{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/hotpp-benchmark-are-we-good-at-the-long","title":"HoTPP Benchmark: Are We Good at the Long Horizon Events Forecasting?","arxiv_id":"2406.14341","date":"2024-06-20","proceeding":null,"authors":["Ivan Karpukhin","Foma Shipilov","Andrey Savchenko"],"abstract":"Accurately forecasting multiple future events within a given time horizon is crucial for finance, retail, social networks, and healthcare applications. Event timing and labels are typically modeled using Marked Temporal Point Processes (MTPP), with evaluations often focused on next-event prediction quality. While some studies have extended evaluations to a fixed number of future events, we demonstrate that this approach leads to inaccuracies in handling false positives and false negatives. To address these issues, we propose a novel evaluation method inspired by object detection techniques from computer vision. Specifically, we introduce Temporal mean Average Precision (T-mAP), a temporal variant of mAP, which overcomes the limitations of existing long-horizon evaluation metrics. Our extensive experiments demonstrate that models with strong next-event prediction accuracy can yield poor long-horizon forecasts and vice versa, indicating that specialized methods are needed for each task. To support further research, we release HoTPP, the first benchmark designed explicitly for evaluating long-horizon MTPP predictions. HoTPP includes large-scale datasets with up to 43 million events and provides optimized procedures for both autoregressive and parallel inference, paving the way for future advancements in the field.","url_abs":"https://arxiv.org/abs/2406.14341v2","url_pdf":"https://arxiv.org/pdf/2406.14341v2.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":"hotpp-benchmark-are-we-good-at-the-long","repo_url":"https://github.com/ivan-chai/hotpp-benchmark","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"hotpp-benchmark-are-we-good-at-the-long","repo_url":"https://github.com/ivan-chai/torch-linear-assignment","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"point-processes","task_name":"Point Processes"},{"task_slug":"time-series-forecasting","task_name":"Time Series Forecasting"}],"methods":[],"datasets_introduced":[{"slug":"agegroup-transactions-mtpp","name":"AgeGroup Transactions MTPP","full_name":"Marked Temporal Point Processes on financial transactions data"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/point-processes-on-agegroup-transactions-mtpp","task":"Point Processes","dataset":"AgeGroup Transactions MTPP","model":"RMTPP","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy (%)":"34.15","MAE":"0.749","OTD":"6.88","T-mAP":"6.69"},"uses_additional_data":false},{"leaderboard":"/sota/point-processes-on-agegroup-transactions-mtpp","task":"Point Processes","dataset":"AgeGroup Transactions MTPP","model":"IFTPP","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy (%)":"34.08","MAE":"0.693","OTD":"6.90","T-mAP":"5.88"},"uses_additional_data":false},{"leaderboard":"/sota/point-processes-on-agegroup-transactions-mtpp","task":"Point Processes","dataset":"AgeGroup Transactions MTPP","model":"NHP","rank_in_archive_order":4,"of":5,"metrics":{"Accuracy (%)":"35.43","MAE":"0.696","OTD":"6.97","T-mAP":"5.61"},"uses_additional_data":false},{"leaderboard":"/sota/point-processes-on-agegroup-transactions-mtpp","task":"Point Processes","dataset":"AgeGroup Transactions MTPP","model":"ODE-RNN","rank_in_archive_order":5,"of":5,"metrics":{"Accuracy (%)":"35.6","MAE":"0.695","OTD":"6.97","T-mAP":"5.52"},"uses_additional_data":false},{"leaderboard":"/sota/point-processes-on-amazon-mtpp","task":"Point Processes","dataset":"Amazon MTPP","model":"NHP","rank_in_archive_order":2,"of":4,"metrics":{"Accuracy (%)":"11.06","MAE":"0.449","OTD":"9.02","T-mAP":"26.29"},"uses_additional_data":false},{"leaderboard":"/sota/point-processes-on-amazon-mtpp","task":"Point Processes","dataset":"Amazon MTPP","model":"IFTPP","rank_in_archive_order":3,"of":4,"metrics":{"Accuracy (%)":"35.73","MAE":"0.242","OTD":"6.52","T-mAP":"22.56"},"uses_additional_data":false},{"leaderboard":"/sota/point-processes-on-amazon-mtpp","task":"Point Processes","dataset":"Amazon MTPP","model":"RMTPP","rank_in_archive_order":4,"of":4,"metrics":{"Accuracy (%)":"35.76","MAE":"0.294","OTD":"6.57","T-mAP":"20.06"},"uses_additional_data":false},{"leaderboard":"/sota/point-processes-on-retweet-mtpp","task":"Point Processes","dataset":"Retweet MTPP","model":"ODE-RNN","rank_in_archive_order":2,"of":6,"metrics":{"Accuracy (%)":"59.95","MAE":"18.38","OTD":"165.3","T-mAP":"48.81"},"uses_additional_data":false},{"leaderboard":"/sota/point-processes-on-retweet-mtpp","task":"Point Processes","dataset":"Retweet MTPP","model":"NHP","rank_in_archive_order":3,"of":6,"metrics":{"Accuracy (%)":"60.08","MAE":"18.42","OTD":"165.8","T-mAP":"45.07"},"uses_additional_data":false},{"leaderboard":"/sota/point-processes-on-retweet-mtpp","task":"Point Processes","dataset":"Retweet MTPP","model":"RMTPP","rank_in_archive_order":4,"of":6,"metrics":{"Accuracy (%)":"60.07","MAE":"18.45","OTD":"166.7","T-mAP":"44.74"},"uses_additional_data":false},{"leaderboard":"/sota/point-processes-on-retweet-mtpp","task":"Point Processes","dataset":"Retweet MTPP","model":"IFTPP","rank_in_archive_order":5,"of":6,"metrics":{"Accuracy (%)":"59.95","MAE":"18.27","OTD":"172.7","T-mAP":"31.75"},"uses_additional_data":false},{"leaderboard":"/sota/point-processes-on-retweet-mtpp","task":"Point Processes","dataset":"Retweet MTPP","model":"AttNHP","rank_in_archive_order":6,"of":6,"metrics":{"Accuracy (%)":"60.03","MAE":"18.39","OTD":"171.6","T-mAP":"25.85"},"uses_additional_data":false},{"leaderboard":"/sota/point-processes-on-stackoverflow-mtpp","task":"Point Processes","dataset":"StackOverflow MTPP","model":"RMTPP","rank_in_archive_order":2,"of":3,"metrics":{"Accuracy (%)":"45.43","MAE":"0.701","OTD":"13.17","T-mAP":"12.72"},"uses_additional_data":false},{"leaderboard":"/sota/point-processes-on-stackoverflow-mtpp","task":"Point Processes","dataset":"StackOverflow MTPP","model":"IFTPP","rank_in_archive_order":3,"of":3,"metrics":{"Accuracy (%)":"45.41","MAE":"0.641","OTD":"13.64","T-mAP":"8.31"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"ivan-chai/hotpp-benchmark","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2210.01753"],"harvested_for_calls":[{"arxiv_id":"2210.01753","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2210.01753"},"call":"get_harvested_code_for_paper(arxiv_id=\"2210.01753\")"}]},{"repo":"ivan-chai/torch-linear-assignment","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"91dd361cb9b72ff16857cf5cd25c8a8794f564e8ae74d4f0088b846e321e7b83","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}