{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CJZGWNA35G37IIGFZWBSLYJXIP","short_pith_number":"pith:CJZGWNA3","canonical_record":{"source":{"id":"2402.11530","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-18T10:09:10Z","cross_cats_sorted":[],"title_canon_sha256":"b2d6ece05912f9f741fb9846eee6a5ae8d29a786546106e375c567dd92a9b0b9","abstract_canon_sha256":"cd13aa3548e2b75afa2331929534e7624354d20707c72c7dcc4650d26bb8684a"},"schema_version":"1.0"},"canonical_sha256":"12726b341be9b7f420c5cd8325e13743c63b4dca170c65abc795a5f22fa58f2a","source":{"kind":"arxiv","id":"2402.11530","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11530","created_at":"2026-07-05T08:46:53Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11530v3","created_at":"2026-07-05T08:46:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11530","created_at":"2026-07-05T08:46:53Z"},{"alias_kind":"pith_short_12","alias_value":"CJZGWNA35G37","created_at":"2026-07-05T08:46:53Z"},{"alias_kind":"pith_short_16","alias_value":"CJZGWNA35G37IIGF","created_at":"2026-07-05T08:46:53Z"},{"alias_kind":"pith_short_8","alias_value":"CJZGWNA3","created_at":"2026-07-05T08:46:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CJZGWNA35G37IIGFZWBSLYJXIP","target":"record","payload":{"canonical_record":{"source":{"id":"2402.11530","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-18T10:09:10Z","cross_cats_sorted":[],"title_canon_sha256":"b2d6ece05912f9f741fb9846eee6a5ae8d29a786546106e375c567dd92a9b0b9","abstract_canon_sha256":"cd13aa3548e2b75afa2331929534e7624354d20707c72c7dcc4650d26bb8684a"},"schema_version":"1.0"},"canonical_sha256":"12726b341be9b7f420c5cd8325e13743c63b4dca170c65abc795a5f22fa58f2a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:53.268790Z","signature_b64":"tq0nhSrD2IfbZbNJ+5QBFsoqdKSsJyEM1fQJooMTuUSz8qI0ncqgKk93r6A6XP82Ny+G7PdHfhFsj1PLEgGyCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12726b341be9b7f420c5cd8325e13743c63b4dca170c65abc795a5f22fa58f2a","last_reissued_at":"2026-07-05T08:46:53.268249Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:53.268249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.11530","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":"2026-07-05T08:46:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vqgmAhyhDgPGnmLZBmee9frZabUhCyaMQphlnv90JOxO8xJ4TJnGxJAUrgVL8myoIL/40bqldBv7jwZr1aZgCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T17:18:12.504118Z"},"content_sha256":"6eac013eec312afe7789940c97e4c5569885ca21e6ee8e8b2849a4cb392989cb","schema_version":"1.0","event_id":"sha256:6eac013eec312afe7789940c97e4c5569885ca21e6ee8e8b2849a4cb392989cb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CJZGWNA35G37IIGFZWBSLYJXIP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Multimodal Learning from Data-centric Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boya Wu, Bo Zhao, Jianhao Yuan, Muyang He, Tiejun Huang, Yexin Liu, Yueze Wang","submitted_at":"2024-02-18T10:09:10Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated notable capabilities in general visual understanding and reasoning tasks. However, their deployment is hindered by substantial computational costs in both training and inference, limiting accessibility to the broader research and user communities. A straightforward solution is to leverage smaller pre-trained vision and language models, which inevitably cause significant performance drops. In this paper, we demonstrate the possibility of training a smaller but better MLLM with high-quality training data. Specifically, we introduce Bunny"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11530","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/2402.11530/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":"2026-07-05T08:46:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l04qIsJOM0VaVdbgqde4ae7rrO+5hJPI+YftoV7V6Znv4nJ0kHHhRo8CfrbAnHjb14ojhWyLQ8BQX3qSNYiNAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T17:18:12.505003Z"},"content_sha256":"aaacc9e116fabb0259d3d976f5c4a56bc31fa18f3c268b1bb0ec30a07afa7ac1","schema_version":"1.0","event_id":"sha256:aaacc9e116fabb0259d3d976f5c4a56bc31fa18f3c268b1bb0ec30a07afa7ac1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CJZGWNA35G37IIGFZWBSLYJXIP/bundle.json","state_url":"https://pith.science/pith/CJZGWNA35G37IIGFZWBSLYJXIP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CJZGWNA35G37IIGFZWBSLYJXIP/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":"2026-08-10T17:18:12Z","links":{"resolver":"https://pith.science/pith/CJZGWNA35G37IIGFZWBSLYJXIP","bundle":"https://pith.science/pith/CJZGWNA35G37IIGFZWBSLYJXIP/bundle.json","state":"https://pith.science/pith/CJZGWNA35G37IIGFZWBSLYJXIP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CJZGWNA35G37IIGFZWBSLYJXIP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CJZGWNA35G37IIGFZWBSLYJXIP","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":"cd13aa3548e2b75afa2331929534e7624354d20707c72c7dcc4650d26bb8684a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-18T10:09:10Z","title_canon_sha256":"b2d6ece05912f9f741fb9846eee6a5ae8d29a786546106e375c567dd92a9b0b9"},"schema_version":"1.0","source":{"id":"2402.11530","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11530","created_at":"2026-07-05T08:46:53Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11530v3","created_at":"2026-07-05T08:46:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11530","created_at":"2026-07-05T08:46:53Z"},{"alias_kind":"pith_short_12","alias_value":"CJZGWNA35G37","created_at":"2026-07-05T08:46:53Z"},{"alias_kind":"pith_short_16","alias_value":"CJZGWNA35G37IIGF","created_at":"2026-07-05T08:46:53Z"},{"alias_kind":"pith_short_8","alias_value":"CJZGWNA3","created_at":"2026-07-05T08:46:53Z"}],"graph_snapshots":[{"event_id":"sha256:aaacc9e116fabb0259d3d976f5c4a56bc31fa18f3c268b1bb0ec30a07afa7ac1","target":"graph","created_at":"2026-07-05T08:46:53Z","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/2402.11530/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated notable capabilities in general visual understanding and reasoning tasks. However, their deployment is hindered by substantial computational costs in both training and inference, limiting accessibility to the broader research and user communities. A straightforward solution is to leverage smaller pre-trained vision and language models, which inevitably cause significant performance drops. In this paper, we demonstrate the possibility of training a smaller but better MLLM with high-quality training data. Specifically, we introduce Bunny","authors_text":"Boya Wu, Bo Zhao, Jianhao Yuan, Muyang He, Tiejun Huang, Yexin Liu, Yueze Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-18T10:09:10Z","title":"Efficient Multimodal Learning from Data-centric Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11530","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":"sha256:6eac013eec312afe7789940c97e4c5569885ca21e6ee8e8b2849a4cb392989cb","target":"record","created_at":"2026-07-05T08:46:53Z","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":"cd13aa3548e2b75afa2331929534e7624354d20707c72c7dcc4650d26bb8684a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-18T10:09:10Z","title_canon_sha256":"b2d6ece05912f9f741fb9846eee6a5ae8d29a786546106e375c567dd92a9b0b9"},"schema_version":"1.0","source":{"id":"2402.11530","kind":"arxiv","version":3}},"canonical_sha256":"12726b341be9b7f420c5cd8325e13743c63b4dca170c65abc795a5f22fa58f2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12726b341be9b7f420c5cd8325e13743c63b4dca170c65abc795a5f22fa58f2a","first_computed_at":"2026-07-05T08:46:53.268249Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:53.268249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tq0nhSrD2IfbZbNJ+5QBFsoqdKSsJyEM1fQJooMTuUSz8qI0ncqgKk93r6A6XP82Ny+G7PdHfhFsj1PLEgGyCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:53.268790Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.11530","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6eac013eec312afe7789940c97e4c5569885ca21e6ee8e8b2849a4cb392989cb","sha256:aaacc9e116fabb0259d3d976f5c4a56bc31fa18f3c268b1bb0ec30a07afa7ac1"],"state_sha256":"8f2bffc3e33bfa7f2091a20a520ec9ae28ee94e1af9e1c42ab9d0a40bcdb4f3c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gq5+0uR0KF/MOBUEjyYOIFV7OUO8Agn51YckdUDsA4W4fZqzUCdOOFO+S3JbjYW7D4PEMPqXUDxW/YPThOFoDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T17:18:12.510362Z","bundle_sha256":"1d4a865f0cb275360e30edda7c06903d2098e281daa432a99529d040f7bfa155"}}