{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YPLBYTYSI3UQYELEPH3Y7LCKQJ","short_pith_number":"pith:YPLBYTYS","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"},"canonical_sha256":"c3d61c4f1246e90c116479f78fac4a827d5131f40e6e941a5c5339e5137227f0","source":{"kind":"arxiv","id":"2412.16243","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16243","created_at":"2026-07-05T09:52:43Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16243v1","created_at":"2026-07-05T09:52:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16243","created_at":"2026-07-05T09:52:43Z"},{"alias_kind":"pith_short_12","alias_value":"YPLBYTYSI3UQ","created_at":"2026-07-05T09:52:43Z"},{"alias_kind":"pith_short_16","alias_value":"YPLBYTYSI3UQYELE","created_at":"2026-07-05T09:52:43Z"},{"alias_kind":"pith_short_8","alias_value":"YPLBYTYS","created_at":"2026-07-05T09:52:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YPLBYTYSI3UQYELEPH3Y7LCKQJ","target":"record","payload":{"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"},"canonical_sha256":"c3d61c4f1246e90c116479f78fac4a827d5131f40e6e941a5c5339e5137227f0","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"},"source_kind":"arxiv","source_id":"2412.16243","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":"2026-07-05T09:52:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sug1B4gHnyyqkmP1k3jtFi753ID0XJxmyfIWAd0TAKG0qSX2cBWqmZT6BbupSqrvNOBbayqx93cda8ZBRAPsDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:07:04.727438Z"},"content_sha256":"b4d5234c5d5fe9da4344416392db8152f242ca811eae985512bd5c7569da3024","schema_version":"1.0","event_id":"sha256:b4d5234c5d5fe9da4344416392db8152f242ca811eae985512bd5c7569da3024"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YPLBYTYSI3UQYELEPH3Y7LCKQJ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:52:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2u/SQ2VhiLaosXrDZc05w2Mu4ji48XsvskIfAYPM/aLPQwuvqttx1dhS3ia3zW6SRiD2Rgg+V6px4o9Hw8BMBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:07:04.727815Z"},"content_sha256":"a5b6cf075705491c91b0e79ff41e9b242cd54d5d31cc5b9bbefda04ffa9372bd","schema_version":"1.0","event_id":"sha256:a5b6cf075705491c91b0e79ff41e9b242cd54d5d31cc5b9bbefda04ffa9372bd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YPLBYTYSI3UQYELEPH3Y7LCKQJ/bundle.json","state_url":"https://pith.science/pith/YPLBYTYSI3UQYELEPH3Y7LCKQJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YPLBYTYSI3UQYELEPH3Y7LCKQJ/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":"2026-08-04T11:07:04Z","links":{"resolver":"https://pith.science/pith/YPLBYTYSI3UQYELEPH3Y7LCKQJ","bundle":"https://pith.science/pith/YPLBYTYSI3UQYELEPH3Y7LCKQJ/bundle.json","state":"https://pith.science/pith/YPLBYTYSI3UQYELEPH3Y7LCKQJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YPLBYTYSI3UQYELEPH3Y7LCKQJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YPLBYTYSI3UQYELEPH3Y7LCKQJ","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":"fd4e34f9d1998bf66b3d4f641c2d7a329d7a70eb7dcc620071c0502868b8d904","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T20:52:10Z","title_canon_sha256":"6b32a699f3fe686e13ba53f1b67b15910557bf21208ce99b23d88b3ec31890ea"},"schema_version":"1.0","source":{"id":"2412.16243","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16243","created_at":"2026-07-05T09:52:43Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16243v1","created_at":"2026-07-05T09:52:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16243","created_at":"2026-07-05T09:52:43Z"},{"alias_kind":"pith_short_12","alias_value":"YPLBYTYSI3UQ","created_at":"2026-07-05T09:52:43Z"},{"alias_kind":"pith_short_16","alias_value":"YPLBYTYSI3UQYELE","created_at":"2026-07-05T09:52:43Z"},{"alias_kind":"pith_short_8","alias_value":"YPLBYTYS","created_at":"2026-07-05T09:52:43Z"}],"graph_snapshots":[{"event_id":"sha256:a5b6cf075705491c91b0e79ff41e9b242cd54d5d31cc5b9bbefda04ffa9372bd","target":"graph","created_at":"2026-07-05T09:52:43Z","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/2412.16243/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Gerald Friedland, Tong He, Zhiqiang Tang, Zihan Zhong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T20:52:10Z","title":"Bag of Tricks for Multimodal AutoML with Image, Text, and Tabular Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16243","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:b4d5234c5d5fe9da4344416392db8152f242ca811eae985512bd5c7569da3024","target":"record","created_at":"2026-07-05T09:52:43Z","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":"fd4e34f9d1998bf66b3d4f641c2d7a329d7a70eb7dcc620071c0502868b8d904","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T20:52:10Z","title_canon_sha256":"6b32a699f3fe686e13ba53f1b67b15910557bf21208ce99b23d88b3ec31890ea"},"schema_version":"1.0","source":{"id":"2412.16243","kind":"arxiv","version":1}},"canonical_sha256":"c3d61c4f1246e90c116479f78fac4a827d5131f40e6e941a5c5339e5137227f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3d61c4f1246e90c116479f78fac4a827d5131f40e6e941a5c5339e5137227f0","first_computed_at":"2026-07-05T09:52:43.598610Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:43.598610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Eh0i3CSjghWfoBLq3+QrsFO1eSfpOIuEjwumq3wSZlzYgqglEwpStIDJ08cBH8oNN6znldhh4UNASRoRhVlSAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:43.599171Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.16243","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4d5234c5d5fe9da4344416392db8152f242ca811eae985512bd5c7569da3024","sha256:a5b6cf075705491c91b0e79ff41e9b242cd54d5d31cc5b9bbefda04ffa9372bd"],"state_sha256":"c21ee55c8fa3a1e409d94dc111225a576c3ff4abe4bd29d7fd8b7204dc5a70fa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5ZwjTyqzvoFQnVYhitviK2kE2CTGzpItc68j865tVZsfqHioFzIcU2qGHEaOKj4PXPLxHJyCM1JrqUeN6+MVDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T11:07:04.730438Z","bundle_sha256":"585715027b0a98b7de58473607352db747225247f1e7fbf461272890723f49e2"}}