{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:GPHXZZDEGZKNG7DHFAGG5RAYPH","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":"45dde9b4e8af14ee31aed2bf41e2daf6da186360aa73df1aa05c9d65658b2edf","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-29T19:10:06Z","title_canon_sha256":"7e4e5e5299d5f944046751a4b972e1b0831fae2fcbfa9fe9fee1701c88b7e959"},"schema_version":"1.0","source":{"id":"1905.12681","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.12681","created_at":"2026-07-05T00:52:26Z"},{"alias_kind":"arxiv_version","alias_value":"1905.12681v5","created_at":"2026-07-05T00:52:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12681","created_at":"2026-07-05T00:52:26Z"},{"alias_kind":"pith_short_12","alias_value":"GPHXZZDEGZKN","created_at":"2026-07-05T00:52:26Z"},{"alias_kind":"pith_short_16","alias_value":"GPHXZZDEGZKNG7DH","created_at":"2026-07-05T00:52:26Z"},{"alias_kind":"pith_short_8","alias_value":"GPHXZZDE","created_at":"2026-07-05T00:52:26Z"}],"graph_snapshots":[{"event_id":"sha256:1b74055ddece961b4adcd7e57865eccb26c568c3bfe91fdf698fefbecb00484d","target":"graph","created_at":"2026-07-05T00:52:26Z","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/1905.12681/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Consider end-to-end training of a multi-modal vs. a single-modal network on a task with multiple input modalities: the multi-modal network receives more information, so it should match or outperform its single-modal counterpart. In our experiments, however, we observe the opposite: the best single-modal network always outperforms the multi-modal network. This observation is consistent across different combinations of modalities and on different tasks and benchmarks.\n  This paper identifies two main causes for this performance drop: first, multi-modal networks are often prone to overfitting due","authors_text":"Du Tran, Matt Feiszli, Weiyao Wang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-29T19:10:06Z","title":"What Makes Training Multi-Modal Classification Networks Hard?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12681","kind":"arxiv","version":5},"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":"sha256:600e9a6adf4df310bcd62b6185d92d14a38d0b35765e4b1703da00b6b53d0c6f","target":"record","created_at":"2026-07-05T00:52:26Z","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":"45dde9b4e8af14ee31aed2bf41e2daf6da186360aa73df1aa05c9d65658b2edf","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-29T19:10:06Z","title_canon_sha256":"7e4e5e5299d5f944046751a4b972e1b0831fae2fcbfa9fe9fee1701c88b7e959"},"schema_version":"1.0","source":{"id":"1905.12681","kind":"arxiv","version":5}},"canonical_sha256":"33cf7ce4643654d37c67280c6ec41879e703376cfab5c7b3fc6ad4566b357303","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33cf7ce4643654d37c67280c6ec41879e703376cfab5c7b3fc6ad4566b357303","first_computed_at":"2026-07-05T00:52:26.664944Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:52:26.664944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WK/TFqXiBFTYKL4Vq7bMe26zOX2nXNZd3j2UDfT2wA39q37cWxtqMNA2ThC9xUCkb00NqsQdTU7diRUU9bavBw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:52:26.665279Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.12681","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:600e9a6adf4df310bcd62b6185d92d14a38d0b35765e4b1703da00b6b53d0c6f","sha256:1b74055ddece961b4adcd7e57865eccb26c568c3bfe91fdf698fefbecb00484d"],"state_sha256":"350cf1472ae67d07173699be34c5a67e4a39383256c13dac4792569c0518d97f"}