{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6TBXGIK63JQF63QYHTDJISO7I7","short_pith_number":"pith:6TBXGIK6","canonical_record":{"source":{"id":"2506.23136","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-29T08:22:03Z","cross_cats_sorted":[],"title_canon_sha256":"7995b263e69f27abeb3f59d62e1465df78bd5079378ed0b3d395e44def9d90e1","abstract_canon_sha256":"f01d87854b3abd413b4d7844498b038b8fb2d98e7cad94a6dced39ae96220ccf"},"schema_version":"1.0"},"canonical_sha256":"f4c373215eda605f6e183cc69449df47d803a3611f6175490db6e9f6ae9f921b","source":{"kind":"arxiv","id":"2506.23136","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23136","created_at":"2026-07-05T11:29:16Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23136v1","created_at":"2026-07-05T11:29:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23136","created_at":"2026-07-05T11:29:16Z"},{"alias_kind":"pith_short_12","alias_value":"6TBXGIK63JQF","created_at":"2026-07-05T11:29:16Z"},{"alias_kind":"pith_short_16","alias_value":"6TBXGIK63JQF63QY","created_at":"2026-07-05T11:29:16Z"},{"alias_kind":"pith_short_8","alias_value":"6TBXGIK6","created_at":"2026-07-05T11:29:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6TBXGIK63JQF63QYHTDJISO7I7","target":"record","payload":{"canonical_record":{"source":{"id":"2506.23136","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-29T08:22:03Z","cross_cats_sorted":[],"title_canon_sha256":"7995b263e69f27abeb3f59d62e1465df78bd5079378ed0b3d395e44def9d90e1","abstract_canon_sha256":"f01d87854b3abd413b4d7844498b038b8fb2d98e7cad94a6dced39ae96220ccf"},"schema_version":"1.0"},"canonical_sha256":"f4c373215eda605f6e183cc69449df47d803a3611f6175490db6e9f6ae9f921b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:16.426367Z","signature_b64":"WAPBD49zpHJFWGCHirdAdB+GSJREvBlftrA3TrtxnE5PICWqsxkIEd8f901FGwpJidu8Lrl2o/KsIXq2A0/+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4c373215eda605f6e183cc69449df47d803a3611f6175490db6e9f6ae9f921b","last_reissued_at":"2026-07-05T11:29:16.425595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:16.425595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.23136","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":"2026-07-05T11:29:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WzuwvHg4u5UWQngSz+sc6Af5r82x3alVHgm20kLQc+S5VxJ3RYjFgdXcEx+ZNoOgrCjgwW2pdR3xvckki4aYAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:30:43.017168Z"},"content_sha256":"d10522217ffcedbbdbe3d1fbe355b701fc25fb751bae2ce9eac4791a7bb262fc","schema_version":"1.0","event_id":"sha256:d10522217ffcedbbdbe3d1fbe355b701fc25fb751bae2ce9eac4791a7bb262fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6TBXGIK63JQF63QYHTDJISO7I7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM-Assisted Question-Answering on Technical Documents Using Structured Data-Aware Retrieval Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mohammad Ariful Haque, Shadman Sobhan","submitted_at":"2025-06-29T08:22:03Z","abstract_excerpt":"Large Language Models (LLMs) are capable of natural language understanding and generation. But they face challenges such as hallucination and outdated knowledge. Fine-tuning is one possible solution, but it is resource-intensive and must be repeated with every data update. Retrieval-Augmented Generation (RAG) offers an efficient solution by allowing LLMs to access external knowledge sources. However, traditional RAG pipelines struggle with retrieving information from complex technical documents with structured data such as tables and images. In this work, we propose a RAG pipeline, capable of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23136","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/2506.23136/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":"2026-07-05T11:29:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tB5y+bBNRNp0fMRg9lsJsAT331rtxMQbAvKpLEJWU/VGSCAmPmj0xruQcDBbMgehKYVThs4T8aledKU0qLgiDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:30:43.017657Z"},"content_sha256":"d972450a0983b6a7878b60f9137eadea4cdf26bcfc92e04ba4f6f546a79e434e","schema_version":"1.0","event_id":"sha256:d972450a0983b6a7878b60f9137eadea4cdf26bcfc92e04ba4f6f546a79e434e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6TBXGIK63JQF63QYHTDJISO7I7/bundle.json","state_url":"https://pith.science/pith/6TBXGIK63JQF63QYHTDJISO7I7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6TBXGIK63JQF63QYHTDJISO7I7/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":"2026-08-09T14:30:43Z","links":{"resolver":"https://pith.science/pith/6TBXGIK63JQF63QYHTDJISO7I7","bundle":"https://pith.science/pith/6TBXGIK63JQF63QYHTDJISO7I7/bundle.json","state":"https://pith.science/pith/6TBXGIK63JQF63QYHTDJISO7I7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6TBXGIK63JQF63QYHTDJISO7I7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6TBXGIK63JQF63QYHTDJISO7I7","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":"f01d87854b3abd413b4d7844498b038b8fb2d98e7cad94a6dced39ae96220ccf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-29T08:22:03Z","title_canon_sha256":"7995b263e69f27abeb3f59d62e1465df78bd5079378ed0b3d395e44def9d90e1"},"schema_version":"1.0","source":{"id":"2506.23136","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23136","created_at":"2026-07-05T11:29:16Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23136v1","created_at":"2026-07-05T11:29:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23136","created_at":"2026-07-05T11:29:16Z"},{"alias_kind":"pith_short_12","alias_value":"6TBXGIK63JQF","created_at":"2026-07-05T11:29:16Z"},{"alias_kind":"pith_short_16","alias_value":"6TBXGIK63JQF63QY","created_at":"2026-07-05T11:29:16Z"},{"alias_kind":"pith_short_8","alias_value":"6TBXGIK6","created_at":"2026-07-05T11:29:16Z"}],"graph_snapshots":[{"event_id":"sha256:d972450a0983b6a7878b60f9137eadea4cdf26bcfc92e04ba4f6f546a79e434e","target":"graph","created_at":"2026-07-05T11:29:16Z","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/2506.23136/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are capable of natural language understanding and generation. But they face challenges such as hallucination and outdated knowledge. Fine-tuning is one possible solution, but it is resource-intensive and must be repeated with every data update. Retrieval-Augmented Generation (RAG) offers an efficient solution by allowing LLMs to access external knowledge sources. However, traditional RAG pipelines struggle with retrieving information from complex technical documents with structured data such as tables and images. In this work, we propose a RAG pipeline, capable of ","authors_text":"Mohammad Ariful Haque, Shadman Sobhan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-29T08:22:03Z","title":"LLM-Assisted Question-Answering on Technical Documents Using Structured Data-Aware Retrieval Augmented Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23136","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:d10522217ffcedbbdbe3d1fbe355b701fc25fb751bae2ce9eac4791a7bb262fc","target":"record","created_at":"2026-07-05T11:29:16Z","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":"f01d87854b3abd413b4d7844498b038b8fb2d98e7cad94a6dced39ae96220ccf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-29T08:22:03Z","title_canon_sha256":"7995b263e69f27abeb3f59d62e1465df78bd5079378ed0b3d395e44def9d90e1"},"schema_version":"1.0","source":{"id":"2506.23136","kind":"arxiv","version":1}},"canonical_sha256":"f4c373215eda605f6e183cc69449df47d803a3611f6175490db6e9f6ae9f921b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4c373215eda605f6e183cc69449df47d803a3611f6175490db6e9f6ae9f921b","first_computed_at":"2026-07-05T11:29:16.425595Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:16.425595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WAPBD49zpHJFWGCHirdAdB+GSJREvBlftrA3TrtxnE5PICWqsxkIEd8f901FGwpJidu8Lrl2o/KsIXq2A0/+DA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:16.426367Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.23136","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d10522217ffcedbbdbe3d1fbe355b701fc25fb751bae2ce9eac4791a7bb262fc","sha256:d972450a0983b6a7878b60f9137eadea4cdf26bcfc92e04ba4f6f546a79e434e"],"state_sha256":"52ea84e79260b9879ea0b7d3884d0d306e8b153bbe69df365da9c536e2aabab4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9zWeDEFy9+RhA7CGy2Hx8ix7Mv9ycJxzSUTNM1KlIpHthFXn/XNzJhrazyOlA3FE/NQKWoyr/DYrFKsmARBOAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T14:30:43.021161Z","bundle_sha256":"f24c74db3c853c50151902adbca2c93a452268b1c5669b566305b9b6f723b893"}}