{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:APRNZNKOKPDRIB5JEZ4TLCL3CY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e09f11e9719702522e093aa0c34559ff5de51b203b7a999394575533e8171ebf","cross_cats_sorted":["stat.CO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2026-05-13T11:53:57Z","title_canon_sha256":"6d785c1426a11ec842ba2709c6176cd083ea7aec096088f57d1adbfd1a3cefe4"},"schema_version":"1.0","source":{"id":"2605.13397","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13397","created_at":"2026-05-18T02:44:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13397v1","created_at":"2026-05-18T02:44:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13397","created_at":"2026-05-18T02:44:47Z"},{"alias_kind":"pith_short_12","alias_value":"APRNZNKOKPDR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"APRNZNKOKPDRIB5J","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"APRNZNKO","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:e7896a5544310ab9b029f064154ff051e069cc05c3be2c1b5dc56208febe0f8d","target":"graph","created_at":"2026-05-18T02:44:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"The proposed estimators are generic building blocks for subsampling-based inference and can be embedded within frameworks including stochastic optimisation, variational Bayes, and Markov chain Monte Carlo. Applications to conditional volatility models, including standard and threshold generalised autoregressive conditional heteroskedasticity models, demonstrate substantial computational speed-ups while maintaining inferential accuracy."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That a stabilisation framework exists which restricts sampling-probability decay to simultaneously avoid both high estimator variance and high computational cost, and that this can be achieved through principled hyperparameter tuning without introducing bias."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Stabilised weighted subsampling yields an unbiased log-likelihood estimator for recursive models that reduces recursion depth and computational cost while avoiding variance inflation via principled decay restrictions."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Stabilised weighted subsampling yields unbiased log-likelihood estimates for faster inference in recursive models."}],"snapshot_sha256":"3364b4fdde197226d7eeafdbc0587d6006a4b21d1627660cbbc330eff8afbdf5"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ad72f28e6095bdf2c6943fe50d078557be5300ec3c1fcd5f69a4dffd45fec326"},"paper":{"abstract_excerpt":"Inference for models with recursively defined likelihoods is computationally demanding, limiting scalability to large datasets. We propose a stabilised weighted subsampling methodology for accelerated inference based on an unbiased estimator of the log-likelihood. By assigning higher sampling probabilities to early observations, the method reduces the effective depth of recursive likelihood evaluations and hence expected computational cost. However, slow decay leads to frequent inclusion of late observations and high computational cost, while overly aggressive decay can substantially inflate e","authors_text":"Aishwarya Bhaskaran, Matias Quiroz, Thomas Goodwin, Zixuan Wang","cross_cats":["stat.CO"],"headline":"Stabilised weighted subsampling yields unbiased log-likelihood estimates for faster inference in recursive models.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2026-05-13T11:53:57Z","title":"Stabilised weighted data subsampling for accelerated inference in models with recursive likelihoods"},"references":{"count":64,"internal_anchors":1,"resolved_work":64,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Ai, M., Yu, J., Zhang, H., and Wang, H. (2021). Optimal subsampling algorithms for big data regressions. Statistica Sinica , 31(2):749--772","work_id":"b35444ad-ca41-4053-aa38-3a07cd8d5ab0","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Aicher, C., Putcha, S., Nemeth, C., Fearnhead, P., and Fox, E. (2025). Stochastic gradient MCMC for nonlinear state space models. Bayesian Analysis , 20(1):83 -- 105","work_id":"81091ccc-4f55-4797-a37c-c44c5de35f91","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Amari, S.-i. (1998). Natural gradient works efficiently in learning. Neural Computation , 10(2):251--276","work_id":"f0b6c8a3-408e-4b2f-9906-4a4413a5a4de","year":1998},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Bardenet, R., Doucet, A., and Holmes, C. (2014). Towards scaling up M arkov chain M onte C arlo: A n adaptive subsampling approach. Proceedings of the 31st International Conference on Machine Learning","work_id":"9b58fc49-7bf1-4385-8bb2-87bb0ba6d686","year":2014},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Bardenet, R., Doucet, A., and Holmes, C. (2017). On M arkov chain M onte C arlo methods for tall data. Journal of Machine Learning Research , 18(47):1--43","work_id":"ff891eb3-a2d4-4e3c-86f0-0b97fe87c03e","year":2017}],"snapshot_sha256":"60ffae24fc6f8890f1ae75cf18fa725023aad96e79e23cc4bc7ddcc2f04d288a"},"source":{"id":"2605.13397","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T17:57:21.911396Z","id":"03d94445-a1a9-4d1c-bd2c-aa68a3b4e57a","model_set":{"reader":"grok-4.3"},"one_line_summary":"Stabilised weighted subsampling yields an unbiased log-likelihood estimator for recursive models that reduces recursion depth and computational cost while avoiding variance inflation via principled decay restrictions.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Stabilised weighted subsampling yields unbiased log-likelihood estimates for faster inference in recursive models.","strongest_claim":"The proposed estimators are generic building blocks for subsampling-based inference and can be embedded within frameworks including stochastic optimisation, variational Bayes, and Markov chain Monte Carlo. Applications to conditional volatility models, including standard and threshold generalised autoregressive conditional heteroskedasticity models, demonstrate substantial computational speed-ups while maintaining inferential accuracy.","weakest_assumption":"That a stabilisation framework exists which restricts sampling-probability decay to simultaneously avoid both high estimator variance and high computational cost, and that this can be achieved through principled hyperparameter tuning without introducing bias."}},"verdict_id":"03d94445-a1a9-4d1c-bd2c-aa68a3b4e57a"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bb1d4383c710dba59b351e37e505def64f041b90fcc2e21d0fae6b2f61cc33fc","target":"record","created_at":"2026-05-18T02:44:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e09f11e9719702522e093aa0c34559ff5de51b203b7a999394575533e8171ebf","cross_cats_sorted":["stat.CO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2026-05-13T11:53:57Z","title_canon_sha256":"6d785c1426a11ec842ba2709c6176cd083ea7aec096088f57d1adbfd1a3cefe4"},"schema_version":"1.0","source":{"id":"2605.13397","kind":"arxiv","version":1}},"canonical_sha256":"03e2dcb54e53c71407a9267935897b162e62c0fc611667a4122c999a550cea4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03e2dcb54e53c71407a9267935897b162e62c0fc611667a4122c999a550cea4f","first_computed_at":"2026-05-18T02:44:47.630996Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:47.630996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wURbt3ZFAQTcX0bAHV2TfIKp+dI8dFAUTwPllgaBe3OJC9wVZDMQrjVufheqvGQ20rRlGgW/MPeDTWO4WXg5AQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:47.631431Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13397","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb1d4383c710dba59b351e37e505def64f041b90fcc2e21d0fae6b2f61cc33fc","sha256:e7896a5544310ab9b029f064154ff051e069cc05c3be2c1b5dc56208febe0f8d"],"state_sha256":"3a789c8d16e5682a247eec940622f5eaec9afd6bfb06536406d413fb76846c68"}