{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EQXA4OYIVRDOAGEYNLKNA3H2KE","short_pith_number":"pith:EQXA4OYI","schema_version":"1.0","canonical_sha256":"242e0e3b08ac46e018986ad4d06cfa5136dcf05929132524940957cd7fae1802","source":{"kind":"arxiv","id":"2606.18986","version":1},"attestation_state":"computed","paper":{"title":"Beyond Tokenization: Direct Timestep Embedding and Contrastive Alignment for Time-Series Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hung Le, Huu Hiep Nguyen, Thin Nguyen, Yafeng Wu","submitted_at":"2026-06-17T12:07:23Z","abstract_excerpt":"Recent advances in large language models (LLMs) have given rise to time-series question answering (TSQA), which formulates time-series analysis as natural-language question answering. However, directly feeding raw numerical series into LLMs suffers from a tokenization bottleneck: Byte Pair Encoding fragments continuous values into unstable tokens whose embeddings lack meaningful metric structure, resulting in the loss of magnitude, scale, and trend information. Prior methods use patch-based encoders that split the series into fixed windows, locking in one granularity that breaks patterns and h"},"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":"2606.18986","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T12:07:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"486aad2ac7048b1c699de972678c273d11c1b2be8eb76d5a782b99027e7ac22f","abstract_canon_sha256":"51da95a3f7d4d489de0c2f939f49a6f72713d55f35d3b1723988f58af0c5b381"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:53.838038Z","signature_b64":"wJrcFDaOlFlkv5GAJ2yHTR21XwXZSXtb5BLshX7XSuPLZhT1eUj2oz04yqTOQp4mMKZFck8Tc4dO1zzkMw5qBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"242e0e3b08ac46e018986ad4d06cfa5136dcf05929132524940957cd7fae1802","last_reissued_at":"2026-06-19T16:11:53.837675Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:53.837675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Tokenization: Direct Timestep Embedding and Contrastive Alignment for Time-Series Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hung Le, Huu Hiep Nguyen, Thin Nguyen, Yafeng Wu","submitted_at":"2026-06-17T12:07:23Z","abstract_excerpt":"Recent advances in large language models (LLMs) have given rise to time-series question answering (TSQA), which formulates time-series analysis as natural-language question answering. However, directly feeding raw numerical series into LLMs suffers from a tokenization bottleneck: Byte Pair Encoding fragments continuous values into unstable tokens whose embeddings lack meaningful metric structure, resulting in the loss of magnitude, scale, and trend information. Prior methods use patch-based encoders that split the series into fixed windows, locking in one granularity that breaks patterns and h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18986","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/2606.18986/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":"2606.18986","created_at":"2026-06-19T16:11:53.837745+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18986v1","created_at":"2026-06-19T16:11:53.837745+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18986","created_at":"2026-06-19T16:11:53.837745+00:00"},{"alias_kind":"pith_short_12","alias_value":"EQXA4OYIVRDO","created_at":"2026-06-19T16:11:53.837745+00:00"},{"alias_kind":"pith_short_16","alias_value":"EQXA4OYIVRDOAGEY","created_at":"2026-06-19T16:11:53.837745+00:00"},{"alias_kind":"pith_short_8","alias_value":"EQXA4OYI","created_at":"2026-06-19T16:11:53.837745+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/EQXA4OYIVRDOAGEYNLKNA3H2KE","json":"https://pith.science/pith/EQXA4OYIVRDOAGEYNLKNA3H2KE.json","graph_json":"https://pith.science/api/pith-number/EQXA4OYIVRDOAGEYNLKNA3H2KE/graph.json","events_json":"https://pith.science/api/pith-number/EQXA4OYIVRDOAGEYNLKNA3H2KE/events.json","paper":"https://pith.science/paper/EQXA4OYI"},"agent_actions":{"view_html":"https://pith.science/pith/EQXA4OYIVRDOAGEYNLKNA3H2KE","download_json":"https://pith.science/pith/EQXA4OYIVRDOAGEYNLKNA3H2KE.json","view_paper":"https://pith.science/paper/EQXA4OYI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18986&json=true","fetch_graph":"https://pith.science/api/pith-number/EQXA4OYIVRDOAGEYNLKNA3H2KE/graph.json","fetch_events":"https://pith.science/api/pith-number/EQXA4OYIVRDOAGEYNLKNA3H2KE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EQXA4OYIVRDOAGEYNLKNA3H2KE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EQXA4OYIVRDOAGEYNLKNA3H2KE/action/storage_attestation","attest_author":"https://pith.science/pith/EQXA4OYIVRDOAGEYNLKNA3H2KE/action/author_attestation","sign_citation":"https://pith.science/pith/EQXA4OYIVRDOAGEYNLKNA3H2KE/action/citation_signature","submit_replication":"https://pith.science/pith/EQXA4OYIVRDOAGEYNLKNA3H2KE/action/replication_record"}},"created_at":"2026-06-19T16:11:53.837745+00:00","updated_at":"2026-06-19T16:11:53.837745+00:00"}