{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CK5ORTCTWFKGFYJMN4JTJ3HTVV","short_pith_number":"pith:CK5ORTCT","schema_version":"1.0","canonical_sha256":"12bae8cc53b15462e12c6f1334ecf3ad4c6b58da5c66b1dd84024517ecd6654d","source":{"kind":"arxiv","id":"2408.04023","version":1},"attestation_state":"computed","paper":{"title":"Improving Large Language Model (LLM) fidelity through context-aware grounding: A systematic approach to reliability and veracity","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anjanava Biswas, Wrick Talukdar","submitted_at":"2024-08-07T18:12:02Z","abstract_excerpt":"As Large Language Models (LLMs) become increasingly sophisticated and ubiquitous in natural language processing (NLP) applications, ensuring their robustness, trustworthiness, and alignment with human values has become a critical challenge. This paper presents a novel framework for contextual grounding in textual models, with a particular emphasis on the Context Representation stage. Our approach aims to enhance the reliability and ethical alignment of these models through a comprehensive, context-aware methodology. By explicitly capturing and representing relevant situational, cultural, and e"},"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":"2408.04023","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-07T18:12:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"360f0715dec8844f0c30420fc989976d37cff8524fc42433d4e96c2d79b42de2","abstract_canon_sha256":"6acc52edb97da230375405b8eb7ba01f0b615c6e7456626afdb19a9fec3beab8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:26.825933Z","signature_b64":"rPpXm1v2m1DUuvOsVJMoEfXwZ1iV0kxmX1KEK1RsFBWvzMjyfiIMvQXSvejBj64CJKefq9lmIF/a+iG0Apr0CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12bae8cc53b15462e12c6f1334ecf3ad4c6b58da5c66b1dd84024517ecd6654d","last_reissued_at":"2026-07-05T08:53:26.825450Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:26.825450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Large Language Model (LLM) fidelity through context-aware grounding: A systematic approach to reliability and veracity","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anjanava Biswas, Wrick Talukdar","submitted_at":"2024-08-07T18:12:02Z","abstract_excerpt":"As Large Language Models (LLMs) become increasingly sophisticated and ubiquitous in natural language processing (NLP) applications, ensuring their robustness, trustworthiness, and alignment with human values has become a critical challenge. This paper presents a novel framework for contextual grounding in textual models, with a particular emphasis on the Context Representation stage. Our approach aims to enhance the reliability and ethical alignment of these models through a comprehensive, context-aware methodology. By explicitly capturing and representing relevant situational, cultural, and e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04023","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/2408.04023/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":"2408.04023","created_at":"2026-07-05T08:53:26.825512+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.04023v1","created_at":"2026-07-05T08:53:26.825512+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04023","created_at":"2026-07-05T08:53:26.825512+00:00"},{"alias_kind":"pith_short_12","alias_value":"CK5ORTCTWFKG","created_at":"2026-07-05T08:53:26.825512+00:00"},{"alias_kind":"pith_short_16","alias_value":"CK5ORTCTWFKGFYJM","created_at":"2026-07-05T08:53:26.825512+00:00"},{"alias_kind":"pith_short_8","alias_value":"CK5ORTCT","created_at":"2026-07-05T08:53:26.825512+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.13256","citing_title":"Bypassing Array Canaries via Autonomous Function Call Resolution","ref_index":59,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CK5ORTCTWFKGFYJMN4JTJ3HTVV","json":"https://pith.science/pith/CK5ORTCTWFKGFYJMN4JTJ3HTVV.json","graph_json":"https://pith.science/api/pith-number/CK5ORTCTWFKGFYJMN4JTJ3HTVV/graph.json","events_json":"https://pith.science/api/pith-number/CK5ORTCTWFKGFYJMN4JTJ3HTVV/events.json","paper":"https://pith.science/paper/CK5ORTCT"},"agent_actions":{"view_html":"https://pith.science/pith/CK5ORTCTWFKGFYJMN4JTJ3HTVV","download_json":"https://pith.science/pith/CK5ORTCTWFKGFYJMN4JTJ3HTVV.json","view_paper":"https://pith.science/paper/CK5ORTCT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.04023&json=true","fetch_graph":"https://pith.science/api/pith-number/CK5ORTCTWFKGFYJMN4JTJ3HTVV/graph.json","fetch_events":"https://pith.science/api/pith-number/CK5ORTCTWFKGFYJMN4JTJ3HTVV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CK5ORTCTWFKGFYJMN4JTJ3HTVV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CK5ORTCTWFKGFYJMN4JTJ3HTVV/action/storage_attestation","attest_author":"https://pith.science/pith/CK5ORTCTWFKGFYJMN4JTJ3HTVV/action/author_attestation","sign_citation":"https://pith.science/pith/CK5ORTCTWFKGFYJMN4JTJ3HTVV/action/citation_signature","submit_replication":"https://pith.science/pith/CK5ORTCTWFKGFYJMN4JTJ3HTVV/action/replication_record"}},"created_at":"2026-07-05T08:53:26.825512+00:00","updated_at":"2026-07-05T08:53:26.825512+00:00"}