{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:STRRA73JOTVFPIPEQ56MXTY7FQ","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":"a6977242d729427dd0826691048dc1f976519cd99cf09037a8e496f9bb0be0db","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-06-05T03:50:50Z","title_canon_sha256":"3e4909948d704f42394bb11f8d8f33a2767862aec66b6bd515e0fba95fa481fd"},"schema_version":"1.0","source":{"id":"1806.01483","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.01483","created_at":"2026-07-05T02:25:15Z"},{"alias_kind":"arxiv_version","alias_value":"1806.01483v2","created_at":"2026-07-05T02:25:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.01483","created_at":"2026-07-05T02:25:15Z"},{"alias_kind":"pith_short_12","alias_value":"STRRA73JOTVF","created_at":"2026-07-05T02:25:15Z"},{"alias_kind":"pith_short_16","alias_value":"STRRA73JOTVFPIPE","created_at":"2026-07-05T02:25:15Z"},{"alias_kind":"pith_short_8","alias_value":"STRRA73J","created_at":"2026-07-05T02:25:15Z"}],"graph_snapshots":[{"event_id":"sha256:81e2915d54f8a0ee034f8c1c0445ea9f0aa012100d47a3f9c55d185c78e2064d","target":"graph","created_at":"2026-07-05T02:25:15Z","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/1806.01483/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning social media content is the basis of many real-world applications, including information retrieval and recommendation systems, among others. In contrast with previous works that focus mainly on single modal or bi-modal learning, we propose to learn social media content by fusing jointly textual, acoustic, and visual information (JTAV). Effective strategies are proposed to extract fine-grained features of each modality, that is, attBiGRU and DCRNN. We also introduce cross-modal fusion and attentive pooling techniques to integrate multi-modal information comprehensively. Extensive exper","authors_text":"Haozheng Wang, Hongru Liang, Jin-Mao Wei, Jun Wang, Shaodi You, Zhenglu Yang, Zhe Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-06-05T03:50:50Z","title":"JTAV: Jointly Learning Social Media Content Representation by Fusing Textual, Acoustic, and Visual Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.01483","kind":"arxiv","version":2},"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:e8c36e254a4cb064cc7eae27ab6929c298626f37e2c436f45063b1bd29d01328","target":"record","created_at":"2026-07-05T02:25:15Z","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":"a6977242d729427dd0826691048dc1f976519cd99cf09037a8e496f9bb0be0db","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-06-05T03:50:50Z","title_canon_sha256":"3e4909948d704f42394bb11f8d8f33a2767862aec66b6bd515e0fba95fa481fd"},"schema_version":"1.0","source":{"id":"1806.01483","kind":"arxiv","version":2}},"canonical_sha256":"94e3107f6974ea57a1e4877ccbcf1f2c3a8aa84f2ba3a472ec902792e0e87fba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94e3107f6974ea57a1e4877ccbcf1f2c3a8aa84f2ba3a472ec902792e0e87fba","first_computed_at":"2026-07-05T02:25:15.263670Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:25:15.263670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GEZuyN+xgBWdVEubYJbVK8hJNIu2A/uE5vYsK7XDnOQIJZg+T36BPy8bZtn0s2o6eTwNtShTuNcWtjYaBRDSBA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:25:15.264069Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.01483","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8c36e254a4cb064cc7eae27ab6929c298626f37e2c436f45063b1bd29d01328","sha256:81e2915d54f8a0ee034f8c1c0445ea9f0aa012100d47a3f9c55d185c78e2064d"],"state_sha256":"dc07b496d7d07e1be24ecf9b47155f16e614cda6dce9e90854cde62b79d3c337"}