{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ULMO4LPU6R24BDWVES26YWOWZC","short_pith_number":"pith:ULMO4LPU","canonical_record":{"source":{"id":"2501.04150","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-04T07:44:49Z","cross_cats_sorted":[],"title_canon_sha256":"47a31704dc78952358df1905a30ae7ec36e67fac40c122358a25b31590a9b1ad","abstract_canon_sha256":"63aa51f1815222e334efb2cb1e5aeb255caa01ebd4d643a368f134ba6c5827e2"},"schema_version":"1.0"},"canonical_sha256":"a2d8ee2df4f475c08ed524b5ec59d6c8b5f2e68f9f14e7669154e3db4dae384f","source":{"kind":"arxiv","id":"2501.04150","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04150","created_at":"2026-07-05T09:58:30Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04150v1","created_at":"2026-07-05T09:58:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04150","created_at":"2026-07-05T09:58:30Z"},{"alias_kind":"pith_short_12","alias_value":"ULMO4LPU6R24","created_at":"2026-07-05T09:58:30Z"},{"alias_kind":"pith_short_16","alias_value":"ULMO4LPU6R24BDWV","created_at":"2026-07-05T09:58:30Z"},{"alias_kind":"pith_short_8","alias_value":"ULMO4LPU","created_at":"2026-07-05T09:58:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ULMO4LPU6R24BDWVES26YWOWZC","target":"record","payload":{"canonical_record":{"source":{"id":"2501.04150","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-04T07:44:49Z","cross_cats_sorted":[],"title_canon_sha256":"47a31704dc78952358df1905a30ae7ec36e67fac40c122358a25b31590a9b1ad","abstract_canon_sha256":"63aa51f1815222e334efb2cb1e5aeb255caa01ebd4d643a368f134ba6c5827e2"},"schema_version":"1.0"},"canonical_sha256":"a2d8ee2df4f475c08ed524b5ec59d6c8b5f2e68f9f14e7669154e3db4dae384f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:30.818613Z","signature_b64":"ggUCtey5wo/HKuTSWXrv8BHwuC2dQZvh2o2ZaWSXVImTiQYKsSpNBZ1DogfF7+A1DEIIFCAOdFUDSvviAutsCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2d8ee2df4f475c08ed524b5ec59d6c8b5f2e68f9f14e7669154e3db4dae384f","last_reissued_at":"2026-07-05T09:58:30.818205Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:30.818205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.04150","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:58:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yADAMeJuP6F/SEBzKmVXBiflGyJmKXyywEUtx51ga5KySPVAs27H6wDdcDR2wF9ihiBtm9Gt5Z69aWUXwyQFCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T23:52:07.412983Z"},"content_sha256":"2e9ed33cc54edbb56197db2f958a3f300b916d24f4d87c2deb35e9339c5ec268","schema_version":"1.0","event_id":"sha256:2e9ed33cc54edbb56197db2f958a3f300b916d24f4d87c2deb35e9339c5ec268"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ULMO4LPU6R24BDWVES26YWOWZC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benchmarking Large and Small MLLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunming Qiao, Dongdong Chen, Junsong Yuan, Mei Gao, Mengchen Liu, Xuelu Feng, Yunsheng Li","submitted_at":"2025-01-04T07:44:49Z","abstract_excerpt":"Large multimodal language models (MLLMs) such as GPT-4V and GPT-4o have achieved remarkable advancements in understanding and generating multimodal content, showcasing superior quality and capabilities across diverse tasks. However, their deployment faces significant challenges, including slow inference, high computational cost, and impracticality for on-device applications. In contrast, the emergence of small MLLMs, exemplified by the LLava-series models and Phi-3-Vision, offers promising alternatives with faster inference, reduced deployment costs, and the ability to handle domain-specific s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04150","kind":"arxiv","version":1},"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/2501.04150/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":"2026-07-05T09:58:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3/EjswjTNCjsbdPZCs4DnAOIuecm12vML9e7zgZjAV1seLz6HRxVQZKEW82WCx+bIvGOwYhMKkrQ/zE648UvAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T23:52:07.414069Z"},"content_sha256":"d569095227d9f7d0b60d014eff84822d2b5373054b611ca94dbed061133fc612","schema_version":"1.0","event_id":"sha256:d569095227d9f7d0b60d014eff84822d2b5373054b611ca94dbed061133fc612"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ULMO4LPU6R24BDWVES26YWOWZC/bundle.json","state_url":"https://pith.science/pith/ULMO4LPU6R24BDWVES26YWOWZC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ULMO4LPU6R24BDWVES26YWOWZC/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":"2026-08-12T23:52:07Z","links":{"resolver":"https://pith.science/pith/ULMO4LPU6R24BDWVES26YWOWZC","bundle":"https://pith.science/pith/ULMO4LPU6R24BDWVES26YWOWZC/bundle.json","state":"https://pith.science/pith/ULMO4LPU6R24BDWVES26YWOWZC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ULMO4LPU6R24BDWVES26YWOWZC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ULMO4LPU6R24BDWVES26YWOWZC","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":"63aa51f1815222e334efb2cb1e5aeb255caa01ebd4d643a368f134ba6c5827e2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-04T07:44:49Z","title_canon_sha256":"47a31704dc78952358df1905a30ae7ec36e67fac40c122358a25b31590a9b1ad"},"schema_version":"1.0","source":{"id":"2501.04150","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04150","created_at":"2026-07-05T09:58:30Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04150v1","created_at":"2026-07-05T09:58:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04150","created_at":"2026-07-05T09:58:30Z"},{"alias_kind":"pith_short_12","alias_value":"ULMO4LPU6R24","created_at":"2026-07-05T09:58:30Z"},{"alias_kind":"pith_short_16","alias_value":"ULMO4LPU6R24BDWV","created_at":"2026-07-05T09:58:30Z"},{"alias_kind":"pith_short_8","alias_value":"ULMO4LPU","created_at":"2026-07-05T09:58:30Z"}],"graph_snapshots":[{"event_id":"sha256:d569095227d9f7d0b60d014eff84822d2b5373054b611ca94dbed061133fc612","target":"graph","created_at":"2026-07-05T09:58:30Z","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/2501.04150/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large multimodal language models (MLLMs) such as GPT-4V and GPT-4o have achieved remarkable advancements in understanding and generating multimodal content, showcasing superior quality and capabilities across diverse tasks. However, their deployment faces significant challenges, including slow inference, high computational cost, and impracticality for on-device applications. In contrast, the emergence of small MLLMs, exemplified by the LLava-series models and Phi-3-Vision, offers promising alternatives with faster inference, reduced deployment costs, and the ability to handle domain-specific s","authors_text":"Chunming Qiao, Dongdong Chen, Junsong Yuan, Mei Gao, Mengchen Liu, Xuelu Feng, Yunsheng Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-04T07:44:49Z","title":"Benchmarking Large and Small MLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04150","kind":"arxiv","version":1},"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":"sha256:2e9ed33cc54edbb56197db2f958a3f300b916d24f4d87c2deb35e9339c5ec268","target":"record","created_at":"2026-07-05T09:58:30Z","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":"63aa51f1815222e334efb2cb1e5aeb255caa01ebd4d643a368f134ba6c5827e2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-04T07:44:49Z","title_canon_sha256":"47a31704dc78952358df1905a30ae7ec36e67fac40c122358a25b31590a9b1ad"},"schema_version":"1.0","source":{"id":"2501.04150","kind":"arxiv","version":1}},"canonical_sha256":"a2d8ee2df4f475c08ed524b5ec59d6c8b5f2e68f9f14e7669154e3db4dae384f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2d8ee2df4f475c08ed524b5ec59d6c8b5f2e68f9f14e7669154e3db4dae384f","first_computed_at":"2026-07-05T09:58:30.818205Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:58:30.818205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ggUCtey5wo/HKuTSWXrv8BHwuC2dQZvh2o2ZaWSXVImTiQYKsSpNBZ1DogfF7+A1DEIIFCAOdFUDSvviAutsCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:58:30.818613Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.04150","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e9ed33cc54edbb56197db2f958a3f300b916d24f4d87c2deb35e9339c5ec268","sha256:d569095227d9f7d0b60d014eff84822d2b5373054b611ca94dbed061133fc612"],"state_sha256":"ae762ac5174da4e21844b436b417a4e99f7adbad61144d6fe755f4fb256a1e30"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/SWKcXnJAeIjDXJVXK2bJfpFYt7epyTW2btViiLGrqnXBf0eNB/2x/AfNfHmGMzn5Bou2mzRUCR8Clc3TcwWBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T23:52:07.429975Z","bundle_sha256":"859ac4e8af2b7070608329c4e0d1ecf56353db95e867a3e021ff3d537563caf8"}}