{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5A7THPJQBTFQQVVVEB3O4OKM7F","short_pith_number":"pith:5A7THPJQ","schema_version":"1.0","canonical_sha256":"e83f33bd300ccb0856b52076ee394cf97a2614d707ab7a64a5e3c900b2acc6d4","source":{"kind":"arxiv","id":"2507.07439","version":1},"attestation_state":"computed","paper":{"title":"Towards Interpretable Time Series Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jeremy Pawlus, Matthieu Boileau, Philippe Helluy, Svitlana Vyetrenko","submitted_at":"2025-07-10T05:29:34Z","abstract_excerpt":"In this paper, we investigate the distillation of time series reasoning capabilities into small, instruction-tuned language models as a step toward building interpretable time series foundation models. Leveraging a synthetic dataset of mean-reverting time series with systematically varied trends and noise levels, we generate natural language annotations using a large multimodal model and use these to supervise the fine-tuning of compact Qwen models. We introduce evaluation metrics that assess the quality of the distilled reasoning - focusing on trend direction, noise intensity, and extremum lo"},"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":"2507.07439","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T05:29:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fb3b629a13bd7e9327fe0e60eeda1cf04068b6bbc2bfa1d5d3a7bcdd581b3574","abstract_canon_sha256":"2589df537ac72e1f2a90137272ca1857d3b940541f1394e6387def68af1db16b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:58.052226Z","signature_b64":"Sa+5/2kAg7Cr7MO6wgzQhFkJ1r7eMLIvT/s85Ci9hrB6HTtCQ8OW3LMilRj5mVwNC9bxkCAnkgki18OvZ48cBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e83f33bd300ccb0856b52076ee394cf97a2614d707ab7a64a5e3c900b2acc6d4","last_reissued_at":"2026-07-05T11:34:58.051727Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:58.051727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Interpretable Time Series Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jeremy Pawlus, Matthieu Boileau, Philippe Helluy, Svitlana Vyetrenko","submitted_at":"2025-07-10T05:29:34Z","abstract_excerpt":"In this paper, we investigate the distillation of time series reasoning capabilities into small, instruction-tuned language models as a step toward building interpretable time series foundation models. Leveraging a synthetic dataset of mean-reverting time series with systematically varied trends and noise levels, we generate natural language annotations using a large multimodal model and use these to supervise the fine-tuning of compact Qwen models. We introduce evaluation metrics that assess the quality of the distilled reasoning - focusing on trend direction, noise intensity, and extremum lo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07439","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/2507.07439/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":"2507.07439","created_at":"2026-07-05T11:34:58.051787+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.07439v1","created_at":"2026-07-05T11:34:58.051787+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07439","created_at":"2026-07-05T11:34:58.051787+00:00"},{"alias_kind":"pith_short_12","alias_value":"5A7THPJQBTFQ","created_at":"2026-07-05T11:34:58.051787+00:00"},{"alias_kind":"pith_short_16","alias_value":"5A7THPJQBTFQQVVV","created_at":"2026-07-05T11:34:58.051787+00:00"},{"alias_kind":"pith_short_8","alias_value":"5A7THPJQ","created_at":"2026-07-05T11:34:58.051787+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/5A7THPJQBTFQQVVVEB3O4OKM7F","json":"https://pith.science/pith/5A7THPJQBTFQQVVVEB3O4OKM7F.json","graph_json":"https://pith.science/api/pith-number/5A7THPJQBTFQQVVVEB3O4OKM7F/graph.json","events_json":"https://pith.science/api/pith-number/5A7THPJQBTFQQVVVEB3O4OKM7F/events.json","paper":"https://pith.science/paper/5A7THPJQ"},"agent_actions":{"view_html":"https://pith.science/pith/5A7THPJQBTFQQVVVEB3O4OKM7F","download_json":"https://pith.science/pith/5A7THPJQBTFQQVVVEB3O4OKM7F.json","view_paper":"https://pith.science/paper/5A7THPJQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.07439&json=true","fetch_graph":"https://pith.science/api/pith-number/5A7THPJQBTFQQVVVEB3O4OKM7F/graph.json","fetch_events":"https://pith.science/api/pith-number/5A7THPJQBTFQQVVVEB3O4OKM7F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5A7THPJQBTFQQVVVEB3O4OKM7F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5A7THPJQBTFQQVVVEB3O4OKM7F/action/storage_attestation","attest_author":"https://pith.science/pith/5A7THPJQBTFQQVVVEB3O4OKM7F/action/author_attestation","sign_citation":"https://pith.science/pith/5A7THPJQBTFQQVVVEB3O4OKM7F/action/citation_signature","submit_replication":"https://pith.science/pith/5A7THPJQBTFQQVVVEB3O4OKM7F/action/replication_record"}},"created_at":"2026-07-05T11:34:58.051787+00:00","updated_at":"2026-07-05T11:34:58.051787+00:00"}