{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NAR5APQV22DCXCBJNLTKBJSUW3","short_pith_number":"pith:NAR5APQV","schema_version":"1.0","canonical_sha256":"6823d03e15d6862b88296ae6a0a654b6f9ad32831ee4b55a7c91c2488e969cd7","source":{"kind":"arxiv","id":"2501.00421","version":2},"attestation_state":"computed","paper":{"title":"Outlier-Robust Linear System Identification Under Heavy-tailed Noise","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SY","math.OC"],"primary_cat":"eess.SY","authors_text":"Aritra Mitra, Vinay Kanakeri","submitted_at":"2024-12-31T12:53:02Z","abstract_excerpt":"We consider the problem of estimating the state transition matrix of a linear time-invariant (LTI) system, given access to multiple independent trajectories sampled from the system. Several recent papers have conducted a non-asymptotic analysis of this problem, relying crucially on the assumption that the process noise is either Gaussian or sub-Gaussian, i.e., \"light-tailed\". In sharp contrast, we work under a significantly weaker noise model, assuming nothing more than the existence of the fourth moment of the noise distribution. For this setting, we provide the first set of results demonstra"},"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":"2501.00421","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2024-12-31T12:53:02Z","cross_cats_sorted":["cs.LG","cs.SY","math.OC"],"title_canon_sha256":"fdb588a403f61c9e566d1ad8289d818abec1e8d8aa8ccd4524300f0f3da26ff5","abstract_canon_sha256":"63e2c29f226ab4dffce4f8ed1a8b0d1e7d7e1078a566cd425e2b8c720e72333e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:50.016201Z","signature_b64":"ZSVDRl3uvNt9sYeRAvdi2owSAM4YhBwFTBRuufhJgMS4wXcpOe+offMkmTXXk5aJ+IddrUsKyHcPV24F09zTBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6823d03e15d6862b88296ae6a0a654b6f9ad32831ee4b55a7c91c2488e969cd7","last_reissued_at":"2026-07-05T11:10:50.015719Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:50.015719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Outlier-Robust Linear System Identification Under Heavy-tailed Noise","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SY","math.OC"],"primary_cat":"eess.SY","authors_text":"Aritra Mitra, Vinay Kanakeri","submitted_at":"2024-12-31T12:53:02Z","abstract_excerpt":"We consider the problem of estimating the state transition matrix of a linear time-invariant (LTI) system, given access to multiple independent trajectories sampled from the system. Several recent papers have conducted a non-asymptotic analysis of this problem, relying crucially on the assumption that the process noise is either Gaussian or sub-Gaussian, i.e., \"light-tailed\". In sharp contrast, we work under a significantly weaker noise model, assuming nothing more than the existence of the fourth moment of the noise distribution. For this setting, we provide the first set of results demonstra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00421","kind":"arxiv","version":2},"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/2501.00421/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":"2501.00421","created_at":"2026-07-05T11:10:50.015768+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00421v2","created_at":"2026-07-05T11:10:50.015768+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00421","created_at":"2026-07-05T11:10:50.015768+00:00"},{"alias_kind":"pith_short_12","alias_value":"NAR5APQV22DC","created_at":"2026-07-05T11:10:50.015768+00:00"},{"alias_kind":"pith_short_16","alias_value":"NAR5APQV22DCXCBJ","created_at":"2026-07-05T11:10:50.015768+00:00"},{"alias_kind":"pith_short_8","alias_value":"NAR5APQV","created_at":"2026-07-05T11:10:50.015768+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.08933","citing_title":"Corruption-Tolerant Asynchronous Q-Learning with Near-Optimal Rates","ref_index":75,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NAR5APQV22DCXCBJNLTKBJSUW3","json":"https://pith.science/pith/NAR5APQV22DCXCBJNLTKBJSUW3.json","graph_json":"https://pith.science/api/pith-number/NAR5APQV22DCXCBJNLTKBJSUW3/graph.json","events_json":"https://pith.science/api/pith-number/NAR5APQV22DCXCBJNLTKBJSUW3/events.json","paper":"https://pith.science/paper/NAR5APQV"},"agent_actions":{"view_html":"https://pith.science/pith/NAR5APQV22DCXCBJNLTKBJSUW3","download_json":"https://pith.science/pith/NAR5APQV22DCXCBJNLTKBJSUW3.json","view_paper":"https://pith.science/paper/NAR5APQV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00421&json=true","fetch_graph":"https://pith.science/api/pith-number/NAR5APQV22DCXCBJNLTKBJSUW3/graph.json","fetch_events":"https://pith.science/api/pith-number/NAR5APQV22DCXCBJNLTKBJSUW3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NAR5APQV22DCXCBJNLTKBJSUW3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NAR5APQV22DCXCBJNLTKBJSUW3/action/storage_attestation","attest_author":"https://pith.science/pith/NAR5APQV22DCXCBJNLTKBJSUW3/action/author_attestation","sign_citation":"https://pith.science/pith/NAR5APQV22DCXCBJNLTKBJSUW3/action/citation_signature","submit_replication":"https://pith.science/pith/NAR5APQV22DCXCBJNLTKBJSUW3/action/replication_record"}},"created_at":"2026-07-05T11:10:50.015768+00:00","updated_at":"2026-07-05T11:10:50.015768+00:00"}