e7886e52f68fe181bac891973a128d22bf295322a315","schema_version":"1.0","event_id":"sha256:7187a3bf09cf3252e461e7886e52f68fe181bac891973a128d22bf295322a315"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YL5FFR52KQHA7Z2LY7W2UMM6UH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EchoSight: Advancing Visual-Language Models with Wiki Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Weidi Xie, Yibin Yan","submitted_at":"2024-07-17T16:55:42Z","abstract_excerpt":"Knowledge-based Visual Question Answering (KVQA) tasks require answering questions about images using extensive background knowledge. Despite significant advancements, generative models often struggle with these tasks due to the limited integration of external knowledge. In this paper, we introduce EchoSight, a novel multimodal Retrieval-Augmented Generation (RAG) framework that enables large language models (LLMs) to answer visual questions requiring fine-grained encyclopedic knowledge. To strive for high-performing retrieval, EchoSight first searches wiki articles by using visual-only inform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12735","kind":"arxiv","version":4},"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/2407.12735/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":"2026-07-05T09:42:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0pcfg/CwRsw0BWY1clK2ljP0zuWFIHqVOWclbMnrVqhvwyTn95WhETyYeZhbPmxtlc/PsiEbQAFwJA5BIanhDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:32:46.781262Z"},"content_sha256":"7f644938c8c0052475e4abafea4e0c41c664f923560c153314916395bbb8311b","schema_version":"1.0","event_id":"sha256:7f644938c8c0052475e4abafea4e0c41c664f923560c153314916395bbb8311b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YL5FFR52KQHA7Z2LY7W2UMM6UH/bundle.json","state_url":"https://pith.science/pith/YL5FFR52KQHA7Z2LY7W2UMM6UH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YL5FFR52KQHA7Z2LY7W2UMM6UH/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":"2026-08-05T06:32:46Z","links":{"resolver":"https://pith.science/pith/YL5FFR52KQHA7Z2LY7W2UMM6UH","bundle":"https://pith.science/pith/YL5FFR52KQHA7Z2LY7W2UMM6UH/bundle.json","state":"https://pith.science/pith/YL5FFR52KQHA7Z2LY7W2UMM6UH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YL5FFR52KQHA7Z2LY7W2UMM6UH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YL5FFR52KQHA7Z2LY7W2UMM6UH","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":"f714754acf693b6654cad64a33a7690062eae9df8d1db6a15d77a08283f16b38","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T16:55:42Z","title_canon_sha256":"6ac67e5ef8846f5c1abbb7c558cfd1b8c3b8db089024b0493c1883887977cf9a"},"schema_version":"1.0","source":{"id":"2407.12735","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12735","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12735v4","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12735","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"pith_short_12","alias_value":"YL5FFR52KQHA","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"pith_short_16","alias_value":"YL5FFR52KQHA7Z2L","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"pith_short_8","alias_value":"YL5FFR52","created_at":"2026-07-05T09:42:28Z"}],"graph_snapshots":[{"event_id":"sha256:7f644938c8c0052475e4abafea4e0c41c664f923560c153314916395bbb8311b","target":"graph","created_at":"2026-07-05T09:42:28Z","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/2407.12735/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Knowledge-based Visual Question Answering (KVQA) tasks require answering questions about images using extensive background knowledge. Despite significant advancements, generative models often struggle with these tasks due to the limited integration of external knowledge. In this paper, we introduce EchoSight, a novel multimodal Retrieval-Augmented Generation (RAG) framework that enables large language models (LLMs) to answer visual questions requiring fine-grained encyclopedic knowledge. To strive for high-performing retrieval, EchoSight first searches wiki articles by using visual-only inform","authors_text":"Weidi Xie, Yibin Yan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T16:55:42Z","title":"EchoSight: Advancing Visual-Language Models with Wiki Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12735","kind":"arxiv","version":4},"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":"sha256:7187a3bf09cf3252e461e7886e52f68fe181bac891973a128d22bf295322a315","target":"record","created_at":"2026-07-05T09:42:28Z","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":"f714754acf693b6654cad64a33a7690062eae9df8d1db6a15d77a08283f16b38","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T16:55:42Z","title_canon_sha256":"6ac67e5ef8846f5c1abbb7c558cfd1b8c3b8db089024b0493c1883887977cf9a"},"schema_version":"1.0","source":{"id":"2407.12735","kind":"arxiv","version":4}},"canonical_sha256":"c2fa52c7ba540e0fe74bc7edaa319ea1d60077dbc79a5c84effed31c0aaf7e2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2fa52c7ba540e0fe74bc7edaa319ea1d60077dbc79a5c84effed31c0aaf7e2d","first_computed_at":"2026-07-05T09:42:28.069036Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:28.069036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V9M1/0sZ47g6k/34y9hCGUGp6h3lEQjM4WidnnDgUrqVVVqTVQ89BoKIFRbK8UFhRxDqlGikEE1KbJyeoMtIBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:28.069509Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12735","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7187a3bf09cf3252e461e7886e52f68fe181bac891973a128d22bf295322a315","sha256:7f644938c8c0052475e4abafea4e0c41c664f923560c153314916395bbb8311b"],"state_sha256":"677b2c7a08aa2379da8d473bf66586293d1d96b749feb341605fc6a423c95240"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lJWGv6UVrsI/FMA7Ir1xLcXVf4Riw6AtAz2Wm/alVObtqq+5l2ODMki/YlEcpb4Vf8W3Bxbi8of8jrXdJZeDAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T06:32:46.785009Z","bundle_sha256":"1a9cfb8d677a0ba6a850f788e091889b8172f10f27ab94fdffba23801a6ea1ad"}}