{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WEZRPUUCRIJYHFGXFAAFFPJ6RE","short_pith_number":"pith:WEZRPUUC","canonical_record":{"source":{"id":"2412.16869","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-22T05:42:40Z","cross_cats_sorted":[],"title_canon_sha256":"1d2b6a656c982ebe059abba03d88ceb9f4333fd7546b80a5e7391080cdc7d32d","abstract_canon_sha256":"858ce6ce86ae64b86bc0df42e025f61a824d31d010725f887f96b506b70daee1"},"schema_version":"1.0"},"canonical_sha256":"b13317d2828a138394d7280052bd3e8906e224ecbb2f51d0c624109bcbcb00b1","source":{"kind":"arxiv","id":"2412.16869","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16869","created_at":"2026-07-05T09:53:13Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16869v1","created_at":"2026-07-05T09:53:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16869","created_at":"2026-07-05T09:53:13Z"},{"alias_kind":"pith_short_12","alias_value":"WEZRPUUCRIJY","created_at":"2026-07-05T09:53:13Z"},{"alias_kind":"pith_short_16","alias_value":"WEZRPUUCRIJYHFGX","created_at":"2026-07-05T09:53:13Z"},{"alias_kind":"pith_short_8","alias_value":"WEZRPUUC","created_at":"2026-07-05T09:53:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WEZRPUUCRIJYHFGXFAAFFPJ6RE","target":"record","payload":{"canonical_record":{"source":{"id":"2412.16869","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-22T05:42:40Z","cross_cats_sorted":[],"title_canon_sha256":"1d2b6a656c982ebe059abba03d88ceb9f4333fd7546b80a5e7391080cdc7d32d","abstract_canon_sha256":"858ce6ce86ae64b86bc0df42e025f61a824d31d010725f887f96b506b70daee1"},"schema_version":"1.0"},"canonical_sha256":"b13317d2828a138394d7280052bd3e8906e224ecbb2f51d0c624109bcbcb00b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:13.943176Z","signature_b64":"XB9x9cWtrL98r6AL3IUGJha3CDtSH65KAIXp4Alxp1Fm2QDfMMEhHm7YhJts3dJ2jmRUPlgWcEz3hTpet7XmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b13317d2828a138394d7280052bd3e8906e224ecbb2f51d0c624109bcbcb00b1","last_reissued_at":"2026-07-05T09:53:13.942705Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:13.942705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.16869","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":"2026-07-05T09:53:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ScViG5ItuGCnSEuNrV7XC5KZnP/VaAMgA78iaHmnbOwPlKk8KbHPGnHDMJPiCeORIbHFpN5oQ8tOD9Jdld8iAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:51:22.927019Z"},"content_sha256":"d739f9ab847b33cb3777e5b6fecc087238d71130e9a50d063748dd5d74908109","schema_version":"1.0","event_id":"sha256:d739f9ab847b33cb3777e5b6fecc087238d71130e9a50d063748dd5d74908109"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WEZRPUUCRIJYHFGXFAAFFPJ6RE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CoF: Coarse to Fine-Grained Image Understanding for Multi-modal Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Li, Dehong Gao, Jinxia Zhang, Lei Yi, Libin Yang, Qi Xuan, Rujiao Long, Shanqing Yu, Xiaoyan Cai, Yeyuan Wang","submitted_at":"2024-12-22T05:42:40Z","abstract_excerpt":"The impressive performance of Large Language Model (LLM) has prompted researchers to develop Multi-modal LLM (MLLM), which has shown great potential for various multi-modal tasks. However, current MLLM often struggles to effectively address fine-grained multi-modal challenges. We argue that this limitation is closely linked to the models' visual grounding capabilities. The restricted spatial awareness and perceptual acuity of visual encoders frequently lead to interference from irrelevant background information in images, causing the models to overlook subtle but crucial details. As a result, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16869","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/2412.16869/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":"2026-07-05T09:53:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rk8BY34OTJBda6h6bzqPEN6AE0QZHRqPWVP24vV4CVjloWqM+luRUrv4yL637PCR+EKqhiboMGKzmpcFuqgXAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:51:22.927412Z"},"content_sha256":"75cab801b44c41e7930bba101e74a0e9b7383755790d77e770909b66e77e79ce","schema_version":"1.0","event_id":"sha256:75cab801b44c41e7930bba101e74a0e9b7383755790d77e770909b66e77e79ce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WEZRPUUCRIJYHFGXFAAFFPJ6RE/bundle.json","state_url":"https://pith.science/pith/WEZRPUUCRIJYHFGXFAAFFPJ6RE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WEZRPUUCRIJYHFGXFAAFFPJ6RE/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":"2026-07-07T13:51:22Z","links":{"resolver":"https://pith.science/pith/WEZRPUUCRIJYHFGXFAAFFPJ6RE","bundle":"https://pith.science/pith/WEZRPUUCRIJYHFGXFAAFFPJ6RE/bundle.json","state":"https://pith.science/pith/WEZRPUUCRIJYHFGXFAAFFPJ6RE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WEZRPUUCRIJYHFGXFAAFFPJ6RE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WEZRPUUCRIJYHFGXFAAFFPJ6RE","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":"858ce6ce86ae64b86bc0df42e025f61a824d31d010725f887f96b506b70daee1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-22T05:42:40Z","title_canon_sha256":"1d2b6a656c982ebe059abba03d88ceb9f4333fd7546b80a5e7391080cdc7d32d"},"schema_version":"1.0","source":{"id":"2412.16869","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16869","created_at":"2026-07-05T09:53:13Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16869v1","created_at":"2026-07-05T09:53:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16869","created_at":"2026-07-05T09:53:13Z"},{"alias_kind":"pith_short_12","alias_value":"WEZRPUUCRIJY","created_at":"2026-07-05T09:53:13Z"},{"alias_kind":"pith_short_16","alias_value":"WEZRPUUCRIJYHFGX","created_at":"2026-07-05T09:53:13Z"},{"alias_kind":"pith_short_8","alias_value":"WEZRPUUC","created_at":"2026-07-05T09:53:13Z"}],"graph_snapshots":[{"event_id":"sha256:75cab801b44c41e7930bba101e74a0e9b7383755790d77e770909b66e77e79ce","target":"graph","created_at":"2026-07-05T09:53:13Z","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/2412.16869/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The impressive performance of Large Language Model (LLM) has prompted researchers to develop Multi-modal LLM (MLLM), which has shown great potential for various multi-modal tasks. However, current MLLM often struggles to effectively address fine-grained multi-modal challenges. We argue that this limitation is closely linked to the models' visual grounding capabilities. The restricted spatial awareness and perceptual acuity of visual encoders frequently lead to interference from irrelevant background information in images, causing the models to overlook subtle but crucial details. As a result, ","authors_text":"Bin Li, Dehong Gao, Jinxia Zhang, Lei Yi, Libin Yang, Qi Xuan, Rujiao Long, Shanqing Yu, Xiaoyan Cai, Yeyuan Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-22T05:42:40Z","title":"CoF: Coarse to Fine-Grained Image Understanding for Multi-modal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16869","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:d739f9ab847b33cb3777e5b6fecc087238d71130e9a50d063748dd5d74908109","target":"record","created_at":"2026-07-05T09:53:13Z","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":"858ce6ce86ae64b86bc0df42e025f61a824d31d010725f887f96b506b70daee1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-22T05:42:40Z","title_canon_sha256":"1d2b6a656c982ebe059abba03d88ceb9f4333fd7546b80a5e7391080cdc7d32d"},"schema_version":"1.0","source":{"id":"2412.16869","kind":"arxiv","version":1}},"canonical_sha256":"b13317d2828a138394d7280052bd3e8906e224ecbb2f51d0c624109bcbcb00b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b13317d2828a138394d7280052bd3e8906e224ecbb2f51d0c624109bcbcb00b1","first_computed_at":"2026-07-05T09:53:13.942705Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:13.942705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XB9x9cWtrL98r6AL3IUGJha3CDtSH65KAIXp4Alxp1Fm2QDfMMEhHm7YhJts3dJ2jmRUPlgWcEz3hTpet7XmBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:13.943176Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.16869","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d739f9ab847b33cb3777e5b6fecc087238d71130e9a50d063748dd5d74908109","sha256:75cab801b44c41e7930bba101e74a0e9b7383755790d77e770909b66e77e79ce"],"state_sha256":"a54dd633c238ab337187662c90d820f2f88040f4d014260000902914f17f13cd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ff9bfQAtleHYkVVeqGHVSKjnddfXtqfyitkv8B3E9NWRyo6zQyrpNX0xthpx1Pn/qXNQFVIUI6dgOio6r2YLDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:51:22.929299Z","bundle_sha256":"04ea124f4a69d1907861651416a58ad840c9af87e768c55e3758224119e53757"}}