{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NLTJ5RLJE2VCQYWNVWXHGLTOFB","short_pith_number":"pith:NLTJ5RLJ","schema_version":"1.0","canonical_sha256":"6ae69ec56926aa2862cdadae732e6e285db453fc4faffe26b1591acf86415d25","source":{"kind":"arxiv","id":"2409.18996","version":1},"attestation_state":"computed","paper":{"title":"From Linguistic Giants to Sensory Maestros: A Survey on Cross-Modal Reasoning with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","cs.MM"],"primary_cat":"cs.CL","authors_text":"Bing Wang, Changsheng Xu, Dizhan Xue, Shengsheng Qian, Zuyi Zhou","submitted_at":"2024-09-19T02:51:54Z","abstract_excerpt":"Cross-modal reasoning (CMR), the intricate process of synthesizing and drawing inferences across divergent sensory modalities, is increasingly recognized as a crucial capability in the progression toward more sophisticated and anthropomorphic artificial intelligence systems. Large Language Models (LLMs) represent a class of AI algorithms specifically engineered to parse, produce, and engage with human language on an extensive scale. The recent trend of deploying LLMs to tackle CMR tasks has marked a new mainstream of approaches for enhancing their effectiveness. This survey offers a nuanced ex"},"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":"2409.18996","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T02:51:54Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.MM"],"title_canon_sha256":"00a6e261c2dfcedd1b9fd7b1a32ecb0ea2b597f8bd72f2841cd9ed61d4ee55bd","abstract_canon_sha256":"5533af6374668ad7b65677dd1e7c6c30977fc96668b934a9215d53f7f3089c1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:09.128322Z","signature_b64":"eYQEX7nJoOu0tYoVJXDKR3pvu4SL6FphdsKTDH2ISAj+wYB/SFesjV/sGxiZwZLJ0aWGGA/v6vCJKWQZDig6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ae69ec56926aa2862cdadae732e6e285db453fc4faffe26b1591acf86415d25","last_reissued_at":"2026-07-05T09:13:09.127916Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:09.127916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Linguistic Giants to Sensory Maestros: A Survey on Cross-Modal Reasoning with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","cs.MM"],"primary_cat":"cs.CL","authors_text":"Bing Wang, Changsheng Xu, Dizhan Xue, Shengsheng Qian, Zuyi Zhou","submitted_at":"2024-09-19T02:51:54Z","abstract_excerpt":"Cross-modal reasoning (CMR), the intricate process of synthesizing and drawing inferences across divergent sensory modalities, is increasingly recognized as a crucial capability in the progression toward more sophisticated and anthropomorphic artificial intelligence systems. Large Language Models (LLMs) represent a class of AI algorithms specifically engineered to parse, produce, and engage with human language on an extensive scale. The recent trend of deploying LLMs to tackle CMR tasks has marked a new mainstream of approaches for enhancing their effectiveness. This survey offers a nuanced ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18996","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/2409.18996/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":"2409.18996","created_at":"2026-07-05T09:13:09.127969+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.18996v1","created_at":"2026-07-05T09:13:09.127969+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18996","created_at":"2026-07-05T09:13:09.127969+00:00"},{"alias_kind":"pith_short_12","alias_value":"NLTJ5RLJE2VC","created_at":"2026-07-05T09:13:09.127969+00:00"},{"alias_kind":"pith_short_16","alias_value":"NLTJ5RLJE2VCQYWN","created_at":"2026-07-05T09:13:09.127969+00:00"},{"alias_kind":"pith_short_8","alias_value":"NLTJ5RLJ","created_at":"2026-07-05T09:13:09.127969+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.03724","citing_title":"MemOS: A Memory OS for AI System","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NLTJ5RLJE2VCQYWNVWXHGLTOFB","json":"https://pith.science/pith/NLTJ5RLJE2VCQYWNVWXHGLTOFB.json","graph_json":"https://pith.science/api/pith-number/NLTJ5RLJE2VCQYWNVWXHGLTOFB/graph.json","events_json":"https://pith.science/api/pith-number/NLTJ5RLJE2VCQYWNVWXHGLTOFB/events.json","paper":"https://pith.science/paper/NLTJ5RLJ"},"agent_actions":{"view_html":"https://pith.science/pith/NLTJ5RLJE2VCQYWNVWXHGLTOFB","download_json":"https://pith.science/pith/NLTJ5RLJE2VCQYWNVWXHGLTOFB.json","view_paper":"https://pith.science/paper/NLTJ5RLJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.18996&json=true","fetch_graph":"https://pith.science/api/pith-number/NLTJ5RLJE2VCQYWNVWXHGLTOFB/graph.json","fetch_events":"https://pith.science/api/pith-number/NLTJ5RLJE2VCQYWNVWXHGLTOFB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NLTJ5RLJE2VCQYWNVWXHGLTOFB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NLTJ5RLJE2VCQYWNVWXHGLTOFB/action/storage_attestation","attest_author":"https://pith.science/pith/NLTJ5RLJE2VCQYWNVWXHGLTOFB/action/author_attestation","sign_citation":"https://pith.science/pith/NLTJ5RLJE2VCQYWNVWXHGLTOFB/action/citation_signature","submit_replication":"https://pith.science/pith/NLTJ5RLJE2VCQYWNVWXHGLTOFB/action/replication_record"}},"created_at":"2026-07-05T09:13:09.127969+00:00","updated_at":"2026-07-05T09:13:09.127969+00:00"}