{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/event-stream-gpt-a-data-pre-processing-and-1","title":"Event Stream GPT: A Data Pre-processing and Modeling Library for Generative, Pre-trained Transformers over Continuous-time Sequences of Complex Events","arxiv_id":"2306.11547","date":"2023-06-20","proceeding":"NeurIPS 2023 11","authors":["Matthew B. A. McDermott","Bret Nestor","Peniel Argaw","Isaac Kohane"],"abstract":"Generative, pre-trained transformers (GPTs, a.k.a. \"Foundation Models\") have reshaped natural language processing (NLP) through their versatility in diverse downstream tasks. However, their potential extends far beyond NLP. This paper provides a software utility to help realize this potential, extending the applicability of GPTs to continuous-time sequences of complex events with internal dependencies, such as medical record datasets. Despite their potential, the adoption of foundation models in these domains has been hampered by the lack of suitable tools for model construction and evaluation. To bridge this gap, we introduce Event Stream GPT (ESGPT), an open-source library designed to streamline the end-to-end process for building GPTs for continuous-time event sequences. ESGPT allows users to (1) build flexible, foundation-model scale input datasets by specifying only a minimal configuration file, (2) leverage a Hugging Face compatible modeling API for GPTs over this modality that incorporates intra-event causal dependency structures and autoregressive generation capabilities, and (3) evaluate models via standardized processes that can assess few and even zero-shot performance of pre-trained models on user-specified fine-tuning tasks.","url_abs":"https://arxiv.org/abs/2306.11547v2","url_pdf":"https://arxiv.org/pdf/2306.11547v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"event-stream-gpt-a-data-pre-processing-and-1","repo_url":"https://github.com/mmcdermott/eventstreamgpt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"discriminative-fine-tuning","method_name":"Discriminative Fine-Tuning"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt","method_name":"GPT"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":null,"method_name":"Library"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.11547","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.11547"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mmcdermott/eventstreamgpt","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":10},"by_repo_kind":{"official":{"samples":10,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"c1580a72ecff9f11","entry":"count_or_proportion","repo":"mmcdermott/eventstreamgpt","repo_kind":"official","path":"EventStream/utils.py","file_url":"https://github.com/mmcdermott/eventstreamgpt/blob/HEAD/EventStream/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c1580a72ecff9f11"}},{"code_sha256_prefix":"1fc0b4b21ed6a018","entry":"crps","repo":"mmcdermott/eventstreamgpt","repo_kind":"official","path":"EventStream/evaluation/MCF_evaluation.py","file_url":"https://github.com/mmcdermott/eventstreamgpt/blob/HEAD/EventStream/evaluation/MCF_evaluation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1fc0b4b21ed6a018"}},{"code_sha256_prefix":"73c443ce93317d4e","entry":"eval_multi_class_classification","repo":"mmcdermott/eventstreamgpt","repo_kind":"official","path":"EventStream/baseline/FT_task_baseline.py","file_url":"https://github.com/mmcdermott/eventstreamgpt/blob/HEAD/EventStream/baseline/FT_task_baseline.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"73c443ce93317d4e"}},{"code_sha256_prefix":"5558bb57ff0bcafd","entry":"get_MCF","repo":"mmcdermott/eventstreamgpt","repo_kind":"official","path":"EventStream/evaluation/MCF_evaluation.py","file_url":"https://github.com/mmcdermott/eventstreamgpt/blob/HEAD/EventStream/evaluation/MCF_evaluation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5558bb57ff0bcafd"}},{"code_sha256_prefix":"17ad3912a0d506c2","entry":"get_aligned_timestamps","repo":"mmcdermott/eventstreamgpt","repo_kind":"official","path":"EventStream/evaluation/MCF_evaluation.py","file_url":"https://github.com/mmcdermott/eventstreamgpt/blob/HEAD/EventStream/evaluation/MCF_evaluation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"17ad3912a0d506c2"}},{"code_sha256_prefix":"faf0c133b032fec1","entry":"get_event_types","repo":"mmcdermott/eventstreamgpt","repo_kind":"official","path":"EventStream/transformer/model_output.py","file_url":"https://github.com/mmcdermott/eventstreamgpt/blob/HEAD/EventStream/transformer/model_output.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"faf0c133b032fec1"}},{"code_sha256_prefix":"4fdfe155a398fe7e","entry":"lt_count_or_proportion","repo":"mmcdermott/eventstreamgpt","repo_kind":"official","path":"EventStream/utils.py","file_url":"https://github.com/mmcdermott/eventstreamgpt/blob/HEAD/EventStream/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4fdfe155a398fe7e"}},{"code_sha256_prefix":"5df168a026d63743","entry":"num_initial_spaces","repo":"mmcdermott/eventstreamgpt","repo_kind":"official","path":"EventStream/utils.py","file_url":"https://github.com/mmcdermott/eventstreamgpt/blob/HEAD/EventStream/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5df168a026d63743"}},{"code_sha256_prefix":"c75824103a48d8b0","entry":"registered_sklearn_config","repo":"mmcdermott/eventstreamgpt","repo_kind":"official","path":"EventStream/baseline/FT_task_baseline.py","file_url":"https://github.com/mmcdermott/eventstreamgpt/blob/HEAD/EventStream/baseline/FT_task_baseline.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c75824103a48d8b0"}},{"code_sha256_prefix":"0a1ecbeeead5c732","entry":"strip_unused_indices","repo":"mmcdermott/eventstreamgpt","repo_kind":"official","path":"EventStream/transformer/model_output.py","file_url":"https://github.com/mmcdermott/eventstreamgpt/blob/HEAD/EventStream/transformer/model_output.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0a1ecbeeead5c732"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}