{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6ZCVU6YCR2GZA7US6VQPPCWABH","short_pith_number":"pith:6ZCVU6YC","schema_version":"1.0","canonical_sha256":"f6455a7b028e8d907e92f560f78ac009eaa6d43c25fee9c8f2ab70802ba573de","source":{"kind":"arxiv","id":"2302.13311","version":1},"attestation_state":"computed","paper":{"title":"Understanding Social Media Cross-Modality Discourse in Linguistic Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SI"],"primary_cat":"cs.MM","authors_text":"Chunpu Xu, Hanzhuo Tan, Jing Li, Piji Li","submitted_at":"2023-02-26T13:04:04Z","abstract_excerpt":"The multimedia communications with texts and images are popular on social media. However, limited studies concern how images are structured with texts to form coherent meanings in human cognition. To fill in the gap, we present a novel concept of cross-modality discourse, reflecting how human readers couple image and text understandings. Text descriptions are first derived from images (named as subtitles) in the multimedia contexts. Five labels -- entity-level insertion, projection and concretization and scene-level restatement and extension -- are further employed to shape the structure of su"},"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":"2302.13311","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2023-02-26T13:04:04Z","cross_cats_sorted":["cs.CL","cs.SI"],"title_canon_sha256":"987fb3c8b000c1459ef70efbc5680dcb36a5ba5bf3b5a906308d61216350c700","abstract_canon_sha256":"785f64489124526d8b21af0567e1c778448c79c11793f44f4386a50f4789d1f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:45.608725Z","signature_b64":"dlSDdREzcUnGGly7BwrgFqdi/24hLfdV0stcxpuZqOXS1cfpsqGBdViUlDuUosGv+d4thSsKLtcZ3xQvxXDIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6455a7b028e8d907e92f560f78ac009eaa6d43c25fee9c8f2ab70802ba573de","last_reissued_at":"2026-07-05T05:45:45.608263Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:45.608263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Social Media Cross-Modality Discourse in Linguistic Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SI"],"primary_cat":"cs.MM","authors_text":"Chunpu Xu, Hanzhuo Tan, Jing Li, Piji Li","submitted_at":"2023-02-26T13:04:04Z","abstract_excerpt":"The multimedia communications with texts and images are popular on social media. However, limited studies concern how images are structured with texts to form coherent meanings in human cognition. To fill in the gap, we present a novel concept of cross-modality discourse, reflecting how human readers couple image and text understandings. Text descriptions are first derived from images (named as subtitles) in the multimedia contexts. Five labels -- entity-level insertion, projection and concretization and scene-level restatement and extension -- are further employed to shape the structure of su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.13311","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/2302.13311/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":"2302.13311","created_at":"2026-07-05T05:45:45.608327+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.13311v1","created_at":"2026-07-05T05:45:45.608327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.13311","created_at":"2026-07-05T05:45:45.608327+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ZCVU6YCR2GZ","created_at":"2026-07-05T05:45:45.608327+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ZCVU6YCR2GZA7US","created_at":"2026-07-05T05:45:45.608327+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ZCVU6YC","created_at":"2026-07-05T05:45:45.608327+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.08267","citing_title":"TriMod Fusion for Multimodal Named Entity Recognition in Social Media","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6ZCVU6YCR2GZA7US6VQPPCWABH","json":"https://pith.science/pith/6ZCVU6YCR2GZA7US6VQPPCWABH.json","graph_json":"https://pith.science/api/pith-number/6ZCVU6YCR2GZA7US6VQPPCWABH/graph.json","events_json":"https://pith.science/api/pith-number/6ZCVU6YCR2GZA7US6VQPPCWABH/events.json","paper":"https://pith.science/paper/6ZCVU6YC"},"agent_actions":{"view_html":"https://pith.science/pith/6ZCVU6YCR2GZA7US6VQPPCWABH","download_json":"https://pith.science/pith/6ZCVU6YCR2GZA7US6VQPPCWABH.json","view_paper":"https://pith.science/paper/6ZCVU6YC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.13311&json=true","fetch_graph":"https://pith.science/api/pith-number/6ZCVU6YCR2GZA7US6VQPPCWABH/graph.json","fetch_events":"https://pith.science/api/pith-number/6ZCVU6YCR2GZA7US6VQPPCWABH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ZCVU6YCR2GZA7US6VQPPCWABH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ZCVU6YCR2GZA7US6VQPPCWABH/action/storage_attestation","attest_author":"https://pith.science/pith/6ZCVU6YCR2GZA7US6VQPPCWABH/action/author_attestation","sign_citation":"https://pith.science/pith/6ZCVU6YCR2GZA7US6VQPPCWABH/action/citation_signature","submit_replication":"https://pith.science/pith/6ZCVU6YCR2GZA7US6VQPPCWABH/action/replication_record"}},"created_at":"2026-07-05T05:45:45.608327+00:00","updated_at":"2026-07-05T05:45:45.608327+00:00"}