{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HFAIHWT7DFOC6T232NTOFCDEXU","short_pith_number":"pith:HFAIHWT7","schema_version":"1.0","canonical_sha256":"394083da7f195c2f4f5bd366e28864bd2578909c92b092da14e76334abf43a07","source":{"kind":"arxiv","id":"2507.15863","version":1},"attestation_state":"computed","paper":{"title":"eSapiens's DEREK Module: Deep Extraction & Reasoning Engine for Knowledge with LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fan Liu, Isaac Shi, Lewei He, Tianyu Shi, Wenli Wang, Yang Yang, Zeyuan Li","submitted_at":"2025-07-13T05:54:01Z","abstract_excerpt":"We present the DEREK (Deep Extraction & Reasoning Engine for Knowledge) Module, a secure and scalable Retrieval-Augmented Generation pipeline designed specifically for enterprise document question answering. Designed and implemented by eSapiens, the system ingests heterogeneous content (PDF, Office, web), splits it into 1,000-token overlapping chunks, and indexes them in a hybrid HNSW+BM25 store. User queries are refined by GPT-4o, retrieved via combined vector+BM25 search, reranked with Cohere, and answered by an LLM using CO-STAR prompt engineering. A LangGraph verifier enforces citation ove"},"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":"2507.15863","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-13T05:54:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5c1bfeac91accc7bdc24987bb53c389e39ec0c74fd21b9a872ba831a88f1f124","abstract_canon_sha256":"e3c7b902afcfaca4d2f551e5952438feebcdfdd9029df5a733e4c8b95b8fbe95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:58.240888Z","signature_b64":"hBaMvpRFZ776eWmVz80kow+r5u15+wqxgJA0leth7jb5UntrGl6zixtx2wTOTMBQ7lp0ikiHpKMQL9mgsLIqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"394083da7f195c2f4f5bd366e28864bd2578909c92b092da14e76334abf43a07","last_reissued_at":"2026-07-05T11:40:58.240415Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:58.240415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"eSapiens's DEREK Module: Deep Extraction & Reasoning Engine for Knowledge with LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fan Liu, Isaac Shi, Lewei He, Tianyu Shi, Wenli Wang, Yang Yang, Zeyuan Li","submitted_at":"2025-07-13T05:54:01Z","abstract_excerpt":"We present the DEREK (Deep Extraction & Reasoning Engine for Knowledge) Module, a secure and scalable Retrieval-Augmented Generation pipeline designed specifically for enterprise document question answering. Designed and implemented by eSapiens, the system ingests heterogeneous content (PDF, Office, web), splits it into 1,000-token overlapping chunks, and indexes them in a hybrid HNSW+BM25 store. User queries are refined by GPT-4o, retrieved via combined vector+BM25 search, reranked with Cohere, and answered by an LLM using CO-STAR prompt engineering. A LangGraph verifier enforces citation ove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15863","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/2507.15863/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":"2507.15863","created_at":"2026-07-05T11:40:58.240476+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.15863v1","created_at":"2026-07-05T11:40:58.240476+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15863","created_at":"2026-07-05T11:40:58.240476+00:00"},{"alias_kind":"pith_short_12","alias_value":"HFAIHWT7DFOC","created_at":"2026-07-05T11:40:58.240476+00:00"},{"alias_kind":"pith_short_16","alias_value":"HFAIHWT7DFOC6T23","created_at":"2026-07-05T11:40:58.240476+00:00"},{"alias_kind":"pith_short_8","alias_value":"HFAIHWT7","created_at":"2026-07-05T11:40:58.240476+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/HFAIHWT7DFOC6T232NTOFCDEXU","json":"https://pith.science/pith/HFAIHWT7DFOC6T232NTOFCDEXU.json","graph_json":"https://pith.science/api/pith-number/HFAIHWT7DFOC6T232NTOFCDEXU/graph.json","events_json":"https://pith.science/api/pith-number/HFAIHWT7DFOC6T232NTOFCDEXU/events.json","paper":"https://pith.science/paper/HFAIHWT7"},"agent_actions":{"view_html":"https://pith.science/pith/HFAIHWT7DFOC6T232NTOFCDEXU","download_json":"https://pith.science/pith/HFAIHWT7DFOC6T232NTOFCDEXU.json","view_paper":"https://pith.science/paper/HFAIHWT7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.15863&json=true","fetch_graph":"https://pith.science/api/pith-number/HFAIHWT7DFOC6T232NTOFCDEXU/graph.json","fetch_events":"https://pith.science/api/pith-number/HFAIHWT7DFOC6T232NTOFCDEXU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HFAIHWT7DFOC6T232NTOFCDEXU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HFAIHWT7DFOC6T232NTOFCDEXU/action/storage_attestation","attest_author":"https://pith.science/pith/HFAIHWT7DFOC6T232NTOFCDEXU/action/author_attestation","sign_citation":"https://pith.science/pith/HFAIHWT7DFOC6T232NTOFCDEXU/action/citation_signature","submit_replication":"https://pith.science/pith/HFAIHWT7DFOC6T232NTOFCDEXU/action/replication_record"}},"created_at":"2026-07-05T11:40:58.240476+00:00","updated_at":"2026-07-05T11:40:58.240476+00:00"}