{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EI7UO2HB6FRTE2MO3KNBBZUUZS","short_pith_number":"pith:EI7UO2HB","schema_version":"1.0","canonical_sha256":"223f4768e1f16332698eda9a10e694cc807183e4d9b36388a0e02cfe9d222118","source":{"kind":"arxiv","id":"2407.03418","version":1},"attestation_state":"computed","paper":{"title":"HEMM: Holistic Evaluation of Multimodal Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Akshay Goindani, Haofei Yu, Leena Mathur, Louis-Philippe Morency, Paul Pu Liang, Ruslan Salakhutdinov, Talha Chafekar","submitted_at":"2024-07-03T18:00:48Z","abstract_excerpt":"Multimodal foundation models that can holistically process text alongside images, video, audio, and other sensory modalities are increasingly used in a variety of real-world applications. However, it is challenging to characterize and study progress in multimodal foundation models, given the range of possible modeling decisions, tasks, and domains. In this paper, we introduce Holistic Evaluation of Multimodal Models (HEMM) to systematically evaluate the capabilities of multimodal foundation models across a set of 3 dimensions: basic skills, information flow, and real-world use cases. Basic mul"},"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":"2407.03418","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-03T18:00:48Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"8a70fc92a92afd28342eb76657aec993e7767a00aad5ae168bb4995c0baecd11","abstract_canon_sha256":"f2547e2290366386e9494e030dc35d550b75537488413fa4c6b8fc55f71db865"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:54.603760Z","signature_b64":"+7zojQFTQTo4ggvBmXOOZasBPNw+1SJI20gU9Pntmrekq2xxGD6fixBTTyBPtNT8mUXnKfazQL7ezF8aP+u2CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"223f4768e1f16332698eda9a10e694cc807183e4d9b36388a0e02cfe9d222118","last_reissued_at":"2026-07-05T08:39:54.603345Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:54.603345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HEMM: Holistic Evaluation of Multimodal Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Akshay Goindani, Haofei Yu, Leena Mathur, Louis-Philippe Morency, Paul Pu Liang, Ruslan Salakhutdinov, Talha Chafekar","submitted_at":"2024-07-03T18:00:48Z","abstract_excerpt":"Multimodal foundation models that can holistically process text alongside images, video, audio, and other sensory modalities are increasingly used in a variety of real-world applications. However, it is challenging to characterize and study progress in multimodal foundation models, given the range of possible modeling decisions, tasks, and domains. In this paper, we introduce Holistic Evaluation of Multimodal Models (HEMM) to systematically evaluate the capabilities of multimodal foundation models across a set of 3 dimensions: basic skills, information flow, and real-world use cases. Basic mul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03418","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/2407.03418/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":"2407.03418","created_at":"2026-07-05T08:39:54.603402+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.03418v1","created_at":"2026-07-05T08:39:54.603402+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03418","created_at":"2026-07-05T08:39:54.603402+00:00"},{"alias_kind":"pith_short_12","alias_value":"EI7UO2HB6FRT","created_at":"2026-07-05T08:39:54.603402+00:00"},{"alias_kind":"pith_short_16","alias_value":"EI7UO2HB6FRTE2MO","created_at":"2026-07-05T08:39:54.603402+00:00"},{"alias_kind":"pith_short_8","alias_value":"EI7UO2HB","created_at":"2026-07-05T08:39:54.603402+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.19676","citing_title":"Edge Intelligence in Civil Aviation: Paradigms, Techniques, and Applications","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EI7UO2HB6FRTE2MO3KNBBZUUZS","json":"https://pith.science/pith/EI7UO2HB6FRTE2MO3KNBBZUUZS.json","graph_json":"https://pith.science/api/pith-number/EI7UO2HB6FRTE2MO3KNBBZUUZS/graph.json","events_json":"https://pith.science/api/pith-number/EI7UO2HB6FRTE2MO3KNBBZUUZS/events.json","paper":"https://pith.science/paper/EI7UO2HB"},"agent_actions":{"view_html":"https://pith.science/pith/EI7UO2HB6FRTE2MO3KNBBZUUZS","download_json":"https://pith.science/pith/EI7UO2HB6FRTE2MO3KNBBZUUZS.json","view_paper":"https://pith.science/paper/EI7UO2HB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.03418&json=true","fetch_graph":"https://pith.science/api/pith-number/EI7UO2HB6FRTE2MO3KNBBZUUZS/graph.json","fetch_events":"https://pith.science/api/pith-number/EI7UO2HB6FRTE2MO3KNBBZUUZS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EI7UO2HB6FRTE2MO3KNBBZUUZS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EI7UO2HB6FRTE2MO3KNBBZUUZS/action/storage_attestation","attest_author":"https://pith.science/pith/EI7UO2HB6FRTE2MO3KNBBZUUZS/action/author_attestation","sign_citation":"https://pith.science/pith/EI7UO2HB6FRTE2MO3KNBBZUUZS/action/citation_signature","submit_replication":"https://pith.science/pith/EI7UO2HB6FRTE2MO3KNBBZUUZS/action/replication_record"}},"created_at":"2026-07-05T08:39:54.603402+00:00","updated_at":"2026-07-05T08:39:54.603402+00:00"}