{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OZ3R4MNLIC35EUJLOFQH5MRQKQ","short_pith_number":"pith:OZ3R4MNL","canonical_record":{"source":{"id":"2403.06199","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-10T12:43:27Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"effd3b2bdfb39f0292222b0f06c9c505e6e62688a850b6e1aa97da545e9cf02e","abstract_canon_sha256":"5fb107b306800a2ee3968c76c704bd70028a0c3169dabd7b999ab237708723b1"},"schema_version":"1.0"},"canonical_sha256":"76771e31ab40b7d2512b71607eb230543f0b654753c06db552fd410eee2ad3a1","source":{"kind":"arxiv","id":"2403.06199","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06199","created_at":"2026-07-05T08:00:03Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06199v4","created_at":"2026-07-05T08:00:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06199","created_at":"2026-07-05T08:00:03Z"},{"alias_kind":"pith_short_12","alias_value":"OZ3R4MNLIC35","created_at":"2026-07-05T08:00:03Z"},{"alias_kind":"pith_short_16","alias_value":"OZ3R4MNLIC35EUJL","created_at":"2026-07-05T08:00:03Z"},{"alias_kind":"pith_short_8","alias_value":"OZ3R4MNL","created_at":"2026-07-05T08:00:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OZ3R4MNLIC35EUJLOFQH5MRQKQ","target":"record","payload":{"canonical_record":{"source":{"id":"2403.06199","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-10T12:43:27Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"effd3b2bdfb39f0292222b0f06c9c505e6e62688a850b6e1aa97da545e9cf02e","abstract_canon_sha256":"5fb107b306800a2ee3968c76c704bd70028a0c3169dabd7b999ab237708723b1"},"schema_version":"1.0"},"canonical_sha256":"76771e31ab40b7d2512b71607eb230543f0b654753c06db552fd410eee2ad3a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:03.158837Z","signature_b64":"UuBtpEDN1DhP20vYh8l8joVNMcbAIZcMauawNhojLQbOvQN+whzh+JqNbZd3rUYhVTIctEtcKPPnQfH/iasdDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76771e31ab40b7d2512b71607eb230543f0b654753c06db552fd410eee2ad3a1","last_reissued_at":"2026-07-05T08:00:03.158361Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:03.158361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.06199","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:00:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5NjXyMc4llbkr7I0jxDr2lxd5pvof/W8pcbY0bcC8NThW0EQeYX1owcZFgMR9c+c2rAcSwwYg3jASJXuvsoGDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:43:23.569621Z"},"content_sha256":"00c1ef83b99ebfb1cbc8de50ccbe77f646f2dce8fbfce59ef6438c23752b830f","schema_version":"1.0","event_id":"sha256:00c1ef83b99ebfb1cbc8de50ccbe77f646f2dce8fbfce59ef6438c23752b830f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OZ3R4MNLIC35EUJLOFQH5MRQKQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mipha: A Comprehensive Overhaul of Multimodal Assistant with Small Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chaomin Shen, Feifei Feng, Jian Tang, Minjie Zhu, Ning Liu, Xin Liu, Yaxin Peng, Yichen Zhu, Zhicai Ou, Zhiyuan Xu","submitted_at":"2024-03-10T12:43:27Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have showcased impressive skills in tasks related to visual understanding and reasoning. Yet, their widespread application faces obstacles due to the high computational demands during both the training and inference phases, restricting their use to a limited audience within the research and user communities. In this paper, we investigate the design aspects of Multimodal Small Language Models (MSLMs) and propose an efficient multimodal assistant named Mipha, which is designed to create synergy among various aspects: visual representation, language models"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06199","kind":"arxiv","version":4},"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/2403.06199/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":"2026-07-05T08:00:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BcwHXaaFBMvCrrL9CDLUIpHGyIuXQE7g+GZYfMB8dvdBOlDHQX9182cPkpsv5vt7sjGS8Se9VNjZUIYwLDD/CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:43:23.570116Z"},"content_sha256":"02acbacd6701dac0f821abd8c1a33e23f26e571b83495dca739eab65bc5dcce3","schema_version":"1.0","event_id":"sha256:02acbacd6701dac0f821abd8c1a33e23f26e571b83495dca739eab65bc5dcce3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OZ3R4MNLIC35EUJLOFQH5MRQKQ/bundle.json","state_url":"https://pith.science/pith/OZ3R4MNLIC35EUJLOFQH5MRQKQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OZ3R4MNLIC35EUJLOFQH5MRQKQ/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":"2026-08-08T18:43:23Z","links":{"resolver":"https://pith.science/pith/OZ3R4MNLIC35EUJLOFQH5MRQKQ","bundle":"https://pith.science/pith/OZ3R4MNLIC35EUJLOFQH5MRQKQ/bundle.json","state":"https://pith.science/pith/OZ3R4MNLIC35EUJLOFQH5MRQKQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OZ3R4MNLIC35EUJLOFQH5MRQKQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OZ3R4MNLIC35EUJLOFQH5MRQKQ","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":"5fb107b306800a2ee3968c76c704bd70028a0c3169dabd7b999ab237708723b1","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-10T12:43:27Z","title_canon_sha256":"effd3b2bdfb39f0292222b0f06c9c505e6e62688a850b6e1aa97da545e9cf02e"},"schema_version":"1.0","source":{"id":"2403.06199","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06199","created_at":"2026-07-05T08:00:03Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06199v4","created_at":"2026-07-05T08:00:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06199","created_at":"2026-07-05T08:00:03Z"},{"alias_kind":"pith_short_12","alias_value":"OZ3R4MNLIC35","created_at":"2026-07-05T08:00:03Z"},{"alias_kind":"pith_short_16","alias_value":"OZ3R4MNLIC35EUJL","created_at":"2026-07-05T08:00:03Z"},{"alias_kind":"pith_short_8","alias_value":"OZ3R4MNL","created_at":"2026-07-05T08:00:03Z"}],"graph_snapshots":[{"event_id":"sha256:02acbacd6701dac0f821abd8c1a33e23f26e571b83495dca739eab65bc5dcce3","target":"graph","created_at":"2026-07-05T08:00:03Z","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/2403.06199/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have showcased impressive skills in tasks related to visual understanding and reasoning. Yet, their widespread application faces obstacles due to the high computational demands during both the training and inference phases, restricting their use to a limited audience within the research and user communities. In this paper, we investigate the design aspects of Multimodal Small Language Models (MSLMs) and propose an efficient multimodal assistant named Mipha, which is designed to create synergy among various aspects: visual representation, language models","authors_text":"Chaomin Shen, Feifei Feng, Jian Tang, Minjie Zhu, Ning Liu, Xin Liu, Yaxin Peng, Yichen Zhu, Zhicai Ou, Zhiyuan Xu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-10T12:43:27Z","title":"Mipha: A Comprehensive Overhaul of Multimodal Assistant with Small Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06199","kind":"arxiv","version":4},"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":"sha256:00c1ef83b99ebfb1cbc8de50ccbe77f646f2dce8fbfce59ef6438c23752b830f","target":"record","created_at":"2026-07-05T08:00:03Z","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":"5fb107b306800a2ee3968c76c704bd70028a0c3169dabd7b999ab237708723b1","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-10T12:43:27Z","title_canon_sha256":"effd3b2bdfb39f0292222b0f06c9c505e6e62688a850b6e1aa97da545e9cf02e"},"schema_version":"1.0","source":{"id":"2403.06199","kind":"arxiv","version":4}},"canonical_sha256":"76771e31ab40b7d2512b71607eb230543f0b654753c06db552fd410eee2ad3a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"76771e31ab40b7d2512b71607eb230543f0b654753c06db552fd410eee2ad3a1","first_computed_at":"2026-07-05T08:00:03.158361Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:00:03.158361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UuBtpEDN1DhP20vYh8l8joVNMcbAIZcMauawNhojLQbOvQN+whzh+JqNbZd3rUYhVTIctEtcKPPnQfH/iasdDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:00:03.158837Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.06199","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00c1ef83b99ebfb1cbc8de50ccbe77f646f2dce8fbfce59ef6438c23752b830f","sha256:02acbacd6701dac0f821abd8c1a33e23f26e571b83495dca739eab65bc5dcce3"],"state_sha256":"aa037bad5b22c0cb08369a7ffa125c2b02d2f2c25daa629d083bcdf7f2ff3122"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P9Rq0ubgmCBstRjAOtF9g0Cx+5HWOxONUrvE/W+bcRNcZzV9GTEkMtgFQ4NF5PJ02EmUfkdUN3HTYcKbIk45Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:43:23.575170Z","bundle_sha256":"a1e5165c0106a26ec46ef2f05edab54061844f76c480c705048203cefd2a56f7"}}