{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MWFS7BOUIJJ6Q576OYXZFKYAHU","short_pith_number":"pith:MWFS7BOU","schema_version":"1.0","canonical_sha256":"658b2f85d44253e877fe762f92ab003d0f5c1d4e4ca6a9ff232d87a5eabc5abd","source":{"kind":"arxiv","id":"2505.11902","version":1},"attestation_state":"computed","paper":{"title":"Dynamic Perturbed Adaptive Method for Infinite Task-Conflicting Time Series","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arben Cela, Jiang You, Xiaozhen Wang","submitted_at":"2025-05-17T08:33:57Z","abstract_excerpt":"We formulate time series tasks as input-output mappings under varying objectives, where the same input may yield different outputs. This challenges a model's generalization and adaptability. To study this, we construct a synthetic dataset with numerous conflicting subtasks to evaluate adaptation under frequent task shifts. Existing static models consistently fail in such settings. We propose a dynamic perturbed adaptive method based on a trunk-branch architecture, where the trunk evolves slowly to capture long-term structure, and branch modules are re-initialized and updated for each task. Thi"},"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":"2505.11902","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-17T08:33:57Z","cross_cats_sorted":[],"title_canon_sha256":"f034d2ffe31b3d2364c7ba488f27e5250d8319ffb41eb103dc0ea134993c12ab","abstract_canon_sha256":"9c31a15264d03b5692e5a06dee5664e9f12dca9ae97755d0151493218054ef0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:54.212676Z","signature_b64":"17Z8AFb6Da8KXKYwdvnhblFDkRtTGC8FHphgSvKm3x1KBx9zyf8cbjJOzjmwIdxJxGo2f1AOoxZuk9mAxqwbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"658b2f85d44253e877fe762f92ab003d0f5c1d4e4ca6a9ff232d87a5eabc5abd","last_reissued_at":"2026-07-05T11:04:54.212066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:54.212066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Perturbed Adaptive Method for Infinite Task-Conflicting Time Series","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arben Cela, Jiang You, Xiaozhen Wang","submitted_at":"2025-05-17T08:33:57Z","abstract_excerpt":"We formulate time series tasks as input-output mappings under varying objectives, where the same input may yield different outputs. This challenges a model's generalization and adaptability. To study this, we construct a synthetic dataset with numerous conflicting subtasks to evaluate adaptation under frequent task shifts. Existing static models consistently fail in such settings. We propose a dynamic perturbed adaptive method based on a trunk-branch architecture, where the trunk evolves slowly to capture long-term structure, and branch modules are re-initialized and updated for each task. Thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11902","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/2505.11902/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":"2505.11902","created_at":"2026-07-05T11:04:54.212129+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11902v1","created_at":"2026-07-05T11:04:54.212129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11902","created_at":"2026-07-05T11:04:54.212129+00:00"},{"alias_kind":"pith_short_12","alias_value":"MWFS7BOUIJJ6","created_at":"2026-07-05T11:04:54.212129+00:00"},{"alias_kind":"pith_short_16","alias_value":"MWFS7BOUIJJ6Q576","created_at":"2026-07-05T11:04:54.212129+00:00"},{"alias_kind":"pith_short_8","alias_value":"MWFS7BOU","created_at":"2026-07-05T11:04:54.212129+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/MWFS7BOUIJJ6Q576OYXZFKYAHU","json":"https://pith.science/pith/MWFS7BOUIJJ6Q576OYXZFKYAHU.json","graph_json":"https://pith.science/api/pith-number/MWFS7BOUIJJ6Q576OYXZFKYAHU/graph.json","events_json":"https://pith.science/api/pith-number/MWFS7BOUIJJ6Q576OYXZFKYAHU/events.json","paper":"https://pith.science/paper/MWFS7BOU"},"agent_actions":{"view_html":"https://pith.science/pith/MWFS7BOUIJJ6Q576OYXZFKYAHU","download_json":"https://pith.science/pith/MWFS7BOUIJJ6Q576OYXZFKYAHU.json","view_paper":"https://pith.science/paper/MWFS7BOU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11902&json=true","fetch_graph":"https://pith.science/api/pith-number/MWFS7BOUIJJ6Q576OYXZFKYAHU/graph.json","fetch_events":"https://pith.science/api/pith-number/MWFS7BOUIJJ6Q576OYXZFKYAHU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MWFS7BOUIJJ6Q576OYXZFKYAHU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MWFS7BOUIJJ6Q576OYXZFKYAHU/action/storage_attestation","attest_author":"https://pith.science/pith/MWFS7BOUIJJ6Q576OYXZFKYAHU/action/author_attestation","sign_citation":"https://pith.science/pith/MWFS7BOUIJJ6Q576OYXZFKYAHU/action/citation_signature","submit_replication":"https://pith.science/pith/MWFS7BOUIJJ6Q576OYXZFKYAHU/action/replication_record"}},"created_at":"2026-07-05T11:04:54.212129+00:00","updated_at":"2026-07-05T11:04:54.212129+00:00"}