{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JVF5XXJW3A76VXH2NULT6INMAS","short_pith_number":"pith:JVF5XXJW","schema_version":"1.0","canonical_sha256":"4d4bdbdd36d83feadcfa6d173f21ac049ae1772e2d532d8d5508ba0ce9836670","source":{"kind":"arxiv","id":"2307.06435","version":10},"attestation_state":"computed","paper":{"title":"A Comprehensive Overview of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ajmal Mian, Asad Ullah Khan, Humza Naveed, Muhammad Saqib, Muhammad Usman, Naveed Akhtar, Nick Barnes, Saeed Anwar, Shi Qiu","submitted_at":"2023-07-12T20:01:52Z","abstract_excerpt":"Large Language Models (LLMs) have recently demonstrated remarkable capabilities in natural language processing tasks and beyond. This success of LLMs has led to a large influx of research contributions in this direction. These works encompass diverse topics such as architectural innovations, better training strategies, context length improvements, fine-tuning, multi-modal LLMs, robotics, datasets, benchmarking, efficiency, and more. With the rapid development of techniques and regular breakthroughs in LLM research, it has become considerably challenging to perceive the bigger picture of the ad"},"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":"2307.06435","kind":"arxiv","version":10},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-12T20:01:52Z","cross_cats_sorted":[],"title_canon_sha256":"a929805a8d206b3bb017663af7f174fd25e53860e02d9c0d649b89425e29bb08","abstract_canon_sha256":"4ec43e1d2602fa789ae1d2b9c30090c438e140099b41e7b9790a0fa03b6abfc4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-19T20:22:35.217417Z","signature_b64":"zSCvxH/lNfgZZOus5cVKRnI3QIh3y7Hz5nLzL+RZHmHfrxuji/la+Beaiaj6geL0BUpPngSPgPV+ezx+g0JbCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d4bdbdd36d83feadcfa6d173f21ac049ae1772e2d532d8d5508ba0ce9836670","last_reissued_at":"2026-05-19T20:22:35.215142Z","signature_status":"signed_v1","first_computed_at":"2026-05-19T20:22:35.215142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comprehensive Overview of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ajmal Mian, Asad Ullah Khan, Humza Naveed, Muhammad Saqib, Muhammad Usman, Naveed Akhtar, Nick Barnes, Saeed Anwar, Shi Qiu","submitted_at":"2023-07-12T20:01:52Z","abstract_excerpt":"Large Language Models (LLMs) have recently demonstrated remarkable capabilities in natural language processing tasks and beyond. This success of LLMs has led to a large influx of research contributions in this direction. These works encompass diverse topics such as architectural innovations, better training strategies, context length improvements, fine-tuning, multi-modal LLMs, robotics, datasets, benchmarking, efficiency, and more. With the rapid development of techniques and regular breakthroughs in LLM research, it has become considerably challenging to perceive the bigger picture of the ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06435","kind":"arxiv","version":10},"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/2307.06435/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":"2307.06435","created_at":"2026-05-19T20:22:35.215257+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.06435v10","created_at":"2026-05-19T20:22:35.215257+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06435","created_at":"2026-05-19T20:22:35.215257+00:00"},{"alias_kind":"pith_short_12","alias_value":"JVF5XXJW3A76","created_at":"2026-05-19T20:22:35.215257+00:00"},{"alias_kind":"pith_short_16","alias_value":"JVF5XXJW3A76VXH2","created_at":"2026-05-19T20:22:35.215257+00:00"},{"alias_kind":"pith_short_8","alias_value":"JVF5XXJW","created_at":"2026-05-19T20:22:35.215257+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":29,"internal_anchor_count":29,"sample":[{"citing_arxiv_id":"2409.12059","citing_title":"MeTHanol: Modularized Thinking Language Models with Intermediate Layer Thinking, Decoding and Bootstrapping Reasoning","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2409.11022","citing_title":"DynamicNER: A Dynamic, Multilingual, and Fine-Grained Dataset for LLM-based Named Entity Recognition","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2412.19363","citing_title":"Large Language Models for Market Research: A Data-augmentation Approach","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2501.05465","citing_title":"Small Language Models (SLMs) Can Still Pack a Punch: A survey (updated 2026)","ref_index":96,"is_internal_anchor":true},{"citing_arxiv_id":"2502.03814","citing_title":"Large Language Models for Multi-Robot Systems: A Survey","ref_index":89,"is_internal_anchor":true},{"citing_arxiv_id":"2503.16549","citing_title":"MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2503.17181","citing_title":"A Study of LLMs' Preferences for Libraries and Programming Languages","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"2505.15323","citing_title":"Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Output Prefilling","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2505.16120","citing_title":"LLM-Powered AI Agent Systems and Their Applications in Industry","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2412.14171","citing_title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16972","citing_title":"WhiteTesseract: Reframing the Interpretation of Cultural Heritage through XR and Conversational AI","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2505.20279","citing_title":"VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2510.09093","citing_title":"Exploiting Web Search Tools of AI Agents for Data Exfiltration","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2601.02627","citing_title":"Improved Evidence Extraction and Metrics for Document Inconsistency Detection with LLMs","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2506.02153","citing_title":"Small Language Models are the Future of Agentic AI","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02346","citing_title":"DrugPlayGround: Benchmarking Large Language Models and Embeddings for Drug Discovery","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26328","citing_title":"DSIPA: Detecting LLM-Generated Texts via Sentiment-Invariant Patterns Divergence Analysis","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10622","citing_title":"Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22193","citing_title":"How Large Language Models Balance Internal Knowledge with User and Document Assertions","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05424","citing_title":"Evaluating the Reliability of Multiple Large Language Models in Risk Assessment: A CIS Controls Based Approach","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21700","citing_title":"Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggers","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20273","citing_title":"ActuBench: A Multi-Agent LLM Pipeline for Generation and Evaluation of Actuarial Reasoning Tasks","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19508","citing_title":"Bangla Key2Text: Text Generation from Keywords for a Low Resource Language","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18200","citing_title":"Multi-LLM Token Filtering and Routing for Sequential Recommendation","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JVF5XXJW3A76VXH2NULT6INMAS","json":"https://pith.science/pith/JVF5XXJW3A76VXH2NULT6INMAS.json","graph_json":"https://pith.science/api/pith-number/JVF5XXJW3A76VXH2NULT6INMAS/graph.json","events_json":"https://pith.science/api/pith-number/JVF5XXJW3A76VXH2NULT6INMAS/events.json","paper":"https://pith.science/paper/JVF5XXJW"},"agent_actions":{"view_html":"https://pith.science/pith/JVF5XXJW3A76VXH2NULT6INMAS","download_json":"https://pith.science/pith/JVF5XXJW3A76VXH2NULT6INMAS.json","view_paper":"https://pith.science/paper/JVF5XXJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.06435&json=true","fetch_graph":"https://pith.science/api/pith-number/JVF5XXJW3A76VXH2NULT6INMAS/graph.json","fetch_events":"https://pith.science/api/pith-number/JVF5XXJW3A76VXH2NULT6INMAS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JVF5XXJW3A76VXH2NULT6INMAS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JVF5XXJW3A76VXH2NULT6INMAS/action/storage_attestation","attest_author":"https://pith.science/pith/JVF5XXJW3A76VXH2NULT6INMAS/action/author_attestation","sign_citation":"https://pith.science/pith/JVF5XXJW3A76VXH2NULT6INMAS/action/citation_signature","submit_replication":"https://pith.science/pith/JVF5XXJW3A76VXH2NULT6INMAS/action/replication_record"}},"created_at":"2026-05-19T20:22:35.215257+00:00","updated_at":"2026-05-19T20:22:35.215257+00:00"}