{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TXXCJJQXX5RLSCTDCXA75YOJWK","short_pith_number":"pith:TXXCJJQX","canonical_record":{"source":{"id":"2401.12599","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-01-23T09:54:36Z","cross_cats_sorted":[],"title_canon_sha256":"30210795f696706e301c6cb6048487c89001cd1dc45f92778e96f803dd802053","abstract_canon_sha256":"f0bb553b321842d63c71df3d8a69fe4694ab1bef6a7932f49bf17db3f16238dc"},"schema_version":"1.0"},"canonical_sha256":"9dee24a617bf62b90a6315c1fee1c9b2a4585aee6df61aa5513ddda279000241","source":{"kind":"arxiv","id":"2401.12599","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.12599","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"arxiv_version","alias_value":"2401.12599v1","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12599","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"pith_short_12","alias_value":"TXXCJJQXX5RL","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"pith_short_16","alias_value":"TXXCJJQXX5RLSCTD","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"pith_short_8","alias_value":"TXXCJJQX","created_at":"2026-07-05T07:36:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TXXCJJQXX5RLSCTDCXA75YOJWK","target":"record","payload":{"canonical_record":{"source":{"id":"2401.12599","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-01-23T09:54:36Z","cross_cats_sorted":[],"title_canon_sha256":"30210795f696706e301c6cb6048487c89001cd1dc45f92778e96f803dd802053","abstract_canon_sha256":"f0bb553b321842d63c71df3d8a69fe4694ab1bef6a7932f49bf17db3f16238dc"},"schema_version":"1.0"},"canonical_sha256":"9dee24a617bf62b90a6315c1fee1c9b2a4585aee6df61aa5513ddda279000241","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:33.049955Z","signature_b64":"kNy2G29+45b0q6JN402orHFZeaGdDDbgTNVXoqj8Hve5iZ0Wd1J3SGrtZm/qf+cH1ydNh0PkZS9tnS9oloNACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9dee24a617bf62b90a6315c1fee1c9b2a4585aee6df61aa5513ddda279000241","last_reissued_at":"2026-07-05T07:36:33.049475Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:33.049475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.12599","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":"2026-07-05T07:36:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EYIMldbgpiiRO96P3WeNm1c/LROCpIXsG7nnvTejMGe3BK4us2PBTwIaDIGOhoAC4Zh9ra/p2oByJSefz2SxBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T14:30:50.637481Z"},"content_sha256":"b7fb1f58e0a0b64967271e124f5e506aed606d3b746cd05ab61008e1b233f143","schema_version":"1.0","event_id":"sha256:b7fb1f58e0a0b64967271e124f5e506aed606d3b746cd05ab61008e1b233f143"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TXXCJJQXX5RLSCTDCXA75YOJWK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Revolutionizing Retrieval-Augmented Generation with Enhanced PDF Structure Recognition","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Demiao Lin (chatdoc.com)","submitted_at":"2024-01-23T09:54:36Z","abstract_excerpt":"With the rapid development of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) has become a predominant method in the field of professional knowledge-based question answering. Presently, major foundation model companies have opened up Embedding and Chat API interfaces, and frameworks like LangChain have already integrated the RAG process. It appears that the key models and steps in RAG have been resolved, leading to the question: are professional knowledge QA systems now approaching perfection? This article discovers that current primary methods depend on the premise of acces"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12599","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/2401.12599/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":"2026-07-05T07:36:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nmxzUdKSHljcCCeCz/FxoiQa/U5OCnrbYLC+Dr9f4T+DctvzU45lOz6TIVnzyJHP9AHIfADC0MteEJimkpN2BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T14:30:50.638021Z"},"content_sha256":"d30dc05eccdef1b39b1e1a0cdc952a035c17bdedc1fcec31b25ae4d0c28aeb7d","schema_version":"1.0","event_id":"sha256:d30dc05eccdef1b39b1e1a0cdc952a035c17bdedc1fcec31b25ae4d0c28aeb7d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TXXCJJQXX5RLSCTDCXA75YOJWK/bundle.json","state_url":"https://pith.science/pith/TXXCJJQXX5RLSCTDCXA75YOJWK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TXXCJJQXX5RLSCTDCXA75YOJWK/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":"2026-08-15T14:30:50Z","links":{"resolver":"https://pith.science/pith/TXXCJJQXX5RLSCTDCXA75YOJWK","bundle":"https://pith.science/pith/TXXCJJQXX5RLSCTDCXA75YOJWK/bundle.json","state":"https://pith.science/pith/TXXCJJQXX5RLSCTDCXA75YOJWK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TXXCJJQXX5RLSCTDCXA75YOJWK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TXXCJJQXX5RLSCTDCXA75YOJWK","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":"f0bb553b321842d63c71df3d8a69fe4694ab1bef6a7932f49bf17db3f16238dc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-01-23T09:54:36Z","title_canon_sha256":"30210795f696706e301c6cb6048487c89001cd1dc45f92778e96f803dd802053"},"schema_version":"1.0","source":{"id":"2401.12599","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.12599","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"arxiv_version","alias_value":"2401.12599v1","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12599","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"pith_short_12","alias_value":"TXXCJJQXX5RL","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"pith_short_16","alias_value":"TXXCJJQXX5RLSCTD","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"pith_short_8","alias_value":"TXXCJJQX","created_at":"2026-07-05T07:36:33Z"}],"graph_snapshots":[{"event_id":"sha256:d30dc05eccdef1b39b1e1a0cdc952a035c17bdedc1fcec31b25ae4d0c28aeb7d","target":"graph","created_at":"2026-07-05T07:36:33Z","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/2401.12599/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the rapid development of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) has become a predominant method in the field of professional knowledge-based question answering. Presently, major foundation model companies have opened up Embedding and Chat API interfaces, and frameworks like LangChain have already integrated the RAG process. It appears that the key models and steps in RAG have been resolved, leading to the question: are professional knowledge QA systems now approaching perfection? This article discovers that current primary methods depend on the premise of acces","authors_text":"Demiao Lin (chatdoc.com)","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-01-23T09:54:36Z","title":"Revolutionizing Retrieval-Augmented Generation with Enhanced PDF Structure Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12599","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:b7fb1f58e0a0b64967271e124f5e506aed606d3b746cd05ab61008e1b233f143","target":"record","created_at":"2026-07-05T07:36:33Z","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":"f0bb553b321842d63c71df3d8a69fe4694ab1bef6a7932f49bf17db3f16238dc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-01-23T09:54:36Z","title_canon_sha256":"30210795f696706e301c6cb6048487c89001cd1dc45f92778e96f803dd802053"},"schema_version":"1.0","source":{"id":"2401.12599","kind":"arxiv","version":1}},"canonical_sha256":"9dee24a617bf62b90a6315c1fee1c9b2a4585aee6df61aa5513ddda279000241","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9dee24a617bf62b90a6315c1fee1c9b2a4585aee6df61aa5513ddda279000241","first_computed_at":"2026-07-05T07:36:33.049475Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:36:33.049475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kNy2G29+45b0q6JN402orHFZeaGdDDbgTNVXoqj8Hve5iZ0Wd1J3SGrtZm/qf+cH1ydNh0PkZS9tnS9oloNACw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:36:33.049955Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.12599","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7fb1f58e0a0b64967271e124f5e506aed606d3b746cd05ab61008e1b233f143","sha256:d30dc05eccdef1b39b1e1a0cdc952a035c17bdedc1fcec31b25ae4d0c28aeb7d"],"state_sha256":"9528e248fb59ee3479e43554f0bc1280963f86f76152b20fcc3b451364138e11"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gczHTg+p1xUh+WY9mv0HIDn9dhwK8f5hJ9jbeGgu3dxbY/No1wKHpshQUSHHzeqo8BYXjYg8KRUA0WwB+Ub8Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T14:30:50.645630Z","bundle_sha256":"5c20616d960fcce952f120714036286351aaa0a4050540026382c051add005a5"}}