{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GNWLQJ73H2D3SIDFF22VP6DTRF","short_pith_number":"pith:GNWLQJ73","schema_version":"1.0","canonical_sha256":"336cb827fb3e87b920652eb557f873894ba77695be39deca7817cd866e658ef1","source":{"kind":"arxiv","id":"2410.02637","version":2},"attestation_state":"computed","paper":{"title":"Plots Unlock Time-Series Understanding in Multimodal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Desislav Ivanov, Eva Schnider, Gabriela Botea, Jing Tang, Kay Lamerigts, Marc Wilson, Mathias M.J. Bellaiche, Mayank Daswani, Michael A. Sanchez, Mikhail Papkov, Shravya Shetty, Shruthi Prabhakara, Umesh Telang, Yojan Patel","submitted_at":"2024-10-03T16:23:13Z","abstract_excerpt":"While multimodal foundation models can now natively work with data beyond text, they remain underutilized in analyzing the considerable amounts of multi-dimensional time-series data in fields like healthcare, finance, and social sciences, representing a missed opportunity for richer, data-driven insights. This paper proposes a simple but effective method that leverages the existing vision encoders of these models to \"see\" time-series data via plots, avoiding the need for additional, potentially costly, model training. Our empirical evaluations show that this approach outperforms providing the "},"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":"2410.02637","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-03T16:23:13Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"68b609c319a624f93e2152f89ab125d0145c9c2c88ac0f26269f5719ef0e284b","abstract_canon_sha256":"6321df6a5879e39b1d21085ee500f0760563596be06f8913d9387530e45015ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:42.788586Z","signature_b64":"VagN6oZE2mlgxC9VNOUiimQALyB+He9n9xhReqXnkBz0np3G+3TzNGhc8Zz6DKLs4UJsBzLllA2tEBBJXkNODg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"336cb827fb3e87b920652eb557f873894ba77695be39deca7817cd866e658ef1","last_reissued_at":"2026-07-05T09:41:42.788084Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:42.788084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Plots Unlock Time-Series Understanding in Multimodal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Desislav Ivanov, Eva Schnider, Gabriela Botea, Jing Tang, Kay Lamerigts, Marc Wilson, Mathias M.J. Bellaiche, Mayank Daswani, Michael A. Sanchez, Mikhail Papkov, Shravya Shetty, Shruthi Prabhakara, Umesh Telang, Yojan Patel","submitted_at":"2024-10-03T16:23:13Z","abstract_excerpt":"While multimodal foundation models can now natively work with data beyond text, they remain underutilized in analyzing the considerable amounts of multi-dimensional time-series data in fields like healthcare, finance, and social sciences, representing a missed opportunity for richer, data-driven insights. This paper proposes a simple but effective method that leverages the existing vision encoders of these models to \"see\" time-series data via plots, avoiding the need for additional, potentially costly, model training. Our empirical evaluations show that this approach outperforms providing the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02637","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/2410.02637/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":"2410.02637","created_at":"2026-07-05T09:41:42.788145+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02637v2","created_at":"2026-07-05T09:41:42.788145+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02637","created_at":"2026-07-05T09:41:42.788145+00:00"},{"alias_kind":"pith_short_12","alias_value":"GNWLQJ73H2D3","created_at":"2026-07-05T09:41:42.788145+00:00"},{"alias_kind":"pith_short_16","alias_value":"GNWLQJ73H2D3SIDF","created_at":"2026-07-05T09:41:42.788145+00:00"},{"alias_kind":"pith_short_8","alias_value":"GNWLQJ73","created_at":"2026-07-05T09:41:42.788145+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26320","citing_title":"MULTISEISMO: A Multimodal Seismic Dataset and Model for Cross-Modal Seismic Understanding","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09395","citing_title":"Empowering VLMs for Few-Shot Multimodal Time Series Classification via Tailored Agentic Reasoning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09395","citing_title":"Empowering VLMs for Few-Shot Multimodal Time Series Classification via Tailored Agentic Reasoning","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GNWLQJ73H2D3SIDFF22VP6DTRF","json":"https://pith.science/pith/GNWLQJ73H2D3SIDFF22VP6DTRF.json","graph_json":"https://pith.science/api/pith-number/GNWLQJ73H2D3SIDFF22VP6DTRF/graph.json","events_json":"https://pith.science/api/pith-number/GNWLQJ73H2D3SIDFF22VP6DTRF/events.json","paper":"https://pith.science/paper/GNWLQJ73"},"agent_actions":{"view_html":"https://pith.science/pith/GNWLQJ73H2D3SIDFF22VP6DTRF","download_json":"https://pith.science/pith/GNWLQJ73H2D3SIDFF22VP6DTRF.json","view_paper":"https://pith.science/paper/GNWLQJ73","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02637&json=true","fetch_graph":"https://pith.science/api/pith-number/GNWLQJ73H2D3SIDFF22VP6DTRF/graph.json","fetch_events":"https://pith.science/api/pith-number/GNWLQJ73H2D3SIDFF22VP6DTRF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GNWLQJ73H2D3SIDFF22VP6DTRF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GNWLQJ73H2D3SIDFF22VP6DTRF/action/storage_attestation","attest_author":"https://pith.science/pith/GNWLQJ73H2D3SIDFF22VP6DTRF/action/author_attestation","sign_citation":"https://pith.science/pith/GNWLQJ73H2D3SIDFF22VP6DTRF/action/citation_signature","submit_replication":"https://pith.science/pith/GNWLQJ73H2D3SIDFF22VP6DTRF/action/replication_record"}},"created_at":"2026-07-05T09:41:42.788145+00:00","updated_at":"2026-07-05T09:41:42.788145+00:00"}