{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GY6O7ENRKCNFGJSU5YJUTE3SQF","short_pith_number":"pith:GY6O7ENR","schema_version":"1.0","canonical_sha256":"363cef91b1509a532654ee1349937281615295977bb2594ea2b80ebafd96c4bf","source":{"kind":"arxiv","id":"2504.04569","version":2},"attestation_state":"computed","paper":{"title":"KnowsLM: A framework for evaluation of small language models for knowledge augmentation and humanised conversations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anupam Purwar, Chitranshu Harbola","submitted_at":"2025-04-06T17:58:08Z","abstract_excerpt":"In the evolving landscape of conversational AI, generating concise, context-aware, and human-like dialogue using small and medium-sized language models (LLMs) remains a complex challenge. This study investigates the influence of LoRA rank, dataset scale, and prompt prefix design on both knowledge retention and stylistic alignment. While fine-tuning improves fluency and enables stylistic customization, its ability to integrate unseen knowledge is constrained -- particularly with smaller datasets. Conversely, RAG-augmented models, equipped to incorporate external documents at inference, demonstr"},"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":"2504.04569","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-06T17:58:08Z","cross_cats_sorted":[],"title_canon_sha256":"9229a78cd075a68539f60aa6a8914f9867e66376d738f9337432005890b02cd0","abstract_canon_sha256":"6b2aa2585722a082a2bacc9e2c8448d33092f2564bcd5d2c9b25891224d4a240"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:30.079091Z","signature_b64":"c5yVbaQMUnXscpqr39frRbfHB0rcs6YOUJx4YtZWR2VBHO4fRuOnFqYqDq/CzNG7PmQON7GmleqAW4Jk3A7pDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"363cef91b1509a532654ee1349937281615295977bb2594ea2b80ebafd96c4bf","last_reissued_at":"2026-07-05T10:48:30.078486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:30.078486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KnowsLM: A framework for evaluation of small language models for knowledge augmentation and humanised conversations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anupam Purwar, Chitranshu Harbola","submitted_at":"2025-04-06T17:58:08Z","abstract_excerpt":"In the evolving landscape of conversational AI, generating concise, context-aware, and human-like dialogue using small and medium-sized language models (LLMs) remains a complex challenge. This study investigates the influence of LoRA rank, dataset scale, and prompt prefix design on both knowledge retention and stylistic alignment. While fine-tuning improves fluency and enables stylistic customization, its ability to integrate unseen knowledge is constrained -- particularly with smaller datasets. Conversely, RAG-augmented models, equipped to incorporate external documents at inference, demonstr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04569","kind":"arxiv","version":2},"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/2504.04569/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":"2504.04569","created_at":"2026-07-05T10:48:30.078575+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.04569v2","created_at":"2026-07-05T10:48:30.078575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04569","created_at":"2026-07-05T10:48:30.078575+00:00"},{"alias_kind":"pith_short_12","alias_value":"GY6O7ENRKCNF","created_at":"2026-07-05T10:48:30.078575+00:00"},{"alias_kind":"pith_short_16","alias_value":"GY6O7ENRKCNFGJSU","created_at":"2026-07-05T10:48:30.078575+00:00"},{"alias_kind":"pith_short_8","alias_value":"GY6O7ENR","created_at":"2026-07-05T10:48:30.078575+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.03615","citing_title":"E-ARMOR: Edge case Assessment and Review of Multilingual Optical Character Recognition","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GY6O7ENRKCNFGJSU5YJUTE3SQF","json":"https://pith.science/pith/GY6O7ENRKCNFGJSU5YJUTE3SQF.json","graph_json":"https://pith.science/api/pith-number/GY6O7ENRKCNFGJSU5YJUTE3SQF/graph.json","events_json":"https://pith.science/api/pith-number/GY6O7ENRKCNFGJSU5YJUTE3SQF/events.json","paper":"https://pith.science/paper/GY6O7ENR"},"agent_actions":{"view_html":"https://pith.science/pith/GY6O7ENRKCNFGJSU5YJUTE3SQF","download_json":"https://pith.science/pith/GY6O7ENRKCNFGJSU5YJUTE3SQF.json","view_paper":"https://pith.science/paper/GY6O7ENR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.04569&json=true","fetch_graph":"https://pith.science/api/pith-number/GY6O7ENRKCNFGJSU5YJUTE3SQF/graph.json","fetch_events":"https://pith.science/api/pith-number/GY6O7ENRKCNFGJSU5YJUTE3SQF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GY6O7ENRKCNFGJSU5YJUTE3SQF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GY6O7ENRKCNFGJSU5YJUTE3SQF/action/storage_attestation","attest_author":"https://pith.science/pith/GY6O7ENRKCNFGJSU5YJUTE3SQF/action/author_attestation","sign_citation":"https://pith.science/pith/GY6O7ENRKCNFGJSU5YJUTE3SQF/action/citation_signature","submit_replication":"https://pith.science/pith/GY6O7ENRKCNFGJSU5YJUTE3SQF/action/replication_record"}},"created_at":"2026-07-05T10:48:30.078575+00:00","updated_at":"2026-07-05T10:48:30.078575+00:00"}