{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:R6QIGM3MJPEGLD4QZWXV3Y36VN","short_pith_number":"pith:R6QIGM3M","schema_version":"1.0","canonical_sha256":"8fa083336c4bc8658f90cdaf5de37eab6d4370ac41d25613e613f580a716031a","source":{"kind":"arxiv","id":"2311.01751","version":1},"attestation_state":"computed","paper":{"title":"EmojiLM: Modeling the New Emoji Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hang Liu, Jingbo Shang, Letian Peng, Zihan Wang, Zilong Wang","submitted_at":"2023-11-03T07:06:51Z","abstract_excerpt":"With the rapid development of the internet, online social media welcomes people with different backgrounds through its diverse content. The increasing usage of emoji becomes a noticeable trend thanks to emoji's rich information beyond cultural or linguistic borders. However, the current study on emojis is limited to single emoji prediction and there are limited data resources available for further study of the interesting linguistic phenomenon. To this end, we synthesize a large text-emoji parallel corpus, Text2Emoji, from a large language model. Based on the parallel corpus, we distill a sequ"},"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":"2311.01751","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-03T07:06:51Z","cross_cats_sorted":[],"title_canon_sha256":"aab01fefc2d90806b9f671cc1fac53fe678a012c1c833e03fac41c9de0105dc0","abstract_canon_sha256":"cb4fefe859ccca523f57904b4cbf6d3d725ef576ddaae17bb3a5be8a2440d3c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:44.707304Z","signature_b64":"nNZ49wuTE9BFKfSSJRFXbK0K7/jmIJzEMrtfY+z1+W/82tcypcLD3f/DfX6UZ5nUqMCC/GBrjTxsvofW9hY8Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fa083336c4bc8658f90cdaf5de37eab6d4370ac41d25613e613f580a716031a","last_reissued_at":"2026-07-05T07:08:44.706809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:44.706809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EmojiLM: Modeling the New Emoji Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hang Liu, Jingbo Shang, Letian Peng, Zihan Wang, Zilong Wang","submitted_at":"2023-11-03T07:06:51Z","abstract_excerpt":"With the rapid development of the internet, online social media welcomes people with different backgrounds through its diverse content. The increasing usage of emoji becomes a noticeable trend thanks to emoji's rich information beyond cultural or linguistic borders. However, the current study on emojis is limited to single emoji prediction and there are limited data resources available for further study of the interesting linguistic phenomenon. To this end, we synthesize a large text-emoji parallel corpus, Text2Emoji, from a large language model. Based on the parallel corpus, we distill a sequ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01751","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/2311.01751/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":"2311.01751","created_at":"2026-07-05T07:08:44.706873+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.01751v1","created_at":"2026-07-05T07:08:44.706873+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01751","created_at":"2026-07-05T07:08:44.706873+00:00"},{"alias_kind":"pith_short_12","alias_value":"R6QIGM3MJPEG","created_at":"2026-07-05T07:08:44.706873+00:00"},{"alias_kind":"pith_short_16","alias_value":"R6QIGM3MJPEGLD4Q","created_at":"2026-07-05T07:08:44.706873+00:00"},{"alias_kind":"pith_short_8","alias_value":"R6QIGM3M","created_at":"2026-07-05T07:08:44.706873+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R6QIGM3MJPEGLD4QZWXV3Y36VN","json":"https://pith.science/pith/R6QIGM3MJPEGLD4QZWXV3Y36VN.json","graph_json":"https://pith.science/api/pith-number/R6QIGM3MJPEGLD4QZWXV3Y36VN/graph.json","events_json":"https://pith.science/api/pith-number/R6QIGM3MJPEGLD4QZWXV3Y36VN/events.json","paper":"https://pith.science/paper/R6QIGM3M"},"agent_actions":{"view_html":"https://pith.science/pith/R6QIGM3MJPEGLD4QZWXV3Y36VN","download_json":"https://pith.science/pith/R6QIGM3MJPEGLD4QZWXV3Y36VN.json","view_paper":"https://pith.science/paper/R6QIGM3M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.01751&json=true","fetch_graph":"https://pith.science/api/pith-number/R6QIGM3MJPEGLD4QZWXV3Y36VN/graph.json","fetch_events":"https://pith.science/api/pith-number/R6QIGM3MJPEGLD4QZWXV3Y36VN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R6QIGM3MJPEGLD4QZWXV3Y36VN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R6QIGM3MJPEGLD4QZWXV3Y36VN/action/storage_attestation","attest_author":"https://pith.science/pith/R6QIGM3MJPEGLD4QZWXV3Y36VN/action/author_attestation","sign_citation":"https://pith.science/pith/R6QIGM3MJPEGLD4QZWXV3Y36VN/action/citation_signature","submit_replication":"https://pith.science/pith/R6QIGM3MJPEGLD4QZWXV3Y36VN/action/replication_record"}},"created_at":"2026-07-05T07:08:44.706873+00:00","updated_at":"2026-07-05T07:08:44.706873+00:00"}