{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HU5PAZE5IAVMC4GA5DDWGYZYNQ","short_pith_number":"pith:HU5PAZE5","canonical_record":{"source":{"id":"2412.05939","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-08T13:45:44Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"1f5a19140e5b406d8d06df86c5b77e80594f52413944a8f86cd68fdd850c8af8","abstract_canon_sha256":"9aed66410fae6c2162519364fa6d80a51a8bc8a6069d746c39fc1889740bca4b"},"schema_version":"1.0"},"canonical_sha256":"3d3af0649d402ac170c0e8c76363386c397081fbe7d5cb92c64eb4b9a13fd11f","source":{"kind":"arxiv","id":"2412.05939","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.05939","created_at":"2026-07-05T09:46:11Z"},{"alias_kind":"arxiv_version","alias_value":"2412.05939v1","created_at":"2026-07-05T09:46:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05939","created_at":"2026-07-05T09:46:11Z"},{"alias_kind":"pith_short_12","alias_value":"HU5PAZE5IAVM","created_at":"2026-07-05T09:46:11Z"},{"alias_kind":"pith_short_16","alias_value":"HU5PAZE5IAVMC4GA","created_at":"2026-07-05T09:46:11Z"},{"alias_kind":"pith_short_8","alias_value":"HU5PAZE5","created_at":"2026-07-05T09:46:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HU5PAZE5IAVMC4GA5DDWGYZYNQ","target":"record","payload":{"canonical_record":{"source":{"id":"2412.05939","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-08T13:45:44Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"1f5a19140e5b406d8d06df86c5b77e80594f52413944a8f86cd68fdd850c8af8","abstract_canon_sha256":"9aed66410fae6c2162519364fa6d80a51a8bc8a6069d746c39fc1889740bca4b"},"schema_version":"1.0"},"canonical_sha256":"3d3af0649d402ac170c0e8c76363386c397081fbe7d5cb92c64eb4b9a13fd11f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:11.901073Z","signature_b64":"5sbZHW8LgZnpVoVAZb1Lm6so2023kPnblvW1TKvPNFgjoJhpeeZy6y3eZF+05e9/PpCB/e6b+NIaL0YGbmsvBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d3af0649d402ac170c0e8c76363386c397081fbe7d5cb92c64eb4b9a13fd11f","last_reissued_at":"2026-07-05T09:46:11.900643Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:11.900643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.05939","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":"2026-07-05T09:46:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3zRQtjXDuUfBBYqbonOrWCRBt6sYhGWBe+6E0OOYQGsmU9ZsODeFqBwVzWitxJLWDUO2vfAZppeG4t8BB8RHDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T14:08:34.086441Z"},"content_sha256":"71dbe7ed59f9a99938e6694a278dcdab639d70c441acc18d0a0744e18bb5cbaf","schema_version":"1.0","event_id":"sha256:71dbe7ed59f9a99938e6694a278dcdab639d70c441acc18d0a0744e18bb5cbaf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HU5PAZE5IAVMC4GA5DDWGYZYNQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Libo Qin, Min-Yen Kan, Tianhao Niu, Wanxiang Che, Xiao Xu, Yuxi Xie","submitted_at":"2024-12-08T13:45:44Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) excel in vision--language tasks by pre-training solely on coarse-grained concept annotations (e.g., image captions). We hypothesize that integrating fine-grained concept annotations (e.g., object labels and object regions) will further improve performance, as both data granularities complement each other in terms of breadth and depth in concept representation. We introduce a new dataset featuring Multimodal Multi-Grained Concept annotations (MMGiC) for MLLMs. In constructing MMGiC, we explore the impact of different data recipes on multimodal comprehens"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05939","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/2412.05939/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":"2026-07-05T09:46:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xx4R7l7CwCyQOgmaC2JudoCyCvk7vGeOKUIGc8T2M6VmbqxsgnekWsfajvAhMku0y6H8BDlSNd8cLTrL6NO1Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T14:08:34.086941Z"},"content_sha256":"4f79c5ed6a70085dedacc742a091e3853a8a1619ef375b88f9d4baf95a4e8e6d","schema_version":"1.0","event_id":"sha256:4f79c5ed6a70085dedacc742a091e3853a8a1619ef375b88f9d4baf95a4e8e6d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HU5PAZE5IAVMC4GA5DDWGYZYNQ/bundle.json","state_url":"https://pith.science/pith/HU5PAZE5IAVMC4GA5DDWGYZYNQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HU5PAZE5IAVMC4GA5DDWGYZYNQ/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":"2026-07-31T14:08:34Z","links":{"resolver":"https://pith.science/pith/HU5PAZE5IAVMC4GA5DDWGYZYNQ","bundle":"https://pith.science/pith/HU5PAZE5IAVMC4GA5DDWGYZYNQ/bundle.json","state":"https://pith.science/pith/HU5PAZE5IAVMC4GA5DDWGYZYNQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HU5PAZE5IAVMC4GA5DDWGYZYNQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HU5PAZE5IAVMC4GA5DDWGYZYNQ","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":"9aed66410fae6c2162519364fa6d80a51a8bc8a6069d746c39fc1889740bca4b","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-08T13:45:44Z","title_canon_sha256":"1f5a19140e5b406d8d06df86c5b77e80594f52413944a8f86cd68fdd850c8af8"},"schema_version":"1.0","source":{"id":"2412.05939","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.05939","created_at":"2026-07-05T09:46:11Z"},{"alias_kind":"arxiv_version","alias_value":"2412.05939v1","created_at":"2026-07-05T09:46:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05939","created_at":"2026-07-05T09:46:11Z"},{"alias_kind":"pith_short_12","alias_value":"HU5PAZE5IAVM","created_at":"2026-07-05T09:46:11Z"},{"alias_kind":"pith_short_16","alias_value":"HU5PAZE5IAVMC4GA","created_at":"2026-07-05T09:46:11Z"},{"alias_kind":"pith_short_8","alias_value":"HU5PAZE5","created_at":"2026-07-05T09:46:11Z"}],"graph_snapshots":[{"event_id":"sha256:4f79c5ed6a70085dedacc742a091e3853a8a1619ef375b88f9d4baf95a4e8e6d","target":"graph","created_at":"2026-07-05T09:46:11Z","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/2412.05939/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) excel in vision--language tasks by pre-training solely on coarse-grained concept annotations (e.g., image captions). We hypothesize that integrating fine-grained concept annotations (e.g., object labels and object regions) will further improve performance, as both data granularities complement each other in terms of breadth and depth in concept representation. We introduce a new dataset featuring Multimodal Multi-Grained Concept annotations (MMGiC) for MLLMs. In constructing MMGiC, we explore the impact of different data recipes on multimodal comprehens","authors_text":"Libo Qin, Min-Yen Kan, Tianhao Niu, Wanxiang Che, Xiao Xu, Yuxi Xie","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-08T13:45:44Z","title":"Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05939","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":"sha256:71dbe7ed59f9a99938e6694a278dcdab639d70c441acc18d0a0744e18bb5cbaf","target":"record","created_at":"2026-07-05T09:46:11Z","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":"9aed66410fae6c2162519364fa6d80a51a8bc8a6069d746c39fc1889740bca4b","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-08T13:45:44Z","title_canon_sha256":"1f5a19140e5b406d8d06df86c5b77e80594f52413944a8f86cd68fdd850c8af8"},"schema_version":"1.0","source":{"id":"2412.05939","kind":"arxiv","version":1}},"canonical_sha256":"3d3af0649d402ac170c0e8c76363386c397081fbe7d5cb92c64eb4b9a13fd11f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d3af0649d402ac170c0e8c76363386c397081fbe7d5cb92c64eb4b9a13fd11f","first_computed_at":"2026-07-05T09:46:11.900643Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:46:11.900643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5sbZHW8LgZnpVoVAZb1Lm6so2023kPnblvW1TKvPNFgjoJhpeeZy6y3eZF+05e9/PpCB/e6b+NIaL0YGbmsvBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:46:11.901073Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.05939","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71dbe7ed59f9a99938e6694a278dcdab639d70c441acc18d0a0744e18bb5cbaf","sha256:4f79c5ed6a70085dedacc742a091e3853a8a1619ef375b88f9d4baf95a4e8e6d"],"state_sha256":"b36520e8c0d9af57e04fa9c51f0219e1be2ff8dfc8cdb841336250265b6b098a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vikcPMwOdkoz9sn6AFFQ2h/3y+21MWedE75iGR0wAhtS/AxS4n4MQaWtCm8or3CUlAFQNigG004RZfMU/SQLAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T14:08:34.092356Z","bundle_sha256":"61f122f87191b7fa05758965106312c96e425e281f56b79c4d34083eef3881d9"}}