{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:S3LDVVL2X2CKL65PE4ECTGXV3G","short_pith_number":"pith:S3LDVVL2","schema_version":"1.0","canonical_sha256":"96d63ad57abe84a5fbaf2708299af5d9962a115755adbab147e36093bb9fe7fa","source":{"kind":"arxiv","id":"2507.22938","version":1},"attestation_state":"computed","paper":{"title":"A Graph-based Approach for Multi-Modal Question Answering from Flowcharts in Telecom Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Akshat Jain, Ayaaz Khan, H. G. Ranjani, Pranav Gangrade, Sujoy Roychowdhury, Sumit Soman, Venkata Dharma Surya Narayana Sastry","submitted_at":"2025-07-25T07:36:13Z","abstract_excerpt":"Question-Answering (QA) from technical documents often involves questions whose answers are present in figures, such as flowcharts or flow diagrams. Text-based Retrieval Augmented Generation (RAG) systems may fail to answer such questions. We leverage graph representations of flowcharts obtained from Visual large Language Models (VLMs) and incorporate them in a text-based RAG system to show that this approach can enable image retrieval for QA in the telecom domain. We present the end-to-end approach from processing technical documents, classifying image types, building graph representations, a"},"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":"2507.22938","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-25T07:36:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"17527c7998c163bed0dd656c61123c4f16d2df99f9c26b0d4b3347b5b89c4524","abstract_canon_sha256":"dfd4c2532033066eb93b6a77d2d89a01b835df0d970f39664e1f5d46fca01c8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:02.356496Z","signature_b64":"I4xqWI1otVcN7HXd3bWFCbv+h4lLbJBISfZIHZkBCE7G/EoiOf3lxfuc7yCRFhu80o4qzkm6lFXTcZK8pUqTAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96d63ad57abe84a5fbaf2708299af5d9962a115755adbab147e36093bb9fe7fa","last_reissued_at":"2026-07-05T11:46:02.355952Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:02.355952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Graph-based Approach for Multi-Modal Question Answering from Flowcharts in Telecom Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Akshat Jain, Ayaaz Khan, H. G. Ranjani, Pranav Gangrade, Sujoy Roychowdhury, Sumit Soman, Venkata Dharma Surya Narayana Sastry","submitted_at":"2025-07-25T07:36:13Z","abstract_excerpt":"Question-Answering (QA) from technical documents often involves questions whose answers are present in figures, such as flowcharts or flow diagrams. Text-based Retrieval Augmented Generation (RAG) systems may fail to answer such questions. We leverage graph representations of flowcharts obtained from Visual large Language Models (VLMs) and incorporate them in a text-based RAG system to show that this approach can enable image retrieval for QA in the telecom domain. We present the end-to-end approach from processing technical documents, classifying image types, building graph representations, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22938","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/2507.22938/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":"2507.22938","created_at":"2026-07-05T11:46:02.356013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.22938v1","created_at":"2026-07-05T11:46:02.356013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22938","created_at":"2026-07-05T11:46:02.356013+00:00"},{"alias_kind":"pith_short_12","alias_value":"S3LDVVL2X2CK","created_at":"2026-07-05T11:46:02.356013+00:00"},{"alias_kind":"pith_short_16","alias_value":"S3LDVVL2X2CKL65P","created_at":"2026-07-05T11:46:02.356013+00:00"},{"alias_kind":"pith_short_8","alias_value":"S3LDVVL2","created_at":"2026-07-05T11:46:02.356013+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/S3LDVVL2X2CKL65PE4ECTGXV3G","json":"https://pith.science/pith/S3LDVVL2X2CKL65PE4ECTGXV3G.json","graph_json":"https://pith.science/api/pith-number/S3LDVVL2X2CKL65PE4ECTGXV3G/graph.json","events_json":"https://pith.science/api/pith-number/S3LDVVL2X2CKL65PE4ECTGXV3G/events.json","paper":"https://pith.science/paper/S3LDVVL2"},"agent_actions":{"view_html":"https://pith.science/pith/S3LDVVL2X2CKL65PE4ECTGXV3G","download_json":"https://pith.science/pith/S3LDVVL2X2CKL65PE4ECTGXV3G.json","view_paper":"https://pith.science/paper/S3LDVVL2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.22938&json=true","fetch_graph":"https://pith.science/api/pith-number/S3LDVVL2X2CKL65PE4ECTGXV3G/graph.json","fetch_events":"https://pith.science/api/pith-number/S3LDVVL2X2CKL65PE4ECTGXV3G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S3LDVVL2X2CKL65PE4ECTGXV3G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S3LDVVL2X2CKL65PE4ECTGXV3G/action/storage_attestation","attest_author":"https://pith.science/pith/S3LDVVL2X2CKL65PE4ECTGXV3G/action/author_attestation","sign_citation":"https://pith.science/pith/S3LDVVL2X2CKL65PE4ECTGXV3G/action/citation_signature","submit_replication":"https://pith.science/pith/S3LDVVL2X2CKL65PE4ECTGXV3G/action/replication_record"}},"created_at":"2026-07-05T11:46:02.356013+00:00","updated_at":"2026-07-05T11:46:02.356013+00:00"}