{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZQCR6P5FCDMOXJVEPHYTQK7NFB","short_pith_number":"pith:ZQCR6P5F","canonical_record":{"source":{"id":"2411.13909","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T07:47:27Z","cross_cats_sorted":[],"title_canon_sha256":"422943cf4ffe623aeffceb47045aa219fbaf7792ff4381e520bc4f170cf62ee7","abstract_canon_sha256":"8579ed3e18025f7b9b4e76f4cddcd9ffa7125212fce4bbc976b53eb2663da508"},"schema_version":"1.0"},"canonical_sha256":"cc051f3fa510d8eba6a479f1382bed287e37cde9a0cc6ef72ab3e4041c314fcf","source":{"kind":"arxiv","id":"2411.13909","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.13909","created_at":"2026-07-05T09:39:11Z"},{"alias_kind":"arxiv_version","alias_value":"2411.13909v2","created_at":"2026-07-05T09:39:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13909","created_at":"2026-07-05T09:39:11Z"},{"alias_kind":"pith_short_12","alias_value":"ZQCR6P5FCDMO","created_at":"2026-07-05T09:39:11Z"},{"alias_kind":"pith_short_16","alias_value":"ZQCR6P5FCDMOXJVE","created_at":"2026-07-05T09:39:11Z"},{"alias_kind":"pith_short_8","alias_value":"ZQCR6P5F","created_at":"2026-07-05T09:39:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZQCR6P5FCDMOXJVEPHYTQK7NFB","target":"record","payload":{"canonical_record":{"source":{"id":"2411.13909","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T07:47:27Z","cross_cats_sorted":[],"title_canon_sha256":"422943cf4ffe623aeffceb47045aa219fbaf7792ff4381e520bc4f170cf62ee7","abstract_canon_sha256":"8579ed3e18025f7b9b4e76f4cddcd9ffa7125212fce4bbc976b53eb2663da508"},"schema_version":"1.0"},"canonical_sha256":"cc051f3fa510d8eba6a479f1382bed287e37cde9a0cc6ef72ab3e4041c314fcf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:11.053830Z","signature_b64":"tE4eST0kKBfTWcxrCa77GbP3CsI2TPZC2HxYwutjpNoz02o566mPRthetK7j2PVSZQlOOz4rjO2uCkyqxGgXDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc051f3fa510d8eba6a479f1382bed287e37cde9a0cc6ef72ab3e4041c314fcf","last_reissued_at":"2026-07-05T09:39:11.053484Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:11.053484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.13909","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:39:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dtYKnvCGAmnj7ioXCx2gGSEA2bd5LfVlASMJxux7nakVaSN+WM/+cgalsjxyeX/vwftrn8zeEKWFRuf6om9gBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T05:53:56.661954Z"},"content_sha256":"cef1402592f190a62e581c741bb3a54e08d3ded5b173f6fd8a6c6bbbbae7410b","schema_version":"1.0","event_id":"sha256:cef1402592f190a62e581c741bb3a54e08d3ded5b173f6fd8a6c6bbbbae7410b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZQCR6P5FCDMOXJVEPHYTQK7NFB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Panther: Illuminate the Sight of Multimodal LLMs with Instruction-Guided Visual Prompts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenglu Zhu, Honglin Li, Jingdong Chen, Lin Yang, Ming Yang, Yuting Gao","submitted_at":"2024-11-21T07:47:27Z","abstract_excerpt":"Multimodal large language models (MLLMs) are closing the gap to human visual perception capability rapidly, while, still lag behind on attending to subtle images details or locating small objects precisely, etc. Common schemes to tackle these issues include deploying multiple vision encoders or operating on original high-resolution images. Few studies have concentrated on taking the textual instruction into improving visual representation, resulting in losing focus in some vision-centric tasks, a phenomenon we herein termed as Amblyopia. In this work, we introduce Panther, a MLLM that closely "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13909","kind":"arxiv","version":2},"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/2411.13909/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":"2026-07-05T09:39:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NFg5toqWPb+0gU86WDTXZroXXZLTiOoW8v5pKEY37H8340ZpOBLyb0LaVCmhdI6m3hE35awLpszRzmId5cBADA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T05:53:56.662505Z"},"content_sha256":"1082722981960ab95c23f92b1194f051e3807f5ff35fa7af8d43283d9636f519","schema_version":"1.0","event_id":"sha256:1082722981960ab95c23f92b1194f051e3807f5ff35fa7af8d43283d9636f519"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZQCR6P5FCDMOXJVEPHYTQK7NFB/bundle.json","state_url":"https://pith.science/pith/ZQCR6P5FCDMOXJVEPHYTQK7NFB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZQCR6P5FCDMOXJVEPHYTQK7NFB/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":"2026-08-13T05:53:56Z","links":{"resolver":"https://pith.science/pith/ZQCR6P5FCDMOXJVEPHYTQK7NFB","bundle":"https://pith.science/pith/ZQCR6P5FCDMOXJVEPHYTQK7NFB/bundle.json","state":"https://pith.science/pith/ZQCR6P5FCDMOXJVEPHYTQK7NFB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZQCR6P5FCDMOXJVEPHYTQK7NFB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZQCR6P5FCDMOXJVEPHYTQK7NFB","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":"8579ed3e18025f7b9b4e76f4cddcd9ffa7125212fce4bbc976b53eb2663da508","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T07:47:27Z","title_canon_sha256":"422943cf4ffe623aeffceb47045aa219fbaf7792ff4381e520bc4f170cf62ee7"},"schema_version":"1.0","source":{"id":"2411.13909","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.13909","created_at":"2026-07-05T09:39:11Z"},{"alias_kind":"arxiv_version","alias_value":"2411.13909v2","created_at":"2026-07-05T09:39:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13909","created_at":"2026-07-05T09:39:11Z"},{"alias_kind":"pith_short_12","alias_value":"ZQCR6P5FCDMO","created_at":"2026-07-05T09:39:11Z"},{"alias_kind":"pith_short_16","alias_value":"ZQCR6P5FCDMOXJVE","created_at":"2026-07-05T09:39:11Z"},{"alias_kind":"pith_short_8","alias_value":"ZQCR6P5F","created_at":"2026-07-05T09:39:11Z"}],"graph_snapshots":[{"event_id":"sha256:1082722981960ab95c23f92b1194f051e3807f5ff35fa7af8d43283d9636f519","target":"graph","created_at":"2026-07-05T09:39:11Z","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/2411.13909/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) are closing the gap to human visual perception capability rapidly, while, still lag behind on attending to subtle images details or locating small objects precisely, etc. Common schemes to tackle these issues include deploying multiple vision encoders or operating on original high-resolution images. Few studies have concentrated on taking the textual instruction into improving visual representation, resulting in losing focus in some vision-centric tasks, a phenomenon we herein termed as Amblyopia. In this work, we introduce Panther, a MLLM that closely ","authors_text":"Chenglu Zhu, Honglin Li, Jingdong Chen, Lin Yang, Ming Yang, Yuting Gao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T07:47:27Z","title":"Panther: Illuminate the Sight of Multimodal LLMs with Instruction-Guided Visual Prompts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13909","kind":"arxiv","version":2},"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:cef1402592f190a62e581c741bb3a54e08d3ded5b173f6fd8a6c6bbbbae7410b","target":"record","created_at":"2026-07-05T09:39:11Z","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":"8579ed3e18025f7b9b4e76f4cddcd9ffa7125212fce4bbc976b53eb2663da508","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T07:47:27Z","title_canon_sha256":"422943cf4ffe623aeffceb47045aa219fbaf7792ff4381e520bc4f170cf62ee7"},"schema_version":"1.0","source":{"id":"2411.13909","kind":"arxiv","version":2}},"canonical_sha256":"cc051f3fa510d8eba6a479f1382bed287e37cde9a0cc6ef72ab3e4041c314fcf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc051f3fa510d8eba6a479f1382bed287e37cde9a0cc6ef72ab3e4041c314fcf","first_computed_at":"2026-07-05T09:39:11.053484Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:39:11.053484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tE4eST0kKBfTWcxrCa77GbP3CsI2TPZC2HxYwutjpNoz02o566mPRthetK7j2PVSZQlOOz4rjO2uCkyqxGgXDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:39:11.053830Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.13909","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cef1402592f190a62e581c741bb3a54e08d3ded5b173f6fd8a6c6bbbbae7410b","sha256:1082722981960ab95c23f92b1194f051e3807f5ff35fa7af8d43283d9636f519"],"state_sha256":"1d828bfaf9ce88244c57f6a4b0f000e9df577c4dc52475af636346d264a70f2f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W+P6Zob/TBg1fU17unO87Jlqg96Wmx29o+03EruJa+BL6Qr6D0G2wXmdbqnfq7ktdYgJF0tvyqaGSCYu0shUAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T05:53:56.667767Z","bundle_sha256":"62fad72d81108eb9c014f647c5699379dfadc3a46d322bd2a16451ffb2b13c5d"}}