{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2BC3SYA5ETSKI4LSZ263DGYKCY","short_pith_number":"pith:2BC3SYA5","schema_version":"1.0","canonical_sha256":"d045b9601d24e4a47172cebdb19b0a160a728233dea4a38356017026b71aef05","source":{"kind":"arxiv","id":"2408.04651","version":1},"attestation_state":"computed","paper":{"title":"Knowledge AI: Fine-tuning NLP Models for Facilitating Scientific Knowledge Extraction and Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Balaji Muralidharan, Hayden Beadles, Kalyan Sashank Mupparaju, Reza Marzban","submitted_at":"2024-08-04T01:32:09Z","abstract_excerpt":"This project investigates the efficacy of Large Language Models (LLMs) in understanding and extracting scientific knowledge across specific domains and to create a deep learning framework: Knowledge AI. As a part of this framework, we employ pre-trained models and fine-tune them on datasets in the scientific domain. The models are adapted for four key Natural Language Processing (NLP) tasks: summarization, text generation, question answering, and named entity recognition. Our results indicate that domain-specific fine-tuning significantly enhances model performance in each of these tasks, ther"},"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":"2408.04651","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-04T01:32:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c79888c3f391675b7ac74f328b66f212158484a13c05490bd8bf073cd103a9a2","abstract_canon_sha256":"7896f23d82b8b8981927ed8aea75ce948d9316b0cec4ec01f7ed3c3533397afb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:41.914352Z","signature_b64":"IdnEq47M3DV4UDk4o22n3L14r5rpOK6MotBrCM/vn0kNmPTb+Kqs2c+O8EdQO17vla3hsGq5s1KbfMk9WnJICA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d045b9601d24e4a47172cebdb19b0a160a728233dea4a38356017026b71aef05","last_reissued_at":"2026-07-05T08:53:41.913998Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:41.913998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge AI: Fine-tuning NLP Models for Facilitating Scientific Knowledge Extraction and Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Balaji Muralidharan, Hayden Beadles, Kalyan Sashank Mupparaju, Reza Marzban","submitted_at":"2024-08-04T01:32:09Z","abstract_excerpt":"This project investigates the efficacy of Large Language Models (LLMs) in understanding and extracting scientific knowledge across specific domains and to create a deep learning framework: Knowledge AI. As a part of this framework, we employ pre-trained models and fine-tune them on datasets in the scientific domain. The models are adapted for four key Natural Language Processing (NLP) tasks: summarization, text generation, question answering, and named entity recognition. Our results indicate that domain-specific fine-tuning significantly enhances model performance in each of these tasks, ther"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04651","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/2408.04651/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":"2408.04651","created_at":"2026-07-05T08:53:41.914054+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.04651v1","created_at":"2026-07-05T08:53:41.914054+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04651","created_at":"2026-07-05T08:53:41.914054+00:00"},{"alias_kind":"pith_short_12","alias_value":"2BC3SYA5ETSK","created_at":"2026-07-05T08:53:41.914054+00:00"},{"alias_kind":"pith_short_16","alias_value":"2BC3SYA5ETSKI4LS","created_at":"2026-07-05T08:53:41.914054+00:00"},{"alias_kind":"pith_short_8","alias_value":"2BC3SYA5","created_at":"2026-07-05T08:53:41.914054+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.24663","citing_title":"A corrective agentic hybrid RAG and an operations-grounded evaluation for a scientific facility","ref_index":74,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2BC3SYA5ETSKI4LSZ263DGYKCY","json":"https://pith.science/pith/2BC3SYA5ETSKI4LSZ263DGYKCY.json","graph_json":"https://pith.science/api/pith-number/2BC3SYA5ETSKI4LSZ263DGYKCY/graph.json","events_json":"https://pith.science/api/pith-number/2BC3SYA5ETSKI4LSZ263DGYKCY/events.json","paper":"https://pith.science/paper/2BC3SYA5"},"agent_actions":{"view_html":"https://pith.science/pith/2BC3SYA5ETSKI4LSZ263DGYKCY","download_json":"https://pith.science/pith/2BC3SYA5ETSKI4LSZ263DGYKCY.json","view_paper":"https://pith.science/paper/2BC3SYA5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.04651&json=true","fetch_graph":"https://pith.science/api/pith-number/2BC3SYA5ETSKI4LSZ263DGYKCY/graph.json","fetch_events":"https://pith.science/api/pith-number/2BC3SYA5ETSKI4LSZ263DGYKCY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2BC3SYA5ETSKI4LSZ263DGYKCY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2BC3SYA5ETSKI4LSZ263DGYKCY/action/storage_attestation","attest_author":"https://pith.science/pith/2BC3SYA5ETSKI4LSZ263DGYKCY/action/author_attestation","sign_citation":"https://pith.science/pith/2BC3SYA5ETSKI4LSZ263DGYKCY/action/citation_signature","submit_replication":"https://pith.science/pith/2BC3SYA5ETSKI4LSZ263DGYKCY/action/replication_record"}},"created_at":"2026-07-05T08:53:41.914054+00:00","updated_at":"2026-07-05T08:53:41.914054+00:00"}