{"as_of":"2026-08-17T17:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6d0dad8f9df0ff6420f9d412b954d6366c25f455a41e6a00225bd54d18357db6","coverage":[{"denominator":27,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":27,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T15:42:27.730663Z","state":"measured"},{"denominator":27,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":27,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2505.14143/citation-record","integrity":"/paper/2505.14143/integrity","json":"/paper/2505.14143/citation-record.json","paper":"/paper/2505.14143"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:34.522214Z","title":"Multi-task learning for multi-modal emotion recognition and sentiment analysis,","venue":null,"work_id":"033b71ff-12f4-4364-84c2-637db042d605","year":2019},"citing_paper":{"arxiv_id":"2505.14143","last_updated":"2025-05-20T09:46:56Z","snapshot_observed_at":"2026-08-07T15:37:24.569922Z","submitted_at":"2025-05-20T09:46:56Z","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:25.258419Z"},"links":{"citing_paper":"/paper/2505.14143"},"observation_digest":"sha256:26f406c3fa02d1dff1fd6e8a2f31284eaf692af9651c7c350beb7fab4a3a194f","observation_id":"e8575aba-1b68-4e1b-85a7-d8b4188f5e11","resolution":{"observed_at":"2026-08-07T15:42:34.660379Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:34.332432Z","title":"UniMSE: Towards unified multimodal sentiment analysis and emotion recognition,","venue":null,"work_id":"76d3bde0-c0f4-4c32-9157-51e5a09dfabf","year":2022},"citing_paper":{"arxiv_id":"2505.14143","last_updated":"2025-05-20T09:46:56Z","snapshot_observed_at":"2026-08-07T15:37:24.569922Z","submitted_at":"2025-05-20T09:46:56Z","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:25.318818Z"},"links":{"citing_paper":"/paper/2505.14143"},"observation_digest":"sha256:c53682b1a7ada67a75b8739ffc681b0d17923b6626ce5b22ff64165660f850de","observation_id":"699b33f6-380f-434d-b4d5-1d1fd6a9670c","resolution":{"observed_at":"2026-08-07T15:42:34.442809Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:34.169959Z","title":"Progres- sive layered extraction (ple): A novel multi-task learning (mtl) model for personalized recommendations,","venue":null,"work_id":"eeba9cec-fc30-4137-aa86-a9c0ac82b75e","year":2020},"citing_paper":{"arxiv_id":"2505.14143","last_updated":"2025-05-20T09:46:56Z","snapshot_observed_at":"2026-08-07T15:37:24.569922Z","submitted_at":"2025-05-20T09:46:56Z","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:25.389273Z"},"links":{"citing_paper":"/paper/2505.14143"},"observation_digest":"sha256:bceb9933f72e24896a3c3aa4378faa57e11e65d1dcfbf2982874628fd909ea70","observation_id":"7576069d-5897-4c32-9950-493fc14ef6e5","resolution":{"observed_at":"2026-08-07T15:42:34.253598Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:34.002942Z","title":"Adaptive mixtures of local experts,","venue":null,"work_id":"e3e1931c-53e7-4526-bd78-219b86aee87b","year":1991},"citing_paper":{"arxiv_id":"2505.14143","last_updated":"2025-05-20T09:46:56Z","snapshot_observed_at":"2026-08-07T15:37:24.569922Z","submitted_at":"2025-05-20T09:46:56Z","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:25.454011Z"},"links":{"citing_paper":"/paper/2505.14143"},"observation_digest":"sha256:0eb959c0c21268d4b0c142ba6f48ec4b650344e788d67406a061c4109f530e25","observation_id":"b7273d97-45d6-4906-9e22-c8e8c5e18745","resolution":{"observed_at":"2026-08-07T15:42:34.083700Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:33.814523Z","title":"Multi-task dense prediction via mixture of low-rank experts,","venue":null,"work_id":"54184b1f-86bb-4786-ba69-38a79e9a3db7","year":2024},"citing_paper":{"arxiv_id":"2505.14143","last_updated":"2025-05-20T09:46:56Z","snapshot_observed_at":"2026-08-07T15:37:24.569922Z","submitted_at":"2025-05-20T09:46:56Z","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:25.522523Z"},"links":{"citing_paper":"/paper/2505.14143"},"observation_digest":"sha256:e494ea715c4cca8d83d98315b69b75a11656a952b255e154212184bf76f0a80a","observation_id":"05db8619-b891-4a18-a731-936545211943","resolution":{"observed_at":"2026-08-07T15:42:33.893597Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:33.629211Z","title":"Multimodal multi-loss fusion network for sentiment analysis,","venue":null,"work_id":"9d49162c-96db-420a-ba20-31c0013d1b62","year":2024},"citing_paper":{"arxiv_id":"2505.14143","last_updated":"2025-05-20T09:46:56Z","snapshot_observed_at":"2026-08-07T15:37:24.569922Z","submitted_at":"2025-05-20T09:46:56Z","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:25.584645Z"},"links":{"citing_paper":"/paper/2505.14143"},"observation_digest":"sha256:7c7d1f7d2f07777ac291e1f1ab20158f091c25bfb6464e0832cf50b2acfcb08e","observation_id":"cadf77c8-6043-4de7-b168-429a27b23cc8","resolution":{"observed_at":"2026-08-07T15:42:33.741535Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:33.456054Z","title":"Multimodal trans- former for unaligned multimodal language sequences,","venue":null,"work_id":"216aad5f-c3b4-4ca6-a06d-51644900656c","year":2019},"citing_paper":{"arxiv_id":"2505.14143","last_updated":"2025-05-20T09:46:56Z","snapshot_observed_at":"2026-08-07T15:37:24.569922Z","submitted_at":"2025-05-20T09:46:56Z","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:25.644779Z"},"links":{"citing_paper":"/paper/2505.14143"},"observation_digest":"sha256:ff58de3aa810b1863ed3c105bc69f0a7c33359ed8326de194f1202f99e44ec06","observation_id":"dc87dba0-4857-4695-9e08-e7914974ba73","resolution":{"observed_at":"2026-08-07T15:42:33.543705Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:33.285689Z","title":"Hybrid contrastive learning of tri-modal representation for multimodal sentiment analysis,","venue":null,"work_id":"97dd794c-a7cd-49b8-8efc-903290e01e93","year":2023},"citing_paper":{"arxiv_id":"2505.14143","last_updated":"2025-05-20T09:46:56Z","snapshot_observed_at":"2026-08-07T15:37:24.569922Z","submitted_at":"2025-05-20T09:46:56Z","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:25.727953Z"},"links":{"citing_paper":"/paper/2505.14143"},"observation_digest":"sha256:bc54ca1f9732cfb6f7ac3046a4cfe0e71f6dd2a58d3529114971722787aed9e0","observation_id":"693ea582-416c-4be4-8cfc-9d7b03055c21","resolution":{"observed_at":"2026-08-07T15:42:33.351025Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:33.100511Z","title":"COGMEN: COntextualized GNN based multimodal emotion recognitioN,","venue":null,"work_id":"f496101e-b9bf-4d85-b2d3-19c4e42473b5","year":2022},"citing_paper":{"arxiv_id":"2505.14143","last_updated":"2025-05-20T09:46:56Z","snapshot_observed_at":"2026-08-07T15:37:24.569922Z","submitted_at":"2025-05-20T09:46:56Z","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:25.803981Z"},"links":{"citing_paper":"/paper/2505.14143"},"observation_digest":"sha256:430b4e611ff2482b4479e988c6bb9884ba18917a3c7ea4f99b9e00fa91313d9f","observation_id":"1522a01e-d2e9-4688-badd-1b2f82d29d3a","resolution":{"observed_at":"2026-08-07T15:42:33.189724Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:32.947927Z","title":"Multimodal language analysis in the wild: CMU-MOSEI dataset and interpretable dynamic fusion graph,","venue":null,"work_id":"101699d6-e60b-48d0-8322-73159b569cac","year":2018},"citing_paper":{"arxiv_id":"2505.14143","last_updated":"2025-05-20T09:46:56Z","snapshot_observed_at":"2026-08-07T15:37:24.569922Z","submitted_at":"2025-05-20T09:46:56Z","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:25.866609Z"},"links":{"citing_paper":"/paper/2505.14143"},"observation_digest":"sha256:7654f1a1accfe4276c51b8b468dbc08c4428bc6026563bcd162def8325d01d19","observation_id":"d58d2056-1a64-4acb-bff6-a1a983783812","resolution":{"observed_at":"2026-08-07T15:42:33.000598Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:32.773775Z","title":"Demt: deformable mixer transformer for multi-task learning of dense prediction,","venue":null,"work_id":"c61b8fab-65db-442a-b3b6-2b8eadce7f07","year":2023},"citing_paper":{"arxiv_id":"2505.14143","last_updated":"2025-05-20T09:46:56Z","snapshot_observed_at":"2026-08-07T15:37:24.569922Z","submitted_at":"2025-05-20T09:46:56Z","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:25.930686Z"},"links":{"citing_paper":"/paper/2505.14143"},"observation_digest":"sha256:2bec44048ae636cff751cb8ec764d28bd7d394dfce82a80ea44db59991f846ab","observation_id":"725f0ee8-e461-4fab-83d1-c2e276120d2d","resolution":{"observed_at":"2026-08-07T15:42:32.850030Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:32.599673Z","title":"Mod-squad: Designing mixtures of experts as modular multi-task learners,","venue":null,"work_id":"8aa4de2e-f32c-4515-8505-fbc0af7d8203","year":2023},"citing_paper":{"arxiv_id":"2505.14143","last_updated":"2025-05-20T09:46:56Z","snapshot_observed_at":"2026-08-07T15:37:24.569922Z","submitted_at":"2025-05-20T09:46:56Z","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:26.002197Z"},"links":{"citing_paper":"/paper/2505.14143"},"observation_digest":"sha256:3f00c9ee636aabe1e3e851115e60636396b9a8a9c2f8d5e5851de8ea6d49168b","observation_id":"ae59820b-2d9e-4997-ac1e-07dd1dd04602","resolution":{"observed_at":"2026-08-07T15:42:32.702412Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:32.348668Z","title":"Roberta: A robustly optimized bert pretraining approach,","venue":null,"work_id":"f80b61e1-410e-498e-8584-148f9ac65c13","year":2019},"citing_paper":{"arxiv_id":"2505.14143","last_updated":"2025-05-20T09:46:56Z","snapshot_observed_at":"2026-08-07T15:37:24.569922Z","submitted_at":"2025-05-20T09:46:56Z","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:26.063478Z"},"links":{"citing_paper":"/paper/2505.14143"},"observation_digest":"sha256:91d1d40b94ed8ace3273a722ddc09510ad385f1095decbc441166ae9fd81a176","observation_id":"bcd54648-23a9-4874-99d5-f651fc549e2b","resolution":{"observed_at":"2026-08-07T15:42:32.451989Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:31.996712Z","title":"data2vec: A general framework for self-supervised learning in speech, vision and language,","venue":null,"work_id":"d1346533-a72a-4974-bf3f-a7141ca73453","year":2022},"citing_paper":{"arxiv_id":"2505.14143","last_updated":"2025-05-20T09:46:56Z","snapshot_observed_at":"2026-08-07T15:37:24.569922Z","submitted_at":"2025-05-20T09:46:56Z","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:26.122361Z"},"links":{"citing_paper":"/paper/2505.14143"},"observation_digest":"sha256:5d667084972e966ccb2365c6597a51f467915613cbdbcad1b802c43751d6b4c4","observation_id":"d667f7fe-965f-4ac1-aba6-0a40fbb2ea6f","resolution":{"observed_at":"2026-08-07T15:42:32.133267Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:31.558341Z","title":"Multimodal sentiment intensity analysis in videos: Facial gestures and verbal messages,","venue":null,"work_id":"c4c56bab-5d87-4f70-93d5-6d5d9377b905","year":2016},"citing_paper":{"arxiv_id":"2505.14143","last_updated":"2025-05-20T09:46:56Z","snapshot_observed_at":"2026-08-07T15:37:24.569922Z","submitted_at":"2025-05-20T09:46:56Z","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:26.182736Z"},"links":{"citing_paper":"/paper/2505.14143"},"observation_digest":"sha256:2a0c71840b3ed9eac207db130e185f162381020b3bc827e4f569fa1c1c14d51d","observation_id":"3abe978f-ff3c-43d6-8e97-a1b762ca9d96","resolution":{"observed_at":"2026-08-07T15:42:31.725689Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:31.231247Z","title":"Misa: Modality-invariant and -specific representations for multimodal senti- ment analysis,","venue":null,"work_id":"3ceeb61b-08f0-4310-a9e7-b51fc7f52f57","year":2020},"citing_paper":{"arxiv_id":"2505.14143","last_updated":"2025-05-20T09:46:56Z","snapshot_observed_at":"2026-08-07T15:37:24.569922Z","submitted_at":"2025-05-20T09:46:56Z","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:26.222847Z"},"links":{"citing_paper":"/paper/2505.14143"},"observation_digest":"sha256:fc436c8534c738f7dec7205db380aef74802e6d1e2938b4d5971237325916ef4","observation_id":"89d94570-956f-48ef-916d-646561d371fc","resolution":{"observed_at":"2026-08-07T15:42:31.399302Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:31.018271Z","title":"Integrating multimodal information in large pretrained trans- formers,","venue":null,"work_id":"f99eec84-c13c-498b-b59f-2f01a36ac6fc","year":2020},"citing_paper":{"arxiv_id":"2505.14143","last_updated":"2025-05-20T09:46:56Z","snapshot_observed_at":"2026-08-07T15:37:24.569922Z","submitted_at":"2025-05-20T09:46:56Z","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:26.228871Z"},"links":{"citing_paper":"/paper/2505.14143"},"observation_digest":"sha256:a41a230bd27948b33c6ad2a0a7c95da4340d672443586d03df6ab83f909ea3f7","observation_id":"2b1f1b7c-0647-4939-b881-67e83ecf5021","resolution":{"observed_at":"2026-08-07T15:42:31.156265Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:30.688766Z","title":"Learning modality- specific representations with self-supervised multi-task learning for multimodal sentiment analysis,","venue":null,"work_id":"697ef219-1ffe-45cb-a5d3-3f8e9200db2d","year":2021},"citing_paper":{"arxiv_id":"2505.14143","last_updated":"2025-05-20T09:46:56Z","snapshot_observed_at":"2026-08-07T15:37:24.569922Z","submitted_at":"2025-05-20T09:46:56Z","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:26.325698Z"},"links":{"citing_paper":"/paper/2505.14143"},"observation_digest":"sha256:093719be593057f0d9d70f015eeca862a68b087b49ade6a7bc7159795eea6c3d","observation_id":"5ab8333f-8d99-4a92-b87f-59b9c3e126c2","resolution":{"observed_at":"2026-08-07T15:42:30.851588Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:30.310346Z","title":"Improving multimodal fu- sion with hierarchical mutual information maximization for multimodal sentiment analysis,","venue":null,"work_id":"1829b800-a308-42bd-838b-d1000b01d778","year":2021},"citing_paper":{"arxiv_id":"2505.14143","last_updated":"2025-05-20T09:46:56Z","snapshot_observed_at":"2026-08-07T15:37:24.569922Z","submitted_at":"2025-05-20T09:46:56Z","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:26.488240Z"},"links":{"citing_paper":"/paper/2505.14143"},"observation_digest":"sha256:c88fc03d452d44bb75f13d79449ee6d71eee7be4b213a6258c41b8a05d05899d","observation_id":"c6add986-6065-4a43-b75d-ad3604857e3d","resolution":{"observed_at":"2026-08-07T15:42:30.475343Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:30.093970Z","title":"Speech-text pre-training for spoken dialog understanding with explicit cross-modal alignment,","venue":null,"work_id":"cdff70b4-65ca-46e9-94f9-ac08e732dd6f","year":2023},"citing_paper":{"arxiv_id":"2505.14143","last_updated":"2025-05-20T09:46:56Z","snapshot_observed_at":"2026-08-07T15:37:24.569922Z","submitted_at":"2025-05-20T09:46:56Z","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:26.702745Z"},"links":{"citing_paper":"/paper/2505.14143"},"observation_digest":"sha256:4ce65c07e2e9f1b27262ca187f0eaa7f28a0c092903afe79874955ff2e4b3fb0","observation_id":"a71f8832-ac20-4e53-a686-515eefca42da","resolution":{"observed_at":"2026-08-07T15:42:30.195138Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:29.804238Z","title":"Multilogue-net: A context-aware RNN for multi-modal emotion detection and sentiment analysis in conversation,","venue":null,"work_id":"e3386c9d-2bc2-4bb1-9cbf-2af23f6d75fd","year":2020},"citing_paper":{"arxiv_id":"2505.14143","last_updated":"2025-05-20T09:46:56Z","snapshot_observed_at":"2026-08-07T15:37:24.569922Z","submitted_at":"2025-05-20T09:46:56Z","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:26.905347Z"},"links":{"citing_paper":"/paper/2505.14143"},"observation_digest":"sha256:8e5dd2c44116e41faed192158c99b869abe64dd3b06934a5b0f4131d1ed9ac65","observation_id":"d55e325c-436a-4eb2-8362-6b0e3d569ce9","resolution":{"observed_at":"2026-08-07T15:42:29.912593Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:29.556692Z","title":"A transformer-based joint-encoding for emotion recogni- tion and sentiment analysis,","venue":null,"work_id":"d1e75a34-943a-412f-af3c-455513193b70","year":2020},"citing_paper":{"arxiv_id":"2505.14143","last_updated":"2025-05-20T09:46:56Z","snapshot_observed_at":"2026-08-07T15:37:24.569922Z","submitted_at":"2025-05-20T09:46:56Z","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:27.075881Z"},"links":{"citing_paper":"/paper/2505.14143"},"observation_digest":"sha256:bbaf15134c1adae6c76932c4f81c0ea183f30edc3236af6f0ffd75b0f3d816a0","observation_id":"3f479aab-1b97-49c3-bbc0-e91d6fdf815e","resolution":{"observed_at":"2026-08-07T15:42:29.669252Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:29.303806Z","title":"Multimodal routing: Improving local and global interpretability of multimodal language analysis,","venue":null,"work_id":"d7e772d6-f510-4a65-82fc-5c35069a823f","year":2020},"citing_paper":{"arxiv_id":"2505.14143","last_updated":"2025-05-20T09:46:56Z","snapshot_observed_at":"2026-08-07T15:37:24.569922Z","submitted_at":"2025-05-20T09:46:56Z","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:27.224049Z"},"links":{"citing_paper":"/paper/2505.14143"},"observation_digest":"sha256:7de042c4122183bcaf94c2e2d42db747bc2e9bc12e68cc01584f4b8cf2905055","observation_id":"8f6df33e-a7fa-4678-ba43-9f2f7fb81d5f","resolution":{"observed_at":"2026-08-07T15:42:29.451202Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:28.894343Z","title":"Conversation understanding using relational temporal graph neural networks with auxiliary cross-modality interaction,","venue":null,"work_id":"23acf343-4044-480b-9a0e-51c54aa0abb7","year":2023},"citing_paper":{"arxiv_id":"2505.14143","last_updated":"2025-05-20T09:46:56Z","snapshot_observed_at":"2026-08-07T15:37:24.569922Z","submitted_at":"2025-05-20T09:46:56Z","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:27.397075Z"},"links":{"citing_paper":"/paper/2505.14143"},"observation_digest":"sha256:3a19af689e4a0d0a35d9b041d99102451abc46c6e4fc9885c2b22b01bee83e9f","observation_id":"5a15b4da-71e1-40a9-90bf-bccc16f81e2f","resolution":{"observed_at":"2026-08-07T15:42:29.082172Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:28.602563Z","title":"MELD: A multimodal multi- party dataset for emotion recognition in conversations,","venue":null,"work_id":"5b66e3bf-5d5e-4a8f-8f41-02c1e75dbc74","year":2019},"citing_paper":{"arxiv_id":"2505.14143","last_updated":"2025-05-20T09:46:56Z","snapshot_observed_at":"2026-08-07T15:37:24.569922Z","submitted_at":"2025-05-20T09:46:56Z","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:27.516921Z"},"links":{"citing_paper":"/paper/2505.14143"},"observation_digest":"sha256:330f7f1078d2eca0b3793e065f2c35a26d36f95fc48d8c8923504fa4d08b86da","observation_id":"2032773c-f0b3-4aef-8253-637567d13627","resolution":{"observed_at":"2026-08-07T15:42:28.765645Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:28.217870Z","title":"IEMOCAP: interactive emotional dyadic motion capture database,","venue":null,"work_id":"4d4e1b7b-b985-43bb-84ec-b5d0d62c4532","year":2008},"citing_paper":{"arxiv_id":"2505.14143","last_updated":"2025-05-20T09:46:56Z","snapshot_observed_at":"2026-08-07T15:37:24.569922Z","submitted_at":"2025-05-20T09:46:56Z","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:27.622151Z"},"links":{"citing_paper":"/paper/2505.14143"},"observation_digest":"sha256:e396311787fa6bc600e3b46d3bd0ff02fd124538be33fd7739c2dec4c78cdf4a","observation_id":"56d410f6-a651-4297-b0e2-7600920dcc44","resolution":{"observed_at":"2026-08-07T15:42:28.412194Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:42:27.930435Z","title":"SimCSE: Simple contrastive learning of sentence embeddings,","venue":null,"work_id":"536c19b2-dd71-4731-97c5-4c1e1437f812","year":2021},"citing_paper":{"arxiv_id":"2505.14143","last_updated":"2025-05-20T09:46:56Z","snapshot_observed_at":"2026-08-07T15:37:24.569922Z","submitted_at":"2025-05-20T09:46:56Z","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T15:42:27.730663Z"},"links":{"citing_paper":"/paper/2505.14143"},"observation_digest":"sha256:a4d86647f90c71cf458580c1a29cff0b22328bd57892980489f97457e35f1732","observation_id":"388ee527-dda4-44bf-8f60-1f06277eef0f","resolution":{"observed_at":"2026-08-07T15:42:28.086331Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.14143","last_updated":"2025-05-20T09:46:56Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-07T15:37:24.569922Z","submitted_at":"2025-05-20T09:46:56Z","title":"Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition"},"reference_resolution":{"displayed":27,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":27},"total_outbound_references":27},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 0 inbound Pith citation observations for arXiv:2505.14143."}