{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3HSZDL5Z55IGSXRXUQBK3EOWY7","short_pith_number":"pith:3HSZDL5Z","schema_version":"1.0","canonical_sha256":"d9e591afb9ef50695e37a402ad91d6c7c00089ca4d294d16f39cb2566cd478a7","source":{"kind":"arxiv","id":"2407.05036","version":1},"attestation_state":"computed","paper":{"title":"Enhance the Robustness of Text-Centric Multimodal Alignments","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Keng-Te Liao, Shou-De Lin, Ting-Yu Yen, Yun-Da Tsai","submitted_at":"2024-07-06T10:12:29Z","abstract_excerpt":"Converting different modalities into general text, serving as input prompts for large language models (LLMs), is a common method to align multimodal models when there is limited pairwise data. This text-centric approach leverages the unique properties of text as a modality space, transforming diverse inputs into a unified textual representation. This enables downstream models to effectively interpret various modal inputs. This study assesses the quality and robustness of multimodal representations in the presence of missing entries, noise, or absent modalities, revealing that current text-cent"},"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":"2407.05036","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-06T10:12:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fa710d7b380d643d70cf60375772b2cd7cc410065afde484757c24cd6047157e","abstract_canon_sha256":"f50ee824104ea1a0e1e4915e63979614a1241d2eccc4a5c0fe4882d8995aaeea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:07.074089Z","signature_b64":"K7rler48nTFM4eRRwKzURszHwht+IU6JYxFvu1QhRwUanEffzaaW1aOF/CbcbYhUXZjTvg0+wpw6pFwa+38tDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9e591afb9ef50695e37a402ad91d6c7c00089ca4d294d16f39cb2566cd478a7","last_reissued_at":"2026-07-05T08:41:07.073657Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:07.073657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhance the Robustness of Text-Centric Multimodal Alignments","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Keng-Te Liao, Shou-De Lin, Ting-Yu Yen, Yun-Da Tsai","submitted_at":"2024-07-06T10:12:29Z","abstract_excerpt":"Converting different modalities into general text, serving as input prompts for large language models (LLMs), is a common method to align multimodal models when there is limited pairwise data. This text-centric approach leverages the unique properties of text as a modality space, transforming diverse inputs into a unified textual representation. This enables downstream models to effectively interpret various modal inputs. This study assesses the quality and robustness of multimodal representations in the presence of missing entries, noise, or absent modalities, revealing that current text-cent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05036","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/2407.05036/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":"2407.05036","created_at":"2026-07-05T08:41:07.073720+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.05036v1","created_at":"2026-07-05T08:41:07.073720+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05036","created_at":"2026-07-05T08:41:07.073720+00:00"},{"alias_kind":"pith_short_12","alias_value":"3HSZDL5Z55IG","created_at":"2026-07-05T08:41:07.073720+00:00"},{"alias_kind":"pith_short_16","alias_value":"3HSZDL5Z55IGSXRX","created_at":"2026-07-05T08:41:07.073720+00:00"},{"alias_kind":"pith_short_8","alias_value":"3HSZDL5Z","created_at":"2026-07-05T08:41:07.073720+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.22359","citing_title":"Concept-Level AI for Telecom: Moving Beyond Large Language Models","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3HSZDL5Z55IGSXRXUQBK3EOWY7","json":"https://pith.science/pith/3HSZDL5Z55IGSXRXUQBK3EOWY7.json","graph_json":"https://pith.science/api/pith-number/3HSZDL5Z55IGSXRXUQBK3EOWY7/graph.json","events_json":"https://pith.science/api/pith-number/3HSZDL5Z55IGSXRXUQBK3EOWY7/events.json","paper":"https://pith.science/paper/3HSZDL5Z"},"agent_actions":{"view_html":"https://pith.science/pith/3HSZDL5Z55IGSXRXUQBK3EOWY7","download_json":"https://pith.science/pith/3HSZDL5Z55IGSXRXUQBK3EOWY7.json","view_paper":"https://pith.science/paper/3HSZDL5Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.05036&json=true","fetch_graph":"https://pith.science/api/pith-number/3HSZDL5Z55IGSXRXUQBK3EOWY7/graph.json","fetch_events":"https://pith.science/api/pith-number/3HSZDL5Z55IGSXRXUQBK3EOWY7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3HSZDL5Z55IGSXRXUQBK3EOWY7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3HSZDL5Z55IGSXRXUQBK3EOWY7/action/storage_attestation","attest_author":"https://pith.science/pith/3HSZDL5Z55IGSXRXUQBK3EOWY7/action/author_attestation","sign_citation":"https://pith.science/pith/3HSZDL5Z55IGSXRXUQBK3EOWY7/action/citation_signature","submit_replication":"https://pith.science/pith/3HSZDL5Z55IGSXRXUQBK3EOWY7/action/replication_record"}},"created_at":"2026-07-05T08:41:07.073720+00:00","updated_at":"2026-07-05T08:41:07.073720+00:00"}