{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RHXJELFM7RTNN3J45NEE5XPRJS","short_pith_number":"pith:RHXJELFM","schema_version":"1.0","canonical_sha256":"89ee922cacfc66d6ed3ceb484eddf14c9288e0bf3239ff239b0480053b16341d","source":{"kind":"arxiv","id":"2201.05692","version":1},"attestation_state":"computed","paper":{"title":"Model Stability with Continuous Data Updates","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Avinesh P.V.S., Huiting Liu, Peter Grasch, Sachin Agarwal, Siddharth Patwardhan","submitted_at":"2022-01-14T22:11:16Z","abstract_excerpt":"In this paper, we study the \"stability\" of machine learning (ML) models within the context of larger, complex NLP systems with continuous training data updates. For this study, we propose a methodology for the assessment of model stability (which we refer to as jitter under various experimental conditions. We find that model design choices, including network architecture and input representation, have a critical impact on stability through experiments on four text classification tasks and two sequence labeling tasks. In classification tasks, non-RNN-based models are observed to be more stable "},"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":"2201.05692","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-14T22:11:16Z","cross_cats_sorted":[],"title_canon_sha256":"b9278fa5653525f45ef5e256280cc8ddf066f5aeeb96e3be6445a95a375389b6","abstract_canon_sha256":"ee3bf800a5af63e78209e864dc64a0231228fd3a5b52f2c4c3cfe57d504f4e5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:48:50.450928Z","signature_b64":"L0NkpLePGyZih2TtRpbodlw6CnOC8+NWgrdThPCXayc7lJy8OV16s198/6OzlQbDEZ30IYJfF76pfnGqCpBCCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89ee922cacfc66d6ed3ceb484eddf14c9288e0bf3239ff239b0480053b16341d","last_reissued_at":"2026-07-05T03:48:50.450541Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:48:50.450541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model Stability with Continuous Data Updates","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Avinesh P.V.S., Huiting Liu, Peter Grasch, Sachin Agarwal, Siddharth Patwardhan","submitted_at":"2022-01-14T22:11:16Z","abstract_excerpt":"In this paper, we study the \"stability\" of machine learning (ML) models within the context of larger, complex NLP systems with continuous training data updates. For this study, we propose a methodology for the assessment of model stability (which we refer to as jitter under various experimental conditions. We find that model design choices, including network architecture and input representation, have a critical impact on stability through experiments on four text classification tasks and two sequence labeling tasks. In classification tasks, non-RNN-based models are observed to be more stable "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.05692","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/2201.05692/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":"2201.05692","created_at":"2026-07-05T03:48:50.450606+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.05692v1","created_at":"2026-07-05T03:48:50.450606+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.05692","created_at":"2026-07-05T03:48:50.450606+00:00"},{"alias_kind":"pith_short_12","alias_value":"RHXJELFM7RTN","created_at":"2026-07-05T03:48:50.450606+00:00"},{"alias_kind":"pith_short_16","alias_value":"RHXJELFM7RTNN3J4","created_at":"2026-07-05T03:48:50.450606+00:00"},{"alias_kind":"pith_short_8","alias_value":"RHXJELFM","created_at":"2026-07-05T03:48:50.450606+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RHXJELFM7RTNN3J45NEE5XPRJS","json":"https://pith.science/pith/RHXJELFM7RTNN3J45NEE5XPRJS.json","graph_json":"https://pith.science/api/pith-number/RHXJELFM7RTNN3J45NEE5XPRJS/graph.json","events_json":"https://pith.science/api/pith-number/RHXJELFM7RTNN3J45NEE5XPRJS/events.json","paper":"https://pith.science/paper/RHXJELFM"},"agent_actions":{"view_html":"https://pith.science/pith/RHXJELFM7RTNN3J45NEE5XPRJS","download_json":"https://pith.science/pith/RHXJELFM7RTNN3J45NEE5XPRJS.json","view_paper":"https://pith.science/paper/RHXJELFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.05692&json=true","fetch_graph":"https://pith.science/api/pith-number/RHXJELFM7RTNN3J45NEE5XPRJS/graph.json","fetch_events":"https://pith.science/api/pith-number/RHXJELFM7RTNN3J45NEE5XPRJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RHXJELFM7RTNN3J45NEE5XPRJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RHXJELFM7RTNN3J45NEE5XPRJS/action/storage_attestation","attest_author":"https://pith.science/pith/RHXJELFM7RTNN3J45NEE5XPRJS/action/author_attestation","sign_citation":"https://pith.science/pith/RHXJELFM7RTNN3J45NEE5XPRJS/action/citation_signature","submit_replication":"https://pith.science/pith/RHXJELFM7RTNN3J45NEE5XPRJS/action/replication_record"}},"created_at":"2026-07-05T03:48:50.450606+00:00","updated_at":"2026-07-05T03:48:50.450606+00:00"}