{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IQULTCBQKDNGK5KQE2VIPGCVGN","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":"590c73692de017b640d510feff10f287a89f9c097f4ddbe141115be73041587c","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-02T17:14:57Z","title_canon_sha256":"aa9342b4e3586aa85459d9a281653c9a2d35ce14ede5f155e46722a674507a5f"},"schema_version":"1.0","source":{"id":"2405.01483","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.01483","created_at":"2026-07-05T09:35:48Z"},{"alias_kind":"arxiv_version","alias_value":"2405.01483v3","created_at":"2026-07-05T09:35:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.01483","created_at":"2026-07-05T09:35:48Z"},{"alias_kind":"pith_short_12","alias_value":"IQULTCBQKDNG","created_at":"2026-07-05T09:35:48Z"},{"alias_kind":"pith_short_16","alias_value":"IQULTCBQKDNGK5KQ","created_at":"2026-07-05T09:35:48Z"},{"alias_kind":"pith_short_8","alias_value":"IQULTCBQ","created_at":"2026-07-05T09:35:48Z"}],"graph_snapshots":[{"event_id":"sha256:f46f59fa3b437145b11829af48fcec97e88632a8a6735674ace3f30ece17dc97","target":"graph","created_at":"2026-07-05T09:35:48Z","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/2405.01483/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large multimodal models (LMMs) have shown great results in single-image vision language tasks. However, their abilities to solve multi-image visual language tasks is yet to be improved. The existing LMMs like OpenFlamingo, Emu2, and Idefics gain their multi-image ability through pre-training on hundreds of millions of noisy interleaved image-text data from the web, which is neither efficient nor effective. In this paper, we aim to build strong multi-image LMMs via instruction tuning with academic-level resources. Therefore, we meticulously construct Mantis-Instruct containing 721K multi-image ","authors_text":"Cong Wei, Dongfu Jiang, Huaye Zeng, Max Ku, Qian Liu, Wenhu Chen, Xuan He","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-02T17:14:57Z","title":"MANTIS: Interleaved Multi-Image Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.01483","kind":"arxiv","version":3},"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":"sha256:7bba9e29389da7f7c7ac049cf04e8e3df1e8f3c97cf7a88b5fdc8a44fdf924ba","target":"record","created_at":"2026-07-05T09:35:48Z","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":"590c73692de017b640d510feff10f287a89f9c097f4ddbe141115be73041587c","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-02T17:14:57Z","title_canon_sha256":"aa9342b4e3586aa85459d9a281653c9a2d35ce14ede5f155e46722a674507a5f"},"schema_version":"1.0","source":{"id":"2405.01483","kind":"arxiv","version":3}},"canonical_sha256":"4428b9883050da65755026aa879855337bb605f6fecbc66daeb3e3f6e840429a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4428b9883050da65755026aa879855337bb605f6fecbc66daeb3e3f6e840429a","first_computed_at":"2026-07-05T09:35:48.893774Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:35:48.893774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NCmvdVDF366uIcdYDgfL9S+0X+IbVkWdOugkNvBtfNGbRSL7p2Zs4saiEqlS3glSMy5R5tNbZLjYw94eLj+/AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:35:48.894290Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.01483","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7bba9e29389da7f7c7ac049cf04e8e3df1e8f3c97cf7a88b5fdc8a44fdf924ba","sha256:f46f59fa3b437145b11829af48fcec97e88632a8a6735674ace3f30ece17dc97"],"state_sha256":"c7643074b2c3a0ff641c3dde22f5dddc0b11e0cb1c8446d4d2f7bd4b84286cdc"}