{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WPRSI5XT7EWA3QJBSHUI6UAXB7","short_pith_number":"pith:WPRSI5XT","schema_version":"1.0","canonical_sha256":"b3e32476f3f92c0dc12191e88f50170ff4a40d54d6a13b75157d16b91d07eb6e","source":{"kind":"arxiv","id":"2501.07335","version":2},"attestation_state":"computed","paper":{"title":"TempoGPT: Enhancing Time Series Reasoning via Quantizing Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chunhua Yang, Haochuan Zhang, Jie Han, Liyang Qin, Xiaoli Wang","submitted_at":"2025-01-13T13:47:05Z","abstract_excerpt":"Multi-modal language model has made advanced progress in vision and audio, but still faces significant challenges in dealing with complex reasoning tasks in the time series domain. The reasons are twofold. First, labels for multi-modal time series data are coarse and devoid of analysis or reasoning processes. Training with these data cannot improve the model's reasoning capabilities. Second, due to the lack of precise tokenization in processing time series, the representation patterns for temporal and textual information are inconsistent, which hampers the effectiveness of multi-modal alignmen"},"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":"2501.07335","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-13T13:47:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7bbdf3be8b408d7afa88deb48655f58fa9d5a51488b1516e448d00d08806d44a","abstract_canon_sha256":"c5a9749cb7c2d2f276bf2c8f53ddb38f4d4db4cd40d8305a620766bc7054b163"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:12.512821Z","signature_b64":"lFAxE/bUIPF1n5Af8DOE3wpA1YBB03L/Tkq5LTU5aKabXuddU40AtDTVG/CnqcVsBg/hANdUl0ISMuelyJjOBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3e32476f3f92c0dc12191e88f50170ff4a40d54d6a13b75157d16b91d07eb6e","last_reissued_at":"2026-07-05T10:26:12.512341Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:12.512341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TempoGPT: Enhancing Time Series Reasoning via Quantizing Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chunhua Yang, Haochuan Zhang, Jie Han, Liyang Qin, Xiaoli Wang","submitted_at":"2025-01-13T13:47:05Z","abstract_excerpt":"Multi-modal language model has made advanced progress in vision and audio, but still faces significant challenges in dealing with complex reasoning tasks in the time series domain. The reasons are twofold. First, labels for multi-modal time series data are coarse and devoid of analysis or reasoning processes. Training with these data cannot improve the model's reasoning capabilities. Second, due to the lack of precise tokenization in processing time series, the representation patterns for temporal and textual information are inconsistent, which hampers the effectiveness of multi-modal alignmen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07335","kind":"arxiv","version":2},"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/2501.07335/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":"2501.07335","created_at":"2026-07-05T10:26:12.512396+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.07335v2","created_at":"2026-07-05T10:26:12.512396+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07335","created_at":"2026-07-05T10:26:12.512396+00:00"},{"alias_kind":"pith_short_12","alias_value":"WPRSI5XT7EWA","created_at":"2026-07-05T10:26:12.512396+00:00"},{"alias_kind":"pith_short_16","alias_value":"WPRSI5XT7EWA3QJB","created_at":"2026-07-05T10:26:12.512396+00:00"},{"alias_kind":"pith_short_8","alias_value":"WPRSI5XT","created_at":"2026-07-05T10:26:12.512396+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30344","citing_title":"Tiny but Trusted: Efficient Vision-Language Reasoning for Time-Series Anomaly Detection","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WPRSI5XT7EWA3QJBSHUI6UAXB7","json":"https://pith.science/pith/WPRSI5XT7EWA3QJBSHUI6UAXB7.json","graph_json":"https://pith.science/api/pith-number/WPRSI5XT7EWA3QJBSHUI6UAXB7/graph.json","events_json":"https://pith.science/api/pith-number/WPRSI5XT7EWA3QJBSHUI6UAXB7/events.json","paper":"https://pith.science/paper/WPRSI5XT"},"agent_actions":{"view_html":"https://pith.science/pith/WPRSI5XT7EWA3QJBSHUI6UAXB7","download_json":"https://pith.science/pith/WPRSI5XT7EWA3QJBSHUI6UAXB7.json","view_paper":"https://pith.science/paper/WPRSI5XT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.07335&json=true","fetch_graph":"https://pith.science/api/pith-number/WPRSI5XT7EWA3QJBSHUI6UAXB7/graph.json","fetch_events":"https://pith.science/api/pith-number/WPRSI5XT7EWA3QJBSHUI6UAXB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WPRSI5XT7EWA3QJBSHUI6UAXB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WPRSI5XT7EWA3QJBSHUI6UAXB7/action/storage_attestation","attest_author":"https://pith.science/pith/WPRSI5XT7EWA3QJBSHUI6UAXB7/action/author_attestation","sign_citation":"https://pith.science/pith/WPRSI5XT7EWA3QJBSHUI6UAXB7/action/citation_signature","submit_replication":"https://pith.science/pith/WPRSI5XT7EWA3QJBSHUI6UAXB7/action/replication_record"}},"created_at":"2026-07-05T10:26:12.512396+00:00","updated_at":"2026-07-05T10:26:12.512396+00:00"}