{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IZTV6GYHZX2EP6V3TWUCSWMRSQ","short_pith_number":"pith:IZTV6GYH","schema_version":"1.0","canonical_sha256":"46675f1b07cdf447fabb9da8295991940f74afadf9578bf399232ece90dc2de5","source":{"kind":"arxiv","id":"2511.20577","version":4},"attestation_state":"computed","paper":{"title":"MSTN: A Lightweight and Fast Model for General TimeSeries Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"The Multi-scale Temporal Network uses early aggregation of convolutional features, sequence modeling, and self-gated fusion to set new performance marks on time series tasks while staying under one million parameters.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chandresh K Maurya, Sumit S Shevtekar","submitted_at":"2025-11-25T18:09:42Z","abstract_excerpt":"Real-world time series often exhibit strong non-stationarity, complex nonlinear dynamics, and behavior expressed across multiple temporal scales, from rapid local fluctuations to slow-evolving long-range trends. However, many contemporary architectures impose rigid, fixed-scale structural priors-such as patch-based tokenization, predefined receptive fields, or frozen backbone encoders-which can over-regularize temporal dynamics and limit adaptability to abrupt high-magnitude events. To handle this, we introduce the Multi-scale Temporal Network (MSTN), a hybrid neural architecture grounded in a"},"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":true},"canonical_record":{"source":{"id":"2511.20577","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-11-25T18:09:42Z","cross_cats_sorted":[],"title_canon_sha256":"70ca2fe13429d01dfe8edc3b4c95a4dd08d9a69aac0c5d71636ea2db3863ed3e","abstract_canon_sha256":"327d99bec7165c74170b282782b6c148adafe362ae914f1f20ff547b9c20eb08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:59.543749Z","signature_b64":"nUlYJp5YpHY5HOVOyPABDMZnKaPiCcJr+d1Zz+5U5UtsAz1oRVj0ICKKejBVMHZaDpWhm+qG+m5jDvU4oHJoCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46675f1b07cdf447fabb9da8295991940f74afadf9578bf399232ece90dc2de5","last_reissued_at":"2026-05-20T00:02:59.542821Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:59.542821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MSTN: A Lightweight and Fast Model for General TimeSeries Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"The Multi-scale Temporal Network uses early aggregation of convolutional features, sequence modeling, and self-gated fusion to set new performance marks on time series tasks while staying under one million parameters.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chandresh K Maurya, Sumit S Shevtekar","submitted_at":"2025-11-25T18:09:42Z","abstract_excerpt":"Real-world time series often exhibit strong non-stationarity, complex nonlinear dynamics, and behavior expressed across multiple temporal scales, from rapid local fluctuations to slow-evolving long-range trends. However, many contemporary architectures impose rigid, fixed-scale structural priors-such as patch-based tokenization, predefined receptive fields, or frozen backbone encoders-which can over-regularize temporal dynamics and limit adaptability to abrupt high-magnitude events. To handle this, we introduce the Multi-scale Temporal Network (MSTN), a hybrid neural architecture grounded in a"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Across extensive benchmarks covering imputation, long term forecasting, short term forecasting, classification, and cross-dataset generalization, MSTN achieves state-of-the-art performance, establishing new best results on 33 of 40 datasets, while remaining lightweight (~278,520 params for MSTN-BiLSTM and ~950,776 ≈ 1M for MSTN-Transformer) and suitable for low-latency inference (<1 sec, often in milliseconds).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the specific combination of multi-scale convolutional encoder, sequence module, and self-gated fusion generalizes to new time series distributions without requiring extensive per-dataset hyperparameter retuning or suffering from benchmark overfitting.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MSTN is a lightweight hybrid model that reports new state-of-the-art results on 33 of 40 time series benchmarks for imputation, forecasting, and classification while using under one million parameters and sub-second inference.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"The Multi-scale Temporal Network uses early aggregation of convolutional features, sequence modeling, and self-gated fusion to set new performance marks on time series tasks while staying under one million parameters.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"bbdbdb5aa31f5e9821f096360fbfaf19ebb65b51c926640df7353a47d5430835"},"source":{"id":"2511.20577","kind":"arxiv","version":4},"verdict":{"id":"7cf8b128-3d74-43a7-84fe-ff7e46df4868","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T04:30:50.160183Z","strongest_claim":"Across extensive benchmarks covering imputation, long term forecasting, short term forecasting, classification, and cross-dataset generalization, MSTN achieves state-of-the-art performance, establishing new best results on 33 of 40 datasets, while remaining lightweight (~278,520 params for MSTN-BiLSTM and ~950,776 ≈ 1M for MSTN-Transformer) and suitable for low-latency inference (<1 sec, often in milliseconds).","one_line_summary":"MSTN is a lightweight hybrid model that reports new state-of-the-art results on 33 of 40 time series benchmarks for imputation, forecasting, and classification while using under one million parameters and sub-second inference.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the specific combination of multi-scale convolutional encoder, sequence module, and self-gated fusion generalizes to new time series distributions without requiring extensive per-dataset hyperparameter retuning or suffering from benchmark overfitting.","pith_extraction_headline":"The Multi-scale Temporal Network uses early aggregation of convolutional features, sequence modeling, and self-gated fusion to set new performance marks on time series tasks while staying under one million parameters."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2511.20577/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":2,"snapshot_sha256":"4b3d77795e27cae11112039b67de189ef60faeb42ef4ef5af9cebc0051928d2d"},"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":"2511.20577","created_at":"2026-05-20T00:02:59.542944+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.20577v4","created_at":"2026-05-20T00:02:59.542944+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.20577","created_at":"2026-05-20T00:02:59.542944+00:00"},{"alias_kind":"pith_short_12","alias_value":"IZTV6GYHZX2E","created_at":"2026-05-20T00:02:59.542944+00:00"},{"alias_kind":"pith_short_16","alias_value":"IZTV6GYHZX2EP6V3","created_at":"2026-05-20T00:02:59.542944+00:00"},{"alias_kind":"pith_short_8","alias_value":"IZTV6GYH","created_at":"2026-05-20T00:02:59.542944+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IZTV6GYHZX2EP6V3TWUCSWMRSQ","json":"https://pith.science/pith/IZTV6GYHZX2EP6V3TWUCSWMRSQ.json","graph_json":"https://pith.science/api/pith-number/IZTV6GYHZX2EP6V3TWUCSWMRSQ/graph.json","events_json":"https://pith.science/api/pith-number/IZTV6GYHZX2EP6V3TWUCSWMRSQ/events.json","paper":"https://pith.science/paper/IZTV6GYH"},"agent_actions":{"view_html":"https://pith.science/pith/IZTV6GYHZX2EP6V3TWUCSWMRSQ","download_json":"https://pith.science/pith/IZTV6GYHZX2EP6V3TWUCSWMRSQ.json","view_paper":"https://pith.science/paper/IZTV6GYH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.20577&json=true","fetch_graph":"https://pith.science/api/pith-number/IZTV6GYHZX2EP6V3TWUCSWMRSQ/graph.json","fetch_events":"https://pith.science/api/pith-number/IZTV6GYHZX2EP6V3TWUCSWMRSQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IZTV6GYHZX2EP6V3TWUCSWMRSQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IZTV6GYHZX2EP6V3TWUCSWMRSQ/action/storage_attestation","attest_author":"https://pith.science/pith/IZTV6GYHZX2EP6V3TWUCSWMRSQ/action/author_attestation","sign_citation":"https://pith.science/pith/IZTV6GYHZX2EP6V3TWUCSWMRSQ/action/citation_signature","submit_replication":"https://pith.science/pith/IZTV6GYHZX2EP6V3TWUCSWMRSQ/action/replication_record"}},"created_at":"2026-05-20T00:02:59.542944+00:00","updated_at":"2026-05-20T00:02:59.542944+00:00"}