{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YPLBYTYSI3UQYELEPH3Y7LCKQJ","short_pith_number":"pith:YPLBYTYS","schema_version":"1.0","canonical_sha256":"c3d61c4f1246e90c116479f78fac4a827d5131f40e6e941a5c5339e5137227f0","source":{"kind":"arxiv","id":"2412.16243","version":1},"attestation_state":"computed","paper":{"title":"Bag of Tricks for Multimodal AutoML with Image, Text, and Tabular Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gerald Friedland, Tong He, Zhiqiang Tang, Zihan Zhong","submitted_at":"2024-12-19T20:52:10Z","abstract_excerpt":"This paper studies the best practices for automatic machine learning (AutoML). While previous AutoML efforts have predominantly focused on unimodal data, the multimodal aspect remains under-explored. Our study delves into classification and regression problems involving flexible combinations of image, text, and tabular data. We curate a benchmark comprising 22 multimodal datasets from diverse real-world applications, encompassing all 4 combinations of the 3 modalities. Across this benchmark, we scrutinize design choices related to multimodal fusion strategies, multimodal data augmentation, con"},"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":"2412.16243","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T20:52:10Z","cross_cats_sorted":[],"title_canon_sha256":"6b32a699f3fe686e13ba53f1b67b15910557bf21208ce99b23d88b3ec31890ea","abstract_canon_sha256":"fd4e34f9d1998bf66b3d4f641c2d7a329d7a70eb7dcc620071c0502868b8d904"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:43.599171Z","signature_b64":"Eh0i3CSjghWfoBLq3+QrsFO1eSfpOIuEjwumq3wSZlzYgqglEwpStIDJ08cBH8oNN6znldhh4UNASRoRhVlSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3d61c4f1246e90c116479f78fac4a827d5131f40e6e941a5c5339e5137227f0","last_reissued_at":"2026-07-05T09:52:43.598610Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:43.598610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bag of Tricks for Multimodal AutoML with Image, Text, and Tabular Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gerald Friedland, Tong He, Zhiqiang Tang, Zihan Zhong","submitted_at":"2024-12-19T20:52:10Z","abstract_excerpt":"This paper studies the best practices for automatic machine learning (AutoML). While previous AutoML efforts have predominantly focused on unimodal data, the multimodal aspect remains under-explored. Our study delves into classification and regression problems involving flexible combinations of image, text, and tabular data. We curate a benchmark comprising 22 multimodal datasets from diverse real-world applications, encompassing all 4 combinations of the 3 modalities. Across this benchmark, we scrutinize design choices related to multimodal fusion strategies, multimodal data augmentation, con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16243","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/2412.16243/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":"2412.16243","created_at":"2026-07-05T09:52:43.598673+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.16243v1","created_at":"2026-07-05T09:52:43.598673+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16243","created_at":"2026-07-05T09:52:43.598673+00:00"},{"alias_kind":"pith_short_12","alias_value":"YPLBYTYSI3UQ","created_at":"2026-07-05T09:52:43.598673+00:00"},{"alias_kind":"pith_short_16","alias_value":"YPLBYTYSI3UQYELE","created_at":"2026-07-05T09:52:43.598673+00:00"},{"alias_kind":"pith_short_8","alias_value":"YPLBYTYS","created_at":"2026-07-05T09:52:43.598673+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30410","citing_title":"Beyond IID: How General Are Tabular Foundation Models, Really?","ref_index":117,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08146","citing_title":"VT-Bench: A Unified Benchmark for Visual-Tabular Multi-Modal Learning","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2602.20223","citing_title":"MultiModalPFN: Extending Prior-Data Fitted Networks for Multimodal Tabular Learning","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08146","citing_title":"VT-Bench: A Unified Benchmark for Visual-Tabular Multi-Modal Learning","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10616","citing_title":"MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image","ref_index":98,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YPLBYTYSI3UQYELEPH3Y7LCKQJ","json":"https://pith.science/pith/YPLBYTYSI3UQYELEPH3Y7LCKQJ.json","graph_json":"https://pith.science/api/pith-number/YPLBYTYSI3UQYELEPH3Y7LCKQJ/graph.json","events_json":"https://pith.science/api/pith-number/YPLBYTYSI3UQYELEPH3Y7LCKQJ/events.json","paper":"https://pith.science/paper/YPLBYTYS"},"agent_actions":{"view_html":"https://pith.science/pith/YPLBYTYSI3UQYELEPH3Y7LCKQJ","download_json":"https://pith.science/pith/YPLBYTYSI3UQYELEPH3Y7LCKQJ.json","view_paper":"https://pith.science/paper/YPLBYTYS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.16243&json=true","fetch_graph":"https://pith.science/api/pith-number/YPLBYTYSI3UQYELEPH3Y7LCKQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/YPLBYTYSI3UQYELEPH3Y7LCKQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YPLBYTYSI3UQYELEPH3Y7LCKQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YPLBYTYSI3UQYELEPH3Y7LCKQJ/action/storage_attestation","attest_author":"https://pith.science/pith/YPLBYTYSI3UQYELEPH3Y7LCKQJ/action/author_attestation","sign_citation":"https://pith.science/pith/YPLBYTYSI3UQYELEPH3Y7LCKQJ/action/citation_signature","submit_replication":"https://pith.science/pith/YPLBYTYSI3UQYELEPH3Y7LCKQJ/action/replication_record"}},"created_at":"2026-07-05T09:52:43.598673+00:00","updated_at":"2026-07-05T09:52:43.598673+00:00"}