{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Y3VIMQFL26KS4GZEOKLIPQGXQC","short_pith_number":"pith:Y3VIMQFL","schema_version":"1.0","canonical_sha256":"c6ea8640abd7952e1b24729687c0d780a6f909ca13d077ac699684f97ec8dfe1","source":{"kind":"arxiv","id":"2212.14453","version":2},"attestation_state":"computed","paper":{"title":"Learning Multimodal Data Augmentation in Feature Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Andrew Gordon Wilson, Anshumali Shrivastava, Aston Zhang, Mu Li, Xingjian Shi, Zhiqiang Tang, Zichang Liu","submitted_at":"2022-12-29T20:39:36Z","abstract_excerpt":"The ability to jointly learn from multiple modalities, such as text, audio, and visual data, is a defining feature of intelligent systems. While there have been promising advances in designing neural networks to harness multimodal data, the enormous success of data augmentation currently remains limited to single-modality tasks like image classification. Indeed, it is particularly difficult to augment each modality while preserving the overall semantic structure of the data; for example, a caption may no longer be a good description of an image after standard augmentations have been applied, s"},"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":"2212.14453","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-29T20:39:36Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"86923dc0257d40133bb2ce70463cb90ff476e85973c52550fd8a2e8dd0354310","abstract_canon_sha256":"7755caaa7899839930acf72088763260828ab6fde3362428d0fa44c4bdd57da5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:03:45.896072Z","signature_b64":"GBhi+kFp+C9BhshOVa5eKhS9VGGq5+1c9G44dUsMo71hO1FOAYh2SyyRICZ/RYdNi8S4etbzN03wt6wSnO3YAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6ea8640abd7952e1b24729687c0d780a6f909ca13d077ac699684f97ec8dfe1","last_reissued_at":"2026-07-05T06:03:45.895627Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:03:45.895627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Multimodal Data Augmentation in Feature Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Andrew Gordon Wilson, Anshumali Shrivastava, Aston Zhang, Mu Li, Xingjian Shi, Zhiqiang Tang, Zichang Liu","submitted_at":"2022-12-29T20:39:36Z","abstract_excerpt":"The ability to jointly learn from multiple modalities, such as text, audio, and visual data, is a defining feature of intelligent systems. While there have been promising advances in designing neural networks to harness multimodal data, the enormous success of data augmentation currently remains limited to single-modality tasks like image classification. Indeed, it is particularly difficult to augment each modality while preserving the overall semantic structure of the data; for example, a caption may no longer be a good description of an image after standard augmentations have been applied, s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.14453","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/2212.14453/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":"2212.14453","created_at":"2026-07-05T06:03:45.895688+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.14453v2","created_at":"2026-07-05T06:03:45.895688+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.14453","created_at":"2026-07-05T06:03:45.895688+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y3VIMQFL26KS","created_at":"2026-07-05T06:03:45.895688+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y3VIMQFL26KS4GZE","created_at":"2026-07-05T06:03:45.895688+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y3VIMQFL","created_at":"2026-07-05T06:03:45.895688+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y3VIMQFL26KS4GZEOKLIPQGXQC","json":"https://pith.science/pith/Y3VIMQFL26KS4GZEOKLIPQGXQC.json","graph_json":"https://pith.science/api/pith-number/Y3VIMQFL26KS4GZEOKLIPQGXQC/graph.json","events_json":"https://pith.science/api/pith-number/Y3VIMQFL26KS4GZEOKLIPQGXQC/events.json","paper":"https://pith.science/paper/Y3VIMQFL"},"agent_actions":{"view_html":"https://pith.science/pith/Y3VIMQFL26KS4GZEOKLIPQGXQC","download_json":"https://pith.science/pith/Y3VIMQFL26KS4GZEOKLIPQGXQC.json","view_paper":"https://pith.science/paper/Y3VIMQFL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.14453&json=true","fetch_graph":"https://pith.science/api/pith-number/Y3VIMQFL26KS4GZEOKLIPQGXQC/graph.json","fetch_events":"https://pith.science/api/pith-number/Y3VIMQFL26KS4GZEOKLIPQGXQC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y3VIMQFL26KS4GZEOKLIPQGXQC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y3VIMQFL26KS4GZEOKLIPQGXQC/action/storage_attestation","attest_author":"https://pith.science/pith/Y3VIMQFL26KS4GZEOKLIPQGXQC/action/author_attestation","sign_citation":"https://pith.science/pith/Y3VIMQFL26KS4GZEOKLIPQGXQC/action/citation_signature","submit_replication":"https://pith.science/pith/Y3VIMQFL26KS4GZEOKLIPQGXQC/action/replication_record"}},"created_at":"2026-07-05T06:03:45.895688+00:00","updated_at":"2026-07-05T06:03:45.895688+00:00"}