{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:36CBEUS33S7OII67AVKERGAOM3","short_pith_number":"pith:36CBEUS3","schema_version":"1.0","canonical_sha256":"df8412525bdcbee423df055448980e66e9db531c703bd9cd99f0c1510a071e7a","source":{"kind":"arxiv","id":"2507.12378","version":1},"attestation_state":"computed","paper":{"title":"Developing Visual Augmented Q&A System using Scalable Vision Embedding Retrieval & Late Interaction Re-ranker","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Abhijeet Kumar, Rachna Saxena, Suresh Shanmugam","submitted_at":"2025-07-16T16:27:05Z","abstract_excerpt":"Traditional information extraction systems face challenges with text only language models as it does not consider infographics (visual elements of information) such as tables, charts, images etc. often used to convey complex information to readers. Multimodal LLM (MLLM) face challenges of finding needle in the haystack problem i.e., either longer context length or substantial number of documents as search space. Late interaction mechanism over visual language models has shown state of the art performance in retrieval-based vision augmented Q&A tasks. There are yet few challenges using it for R"},"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":"2507.12378","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-16T16:27:05Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d9579b497060620a9c934c34375e4d0363a63976977df5c1dc9cb8014bfbc0c9","abstract_canon_sha256":"43e8711ae66edc4b0cc77b8bfb1a64b44aebbb476d45359abded9a80cad28e06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:19.254249Z","signature_b64":"Svfloyq/erubJX+RXBPv/14xKGjZr6CQK38CmxM2y9wgRMDelAeDc53k3zldg7+aMFPWSUVyA9f7gCtNiVp7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df8412525bdcbee423df055448980e66e9db531c703bd9cd99f0c1510a071e7a","last_reissued_at":"2026-07-05T11:38:19.253669Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:19.253669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Developing Visual Augmented Q&A System using Scalable Vision Embedding Retrieval & Late Interaction Re-ranker","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Abhijeet Kumar, Rachna Saxena, Suresh Shanmugam","submitted_at":"2025-07-16T16:27:05Z","abstract_excerpt":"Traditional information extraction systems face challenges with text only language models as it does not consider infographics (visual elements of information) such as tables, charts, images etc. often used to convey complex information to readers. Multimodal LLM (MLLM) face challenges of finding needle in the haystack problem i.e., either longer context length or substantial number of documents as search space. Late interaction mechanism over visual language models has shown state of the art performance in retrieval-based vision augmented Q&A tasks. There are yet few challenges using it for R"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12378","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/2507.12378/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":"2507.12378","created_at":"2026-07-05T11:38:19.253733+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12378v1","created_at":"2026-07-05T11:38:19.253733+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12378","created_at":"2026-07-05T11:38:19.253733+00:00"},{"alias_kind":"pith_short_12","alias_value":"36CBEUS33S7O","created_at":"2026-07-05T11:38:19.253733+00:00"},{"alias_kind":"pith_short_16","alias_value":"36CBEUS33S7OII67","created_at":"2026-07-05T11:38:19.253733+00:00"},{"alias_kind":"pith_short_8","alias_value":"36CBEUS3","created_at":"2026-07-05T11:38:19.253733+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/36CBEUS33S7OII67AVKERGAOM3","json":"https://pith.science/pith/36CBEUS33S7OII67AVKERGAOM3.json","graph_json":"https://pith.science/api/pith-number/36CBEUS33S7OII67AVKERGAOM3/graph.json","events_json":"https://pith.science/api/pith-number/36CBEUS33S7OII67AVKERGAOM3/events.json","paper":"https://pith.science/paper/36CBEUS3"},"agent_actions":{"view_html":"https://pith.science/pith/36CBEUS33S7OII67AVKERGAOM3","download_json":"https://pith.science/pith/36CBEUS33S7OII67AVKERGAOM3.json","view_paper":"https://pith.science/paper/36CBEUS3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12378&json=true","fetch_graph":"https://pith.science/api/pith-number/36CBEUS33S7OII67AVKERGAOM3/graph.json","fetch_events":"https://pith.science/api/pith-number/36CBEUS33S7OII67AVKERGAOM3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/36CBEUS33S7OII67AVKERGAOM3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/36CBEUS33S7OII67AVKERGAOM3/action/storage_attestation","attest_author":"https://pith.science/pith/36CBEUS33S7OII67AVKERGAOM3/action/author_attestation","sign_citation":"https://pith.science/pith/36CBEUS33S7OII67AVKERGAOM3/action/citation_signature","submit_replication":"https://pith.science/pith/36CBEUS33S7OII67AVKERGAOM3/action/replication_record"}},"created_at":"2026-07-05T11:38:19.253733+00:00","updated_at":"2026-07-05T11:38:19.253733+00:00"}