{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IQULTCBQKDNGK5KQE2VIPGCVGN","short_pith_number":"pith:IQULTCBQ","canonical_record":{"source":{"id":"2405.01483","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-02T17:14:57Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"aa9342b4e3586aa85459d9a281653c9a2d35ce14ede5f155e46722a674507a5f","abstract_canon_sha256":"590c73692de017b640d510feff10f287a89f9c097f4ddbe141115be73041587c"},"schema_version":"1.0"},"canonical_sha256":"4428b9883050da65755026aa879855337bb605f6fecbc66daeb3e3f6e840429a","source":{"kind":"arxiv","id":"2405.01483","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IQULTCBQKDNGK5KQE2VIPGCVGN","target":"record","payload":{"canonical_record":{"source":{"id":"2405.01483","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-02T17:14:57Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"aa9342b4e3586aa85459d9a281653c9a2d35ce14ede5f155e46722a674507a5f","abstract_canon_sha256":"590c73692de017b640d510feff10f287a89f9c097f4ddbe141115be73041587c"},"schema_version":"1.0"},"canonical_sha256":"4428b9883050da65755026aa879855337bb605f6fecbc66daeb3e3f6e840429a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:48.894290Z","signature_b64":"NCmvdVDF366uIcdYDgfL9S+0X+IbVkWdOugkNvBtfNGbRSL7p2Zs4saiEqlS3glSMy5R5tNbZLjYw94eLj+/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4428b9883050da65755026aa879855337bb605f6fecbc66daeb3e3f6e840429a","last_reissued_at":"2026-07-05T09:35:48.893774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:48.893774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.01483","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:35:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jJ6s8AsG0XTRNQ+0TVM8Mo55Ykw7JHpB9pF7gy3PAolUOzNuV6d9CAbxgGeObCLrJ4eCbmQV77tEbLmLNdgnCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T21:41:34.947728Z"},"content_sha256":"7bba9e29389da7f7c7ac049cf04e8e3df1e8f3c97cf7a88b5fdc8a44fdf924ba","schema_version":"1.0","event_id":"sha256:7bba9e29389da7f7c7ac049cf04e8e3df1e8f3c97cf7a88b5fdc8a44fdf924ba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IQULTCBQKDNGK5KQE2VIPGCVGN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MANTIS: Interleaved Multi-Image Instruction Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Cong Wei, Dongfu Jiang, Huaye Zeng, Max Ku, Qian Liu, Wenhu Chen, Xuan He","submitted_at":"2024-05-02T17:14:57Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.01483","kind":"arxiv","version":3},"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/2405.01483/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:35:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"11pVRmH4HxIyyNK52/TUOwNUcfrcU7wbkoBbEadr7VLzspw0AJ1wATNTMYKNyVXqG2HOWIxdVDC5GLrLVxPgBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T21:41:34.948535Z"},"content_sha256":"f46f59fa3b437145b11829af48fcec97e88632a8a6735674ace3f30ece17dc97","schema_version":"1.0","event_id":"sha256:f46f59fa3b437145b11829af48fcec97e88632a8a6735674ace3f30ece17dc97"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IQULTCBQKDNGK5KQE2VIPGCVGN/bundle.json","state_url":"https://pith.science/pith/IQULTCBQKDNGK5KQE2VIPGCVGN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IQULTCBQKDNGK5KQE2VIPGCVGN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T21:41:34Z","links":{"resolver":"https://pith.science/pith/IQULTCBQKDNGK5KQE2VIPGCVGN","bundle":"https://pith.science/pith/IQULTCBQKDNGK5KQE2VIPGCVGN/bundle.json","state":"https://pith.science/pith/IQULTCBQKDNGK5KQE2VIPGCVGN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IQULTCBQKDNGK5KQE2VIPGCVGN/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kbo6U90ZN3sOicfFSEveDviLIccFJUAvgl6KGyOhNI3deulQf3lCzEOwOCzgEbRRrj2BikFPHUGe8jl5EDopCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T21:41:34.960016Z","bundle_sha256":"8801c2a3740e62fe933533493c2be27f2b4d5f113358f735bab82d33c4dae717"}}