{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JURUABU2K3E7EQW6UFPC3CHKED","short_pith_number":"pith:JURUABU2","schema_version":"1.0","canonical_sha256":"4d2340069a56c9f242dea15e2d88ea20f6553efdf039654313a213e66839fd1d","source":{"kind":"arxiv","id":"2310.00582","version":3},"attestation_state":"computed","paper":{"title":"Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ming Yang, Qingpei Guo, Shiliang Zhang, Shiyu Xuan","submitted_at":"2023-10-01T05:53:15Z","abstract_excerpt":"Multi-modal Large Language Models (MLLMs) have shown remarkable capabilities in various multi-modal tasks. Nevertheless, their performance in fine-grained image understanding tasks is still limited. To address this issue, this paper proposes a new framework to enhance the fine-grained image understanding abilities of MLLMs. Specifically, we present a new method for constructing the instruction tuning dataset at a low cost by leveraging annotations in existing datasets. A self-consistent bootstrapping method is also introduced to extend existing dense object annotations into high-quality referr"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.00582","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-01T05:53:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"22ae7907a1ed171f3b237f81ae345bfe0f7ad75acc67399e4dbbec2b16ec1d31","abstract_canon_sha256":"5c77bdee8a22bc081ee3beddcf0cc27a2ebf61234cb8cdc4d37a996f6a644ff2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:24.807366Z","signature_b64":"q1aiO3AYsDWajSdkb33F3IL0KVFza6GV77z942iEKygmdaCUaeGlWO0yED5mfw7u9aYnjDby8FXfK6BrEAY5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d2340069a56c9f242dea15e2d88ea20f6553efdf039654313a213e66839fd1d","last_reissued_at":"2026-07-05T07:55:24.806882Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:24.806882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ming Yang, Qingpei Guo, Shiliang Zhang, Shiyu Xuan","submitted_at":"2023-10-01T05:53:15Z","abstract_excerpt":"Multi-modal Large Language Models (MLLMs) have shown remarkable capabilities in various multi-modal tasks. Nevertheless, their performance in fine-grained image understanding tasks is still limited. To address this issue, this paper proposes a new framework to enhance the fine-grained image understanding abilities of MLLMs. Specifically, we present a new method for constructing the instruction tuning dataset at a low cost by leveraging annotations in existing datasets. A self-consistent bootstrapping method is also introduced to extend existing dense object annotations into high-quality referr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00582","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/2310.00582/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.00582","created_at":"2026-07-05T07:55:24.806944+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.00582v3","created_at":"2026-07-05T07:55:24.806944+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00582","created_at":"2026-07-05T07:55:24.806944+00:00"},{"alias_kind":"pith_short_12","alias_value":"JURUABU2K3E7","created_at":"2026-07-05T07:55:24.806944+00:00"},{"alias_kind":"pith_short_16","alias_value":"JURUABU2K3E7EQW6","created_at":"2026-07-05T07:55:24.806944+00:00"},{"alias_kind":"pith_short_8","alias_value":"JURUABU2","created_at":"2026-07-05T07:55:24.806944+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2306.13549","citing_title":"A Survey on Multimodal Large Language Models","ref_index":141,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JURUABU2K3E7EQW6UFPC3CHKED","json":"https://pith.science/pith/JURUABU2K3E7EQW6UFPC3CHKED.json","graph_json":"https://pith.science/api/pith-number/JURUABU2K3E7EQW6UFPC3CHKED/graph.json","events_json":"https://pith.science/api/pith-number/JURUABU2K3E7EQW6UFPC3CHKED/events.json","paper":"https://pith.science/paper/JURUABU2"},"agent_actions":{"view_html":"https://pith.science/pith/JURUABU2K3E7EQW6UFPC3CHKED","download_json":"https://pith.science/pith/JURUABU2K3E7EQW6UFPC3CHKED.json","view_paper":"https://pith.science/paper/JURUABU2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.00582&json=true","fetch_graph":"https://pith.science/api/pith-number/JURUABU2K3E7EQW6UFPC3CHKED/graph.json","fetch_events":"https://pith.science/api/pith-number/JURUABU2K3E7EQW6UFPC3CHKED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JURUABU2K3E7EQW6UFPC3CHKED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JURUABU2K3E7EQW6UFPC3CHKED/action/storage_attestation","attest_author":"https://pith.science/pith/JURUABU2K3E7EQW6UFPC3CHKED/action/author_attestation","sign_citation":"https://pith.science/pith/JURUABU2K3E7EQW6UFPC3CHKED/action/citation_signature","submit_replication":"https://pith.science/pith/JURUABU2K3E7EQW6UFPC3CHKED/action/replication_record"}},"created_at":"2026-07-05T07:55:24.806944+00:00","updated_at":"2026-07-05T07:55:24.806944+00:00"}