{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4WJ5AIG3BWWAHI2HCE2BQ7ZBVV","short_pith_number":"pith:4WJ5AIG3","canonical_record":{"source":{"id":"2506.21570","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T18:39:38Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"54a44dbaa922b0b225dc84cccb0726ac34de290c96ab628ee7adbf7a7d82e45e","abstract_canon_sha256":"65faefcafc1814761456715250fe6057f4880e0b2fb0848934985b8ea6a77172"},"schema_version":"1.0"},"canonical_sha256":"e593d020db0dac03a3471134187f21ad620eae03488d5db0fd24c4db2ccafcd4","source":{"kind":"arxiv","id":"2506.21570","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21570","created_at":"2026-07-05T11:27:56Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21570v1","created_at":"2026-07-05T11:27:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21570","created_at":"2026-07-05T11:27:56Z"},{"alias_kind":"pith_short_12","alias_value":"4WJ5AIG3BWWA","created_at":"2026-07-05T11:27:56Z"},{"alias_kind":"pith_short_16","alias_value":"4WJ5AIG3BWWAHI2H","created_at":"2026-07-05T11:27:56Z"},{"alias_kind":"pith_short_8","alias_value":"4WJ5AIG3","created_at":"2026-07-05T11:27:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4WJ5AIG3BWWAHI2HCE2BQ7ZBVV","target":"record","payload":{"canonical_record":{"source":{"id":"2506.21570","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T18:39:38Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"54a44dbaa922b0b225dc84cccb0726ac34de290c96ab628ee7adbf7a7d82e45e","abstract_canon_sha256":"65faefcafc1814761456715250fe6057f4880e0b2fb0848934985b8ea6a77172"},"schema_version":"1.0"},"canonical_sha256":"e593d020db0dac03a3471134187f21ad620eae03488d5db0fd24c4db2ccafcd4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:56.570029Z","signature_b64":"LN0wkdXNZxyOH3n83TekIjvqonY5YWIuxNfTfZ+nYr5Dg6VDjEEUKRfFRBpBgo2M69y3xhwnicoLHsSPXXkDAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e593d020db0dac03a3471134187f21ad620eae03488d5db0fd24c4db2ccafcd4","last_reissued_at":"2026-07-05T11:27:56.569508Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:56.569508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.21570","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:27:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VCpHX6ZfbybbPG3Rqunx0B9FWvw6MIVcHm11IHqh5xaJtonjXabZcYY6qWS/qUWjgEbKZsC32vOyMjX/L+3IDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:36:25.908959Z"},"content_sha256":"9b3fe624681234fe82ba332910b4a622316dddc5a9ee4785f0f11feefa7f62c6","schema_version":"1.0","event_id":"sha256:9b3fe624681234fe82ba332910b4a622316dddc5a9ee4785f0f11feefa7f62c6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4WJ5AIG3BWWAHI2HCE2BQ7ZBVV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexis Roger, Andrew R. Williams, Arjun Ashok, Irina Rish, Kashif Rasul, Prateek Humane, Roland Riachi, Yuriy Nevmyvaka","submitted_at":"2025-06-12T18:39:38Z","abstract_excerpt":"Recent works have demonstrated the effectiveness of adapting pre-trained language models (LMs) for forecasting time series in the low-data regime. We build upon these findings by analyzing the effective transfer from language models to time series forecasting under various design choices including upstream post-training, time series tokenizer and language backbone size. In the low-data regime, these design choices have a significant impact on the validation loss, with clear-cut choices that outperform others. Contrary to Hernandez et al. (2021), we observe that the validation loss of the LMs c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21570","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/2506.21570/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:27:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1qoVpuvm8yhA/wYbEFfJGZW1EbO4E9jC3IiO7Zx6GqC8l4i/4nVWW9EJhFHbBqz9kqChJZ6I/apNZ8twP+1UAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:36:25.909448Z"},"content_sha256":"2473a2a4d9ef355c8f9394ce6803319ed80f875a59e61e9a78b4957e97c72358","schema_version":"1.0","event_id":"sha256:2473a2a4d9ef355c8f9394ce6803319ed80f875a59e61e9a78b4957e97c72358"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4WJ5AIG3BWWAHI2HCE2BQ7ZBVV/bundle.json","state_url":"https://pith.science/pith/4WJ5AIG3BWWAHI2HCE2BQ7ZBVV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4WJ5AIG3BWWAHI2HCE2BQ7ZBVV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T14:36:25Z","links":{"resolver":"https://pith.science/pith/4WJ5AIG3BWWAHI2HCE2BQ7ZBVV","bundle":"https://pith.science/pith/4WJ5AIG3BWWAHI2HCE2BQ7ZBVV/bundle.json","state":"https://pith.science/pith/4WJ5AIG3BWWAHI2HCE2BQ7ZBVV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4WJ5AIG3BWWAHI2HCE2BQ7ZBVV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4WJ5AIG3BWWAHI2HCE2BQ7ZBVV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"65faefcafc1814761456715250fe6057f4880e0b2fb0848934985b8ea6a77172","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T18:39:38Z","title_canon_sha256":"54a44dbaa922b0b225dc84cccb0726ac34de290c96ab628ee7adbf7a7d82e45e"},"schema_version":"1.0","source":{"id":"2506.21570","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21570","created_at":"2026-07-05T11:27:56Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21570v1","created_at":"2026-07-05T11:27:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21570","created_at":"2026-07-05T11:27:56Z"},{"alias_kind":"pith_short_12","alias_value":"4WJ5AIG3BWWA","created_at":"2026-07-05T11:27:56Z"},{"alias_kind":"pith_short_16","alias_value":"4WJ5AIG3BWWAHI2H","created_at":"2026-07-05T11:27:56Z"},{"alias_kind":"pith_short_8","alias_value":"4WJ5AIG3","created_at":"2026-07-05T11:27:56Z"}],"graph_snapshots":[{"event_id":"sha256:2473a2a4d9ef355c8f9394ce6803319ed80f875a59e61e9a78b4957e97c72358","target":"graph","created_at":"2026-07-05T11:27:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.21570/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent works have demonstrated the effectiveness of adapting pre-trained language models (LMs) for forecasting time series in the low-data regime. We build upon these findings by analyzing the effective transfer from language models to time series forecasting under various design choices including upstream post-training, time series tokenizer and language backbone size. In the low-data regime, these design choices have a significant impact on the validation loss, with clear-cut choices that outperform others. Contrary to Hernandez et al. (2021), we observe that the validation loss of the LMs c","authors_text":"Alexis Roger, Andrew R. Williams, Arjun Ashok, Irina Rish, Kashif Rasul, Prateek Humane, Roland Riachi, Yuriy Nevmyvaka","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T18:39:38Z","title":"Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21570","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9b3fe624681234fe82ba332910b4a622316dddc5a9ee4785f0f11feefa7f62c6","target":"record","created_at":"2026-07-05T11:27:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"65faefcafc1814761456715250fe6057f4880e0b2fb0848934985b8ea6a77172","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T18:39:38Z","title_canon_sha256":"54a44dbaa922b0b225dc84cccb0726ac34de290c96ab628ee7adbf7a7d82e45e"},"schema_version":"1.0","source":{"id":"2506.21570","kind":"arxiv","version":1}},"canonical_sha256":"e593d020db0dac03a3471134187f21ad620eae03488d5db0fd24c4db2ccafcd4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e593d020db0dac03a3471134187f21ad620eae03488d5db0fd24c4db2ccafcd4","first_computed_at":"2026-07-05T11:27:56.569508Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:56.569508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LN0wkdXNZxyOH3n83TekIjvqonY5YWIuxNfTfZ+nYr5Dg6VDjEEUKRfFRBpBgo2M69y3xhwnicoLHsSPXXkDAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:56.570029Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.21570","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b3fe624681234fe82ba332910b4a622316dddc5a9ee4785f0f11feefa7f62c6","sha256:2473a2a4d9ef355c8f9394ce6803319ed80f875a59e61e9a78b4957e97c72358"],"state_sha256":"c93c537e6e1d08a3bf44bdf291e949d9c8ee07197449ccc21b46b0b9d5ddf6c9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ke5NYzvjFQLVCPXKorKkzeQkYpHOZBs7GMhY9ra4zKWATAtlWDu3WvAAg6hMOME/ozDiIf38h9GRRna+M8XnCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T14:36:25.913244Z","bundle_sha256":"bd96ca3e43fcca318912d3267dcfe3ab2f5234dfeb6017f2587f88c1003ea3b1"}}