{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3R7M2H47ZLD72KZAX7FBW6MF3V","short_pith_number":"pith:3R7M2H47","schema_version":"1.0","canonical_sha256":"dc7ecd1f9fcac7fd2b20bfca1b7985dd79416a9e9949af149d8e189e2589a789","source":{"kind":"arxiv","id":"2606.09912","version":1},"attestation_state":"computed","paper":{"title":"Mix, Don't Pick: Why Synthetic Corpus Composition Matters for Time Series Foundation Model Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aaryan Nagpal, Debdeep Sanyal, Dhruv Kumar, Murari Mandal, Saurabh Deshpande","submitted_at":"2026-06-06T12:10:38Z","abstract_excerpt":"Choosing the wrong synthetic generator for time-series foundation model pretraining is costly: under identical training budgets, the best and worst generators produce up to a $2\\times$ gap in forecasting error, yet the field has no principled way to make this choice. The problem is compounded by the fact that generator rankings are not stable across architectures: across 11 generator families evaluated on Chronos-T5-Mini and Moirai-Small trained from scratch, we find that which generators are useful depends on the model architecture. Rather than solving the generator selection problem, we side"},"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":"2606.09912","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-06T12:10:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"258a01d0ce3039794c97b52b1df5f08ddcbe3391c2df054dafbfd3e46aa98b95","abstract_canon_sha256":"51c7e7eace2f5b8274782fa99d4481aa2d233243bd1b6b46387312706fad273d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T00:08:32.710523Z","signature_b64":"xJ0DC0VliZnEAS1jLnYN4NOQxrAyEM26IWogEKPhREk+RGE0/MN+u1kDbHom3C2QL+w2E9CFlX0qFSDrC1eVAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc7ecd1f9fcac7fd2b20bfca1b7985dd79416a9e9949af149d8e189e2589a789","last_reissued_at":"2026-06-10T00:08:32.709490Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T00:08:32.709490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mix, Don't Pick: Why Synthetic Corpus Composition Matters for Time Series Foundation Model Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aaryan Nagpal, Debdeep Sanyal, Dhruv Kumar, Murari Mandal, Saurabh Deshpande","submitted_at":"2026-06-06T12:10:38Z","abstract_excerpt":"Choosing the wrong synthetic generator for time-series foundation model pretraining is costly: under identical training budgets, the best and worst generators produce up to a $2\\times$ gap in forecasting error, yet the field has no principled way to make this choice. The problem is compounded by the fact that generator rankings are not stable across architectures: across 11 generator families evaluated on Chronos-T5-Mini and Moirai-Small trained from scratch, we find that which generators are useful depends on the model architecture. Rather than solving the generator selection problem, we side"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09912","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/2606.09912/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":"2606.09912","created_at":"2026-06-10T00:08:32.709648+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09912v1","created_at":"2026-06-10T00:08:32.709648+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09912","created_at":"2026-06-10T00:08:32.709648+00:00"},{"alias_kind":"pith_short_12","alias_value":"3R7M2H47ZLD7","created_at":"2026-06-10T00:08:32.709648+00:00"},{"alias_kind":"pith_short_16","alias_value":"3R7M2H47ZLD72KZA","created_at":"2026-06-10T00:08:32.709648+00:00"},{"alias_kind":"pith_short_8","alias_value":"3R7M2H47","created_at":"2026-06-10T00:08:32.709648+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/3R7M2H47ZLD72KZAX7FBW6MF3V","json":"https://pith.science/pith/3R7M2H47ZLD72KZAX7FBW6MF3V.json","graph_json":"https://pith.science/api/pith-number/3R7M2H47ZLD72KZAX7FBW6MF3V/graph.json","events_json":"https://pith.science/api/pith-number/3R7M2H47ZLD72KZAX7FBW6MF3V/events.json","paper":"https://pith.science/paper/3R7M2H47"},"agent_actions":{"view_html":"https://pith.science/pith/3R7M2H47ZLD72KZAX7FBW6MF3V","download_json":"https://pith.science/pith/3R7M2H47ZLD72KZAX7FBW6MF3V.json","view_paper":"https://pith.science/paper/3R7M2H47","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09912&json=true","fetch_graph":"https://pith.science/api/pith-number/3R7M2H47ZLD72KZAX7FBW6MF3V/graph.json","fetch_events":"https://pith.science/api/pith-number/3R7M2H47ZLD72KZAX7FBW6MF3V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3R7M2H47ZLD72KZAX7FBW6MF3V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3R7M2H47ZLD72KZAX7FBW6MF3V/action/storage_attestation","attest_author":"https://pith.science/pith/3R7M2H47ZLD72KZAX7FBW6MF3V/action/author_attestation","sign_citation":"https://pith.science/pith/3R7M2H47ZLD72KZAX7FBW6MF3V/action/citation_signature","submit_replication":"https://pith.science/pith/3R7M2H47ZLD72KZAX7FBW6MF3V/action/replication_record"}},"created_at":"2026-06-10T00:08:32.709648+00:00","updated_at":"2026-06-10T00:08:32.709648+00:00"}