{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:63PUV7Y4KH2M2OT5AJDKHUGKL6","short_pith_number":"pith:63PUV7Y4","schema_version":"1.0","canonical_sha256":"f6df4aff1c51f4cd3a7d0246a3d0ca5fa3d90afd9047bfa417f8bf7ca151b49a","source":{"kind":"arxiv","id":"2607.20002","version":1},"attestation_state":"computed","paper":{"title":"Post-Training in Time Series Foundation Models: A Unifying Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ambroise Odonnat, Boris N. Oreshkin, Chenghao Liu, Keli Zhang, Lei Zan, Lujia Pan, Malik Tiomoko, Shifeng Xie, Themis Palpanas, Zehao Xiao","submitted_at":"2026-07-22T10:37:10Z","abstract_excerpt":"Time series foundation models (TSFMs) have emerged as general-purpose models for time series analysis, but pretraining alone is often insufficient for reliable downstream deployment. Bridging this gap requires further intervention to handle domain shift, task heterogeneity, limited supervision, and computational constraints, which motivates post-training as a broad class of methods to adapt, augment, compose, calibrate, or specialize pretrained TSFMs for downstream tasks. In this work, we analyze TSFM post-training methods based on their locus of intervention in the prediction pipeline, yieldi"},"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":"2607.20002","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-22T10:37:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d98dc9c2e41e67c76f811f092730e6a420d38b47e5ce1164d6632822aca21fe9","abstract_canon_sha256":"285a33ab307a693a72075bd776c77efaf8a2d75fa2860aac7bc4c9cda9f872d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-23T01:24:54.880356Z","signature_b64":"hMU7ZpK6KO6Cbn9qpXeMA+w8iSMhYp/ON3+s9tUV887KaawQeZ7fRN4CP7SkzB2t8Cq6uNlAKGN2hv8z5Bj9BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6df4aff1c51f4cd3a7d0246a3d0ca5fa3d90afd9047bfa417f8bf7ca151b49a","last_reissued_at":"2026-07-23T01:24:54.879452Z","signature_status":"signed_v1","first_computed_at":"2026-07-23T01:24:54.879452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Post-Training in Time Series Foundation Models: A Unifying Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ambroise Odonnat, Boris N. Oreshkin, Chenghao Liu, Keli Zhang, Lei Zan, Lujia Pan, Malik Tiomoko, Shifeng Xie, Themis Palpanas, Zehao Xiao","submitted_at":"2026-07-22T10:37:10Z","abstract_excerpt":"Time series foundation models (TSFMs) have emerged as general-purpose models for time series analysis, but pretraining alone is often insufficient for reliable downstream deployment. Bridging this gap requires further intervention to handle domain shift, task heterogeneity, limited supervision, and computational constraints, which motivates post-training as a broad class of methods to adapt, augment, compose, calibrate, or specialize pretrained TSFMs for downstream tasks. In this work, we analyze TSFM post-training methods based on their locus of intervention in the prediction pipeline, yieldi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20002","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/2607.20002/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":"2607.20002","created_at":"2026-07-23T01:24:54.879913+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.20002v1","created_at":"2026-07-23T01:24:54.879913+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20002","created_at":"2026-07-23T01:24:54.879913+00:00"},{"alias_kind":"pith_short_12","alias_value":"63PUV7Y4KH2M","created_at":"2026-07-23T01:24:54.879913+00:00"},{"alias_kind":"pith_short_16","alias_value":"63PUV7Y4KH2M2OT5","created_at":"2026-07-23T01:24:54.879913+00:00"},{"alias_kind":"pith_short_8","alias_value":"63PUV7Y4","created_at":"2026-07-23T01:24:54.879913+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/63PUV7Y4KH2M2OT5AJDKHUGKL6","json":"https://pith.science/pith/63PUV7Y4KH2M2OT5AJDKHUGKL6.json","graph_json":"https://pith.science/api/pith-number/63PUV7Y4KH2M2OT5AJDKHUGKL6/graph.json","events_json":"https://pith.science/api/pith-number/63PUV7Y4KH2M2OT5AJDKHUGKL6/events.json","paper":"https://pith.science/paper/63PUV7Y4"},"agent_actions":{"view_html":"https://pith.science/pith/63PUV7Y4KH2M2OT5AJDKHUGKL6","download_json":"https://pith.science/pith/63PUV7Y4KH2M2OT5AJDKHUGKL6.json","view_paper":"https://pith.science/paper/63PUV7Y4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.20002&json=true","fetch_graph":"https://pith.science/api/pith-number/63PUV7Y4KH2M2OT5AJDKHUGKL6/graph.json","fetch_events":"https://pith.science/api/pith-number/63PUV7Y4KH2M2OT5AJDKHUGKL6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/63PUV7Y4KH2M2OT5AJDKHUGKL6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/63PUV7Y4KH2M2OT5AJDKHUGKL6/action/storage_attestation","attest_author":"https://pith.science/pith/63PUV7Y4KH2M2OT5AJDKHUGKL6/action/author_attestation","sign_citation":"https://pith.science/pith/63PUV7Y4KH2M2OT5AJDKHUGKL6/action/citation_signature","submit_replication":"https://pith.science/pith/63PUV7Y4KH2M2OT5AJDKHUGKL6/action/replication_record"}},"created_at":"2026-07-23T01:24:54.879913+00:00","updated_at":"2026-07-23T01:24:54.879913+00:00"}