{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2Y76SXOM6ATNGTOBO3KIZWLFDG","short_pith_number":"pith:2Y76SXOM","schema_version":"1.0","canonical_sha256":"d63fe95dccf026d34dc176d48cd96519b2ffcaa667bf27499cad7eef66a44a34","source":{"kind":"arxiv","id":"2309.08637","version":5},"attestation_state":"computed","paper":{"title":"TextBind: Multi-turn Interleaved Multimodal Instruction-following in the Wild","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Deng Cai, Huayang Li, Lemao Liu, Longyue Wang, Shuming Shi, Siheng Li, Taro Watanabe, Yujiu Yang","submitted_at":"2023-09-14T15:34:01Z","abstract_excerpt":"Large language models with instruction-following abilities have revolutionized the field of artificial intelligence. These models show exceptional generalizability to tackle various real-world tasks through their natural language interfaces. However, their performance heavily relies on high-quality exemplar data, which is often difficult to obtain. This challenge is further exacerbated when it comes to multimodal instruction following. We introduce TextBind, an almost annotation-free framework for empowering larger language models with the multi-turn interleaved multimodal instruction-followin"},"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":"2309.08637","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-14T15:34:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8199a6dfb046fde13d8b5d2fe3ec3d61b98529a2697ac002d8592cce1a3430cd","abstract_canon_sha256":"7d07d7b02771058831f133233c88a76180d010df0eb0c11ce524cd8ec6b10ec4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:13.914233Z","signature_b64":"X2nDNAt+2sgv8+qFvo+umJtPkahhngm8dVu9lN3Ga+bletDYY1iB9DezPkqEKcBiqmtDpFIcVIS+YZFLBHa+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d63fe95dccf026d34dc176d48cd96519b2ffcaa667bf27499cad7eef66a44a34","last_reissued_at":"2026-07-05T08:26:13.913736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:13.913736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TextBind: Multi-turn Interleaved Multimodal Instruction-following in the Wild","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Deng Cai, Huayang Li, Lemao Liu, Longyue Wang, Shuming Shi, Siheng Li, Taro Watanabe, Yujiu Yang","submitted_at":"2023-09-14T15:34:01Z","abstract_excerpt":"Large language models with instruction-following abilities have revolutionized the field of artificial intelligence. These models show exceptional generalizability to tackle various real-world tasks through their natural language interfaces. However, their performance heavily relies on high-quality exemplar data, which is often difficult to obtain. This challenge is further exacerbated when it comes to multimodal instruction following. We introduce TextBind, an almost annotation-free framework for empowering larger language models with the multi-turn interleaved multimodal instruction-followin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08637","kind":"arxiv","version":5},"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/2309.08637/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":"2309.08637","created_at":"2026-07-05T08:26:13.913798+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.08637v5","created_at":"2026-07-05T08:26:13.913798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08637","created_at":"2026-07-05T08:26:13.913798+00:00"},{"alias_kind":"pith_short_12","alias_value":"2Y76SXOM6ATN","created_at":"2026-07-05T08:26:13.913798+00:00"},{"alias_kind":"pith_short_16","alias_value":"2Y76SXOM6ATNGTOB","created_at":"2026-07-05T08:26:13.913798+00:00"},{"alias_kind":"pith_short_8","alias_value":"2Y76SXOM","created_at":"2026-07-05T08:26:13.913798+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02096","citing_title":"SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2Y76SXOM6ATNGTOBO3KIZWLFDG","json":"https://pith.science/pith/2Y76SXOM6ATNGTOBO3KIZWLFDG.json","graph_json":"https://pith.science/api/pith-number/2Y76SXOM6ATNGTOBO3KIZWLFDG/graph.json","events_json":"https://pith.science/api/pith-number/2Y76SXOM6ATNGTOBO3KIZWLFDG/events.json","paper":"https://pith.science/paper/2Y76SXOM"},"agent_actions":{"view_html":"https://pith.science/pith/2Y76SXOM6ATNGTOBO3KIZWLFDG","download_json":"https://pith.science/pith/2Y76SXOM6ATNGTOBO3KIZWLFDG.json","view_paper":"https://pith.science/paper/2Y76SXOM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.08637&json=true","fetch_graph":"https://pith.science/api/pith-number/2Y76SXOM6ATNGTOBO3KIZWLFDG/graph.json","fetch_events":"https://pith.science/api/pith-number/2Y76SXOM6ATNGTOBO3KIZWLFDG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2Y76SXOM6ATNGTOBO3KIZWLFDG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2Y76SXOM6ATNGTOBO3KIZWLFDG/action/storage_attestation","attest_author":"https://pith.science/pith/2Y76SXOM6ATNGTOBO3KIZWLFDG/action/author_attestation","sign_citation":"https://pith.science/pith/2Y76SXOM6ATNGTOBO3KIZWLFDG/action/citation_signature","submit_replication":"https://pith.science/pith/2Y76SXOM6ATNGTOBO3KIZWLFDG/action/replication_record"}},"created_at":"2026-07-05T08:26:13.913798+00:00","updated_at":"2026-07-05T08:26:13.913798+00:00"}