{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XFEEJUUCRSC3ABFDPAUSX7WV24","short_pith_number":"pith:XFEEJUUC","schema_version":"1.0","canonical_sha256":"b94844d2828c85b004a378292bfed5d73894ed824250f4573d96098c51c83e94","source":{"kind":"arxiv","id":"2412.03927","version":1},"attestation_state":"computed","paper":{"title":"MegaCOIN: Enhancing Medium-Grained Color Perception for Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ming-Chang Chiu, Pin-Yu Chen, Shicheng Wen, Xuezhe Ma","submitted_at":"2024-12-05T07:06:17Z","abstract_excerpt":"In vision-language models (VLMs), the ability to perceive and interpret color and physical environment is crucial for achieving contextually accurate understanding and interaction. However, despite advances in multimodal modeling, there remains a significant lack of specialized datasets that rigorously evaluate a model's capacity to discern subtle color variations and spatial context -- critical elements for situational comprehension and reliable deployment across real-world applications. Toward that goal, we curate MegaCOIN, a high-quality, human-labeled dataset based on \\emph{real} images wi"},"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":"2412.03927","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T07:06:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ee0b5911a4cc4a4e396c53eea78f10d808eb0a2e9612a975b0cab8060c638495","abstract_canon_sha256":"6362b649d6122462a224db63606eb42224ea05928b4c4f86ae9e2faf34032706"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:56.505681Z","signature_b64":"AT5q2peihS7VwC7SNoXRJGsCYFuylPFr5gj15/I8cduEmTXEPJdmt3Jkseue6A1trZj0FsThqAmib8IR4rBRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b94844d2828c85b004a378292bfed5d73894ed824250f4573d96098c51c83e94","last_reissued_at":"2026-07-05T09:44:56.505202Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:56.505202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MegaCOIN: Enhancing Medium-Grained Color Perception for Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ming-Chang Chiu, Pin-Yu Chen, Shicheng Wen, Xuezhe Ma","submitted_at":"2024-12-05T07:06:17Z","abstract_excerpt":"In vision-language models (VLMs), the ability to perceive and interpret color and physical environment is crucial for achieving contextually accurate understanding and interaction. However, despite advances in multimodal modeling, there remains a significant lack of specialized datasets that rigorously evaluate a model's capacity to discern subtle color variations and spatial context -- critical elements for situational comprehension and reliable deployment across real-world applications. Toward that goal, we curate MegaCOIN, a high-quality, human-labeled dataset based on \\emph{real} images wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03927","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/2412.03927/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":"2412.03927","created_at":"2026-07-05T09:44:56.505259+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.03927v1","created_at":"2026-07-05T09:44:56.505259+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03927","created_at":"2026-07-05T09:44:56.505259+00:00"},{"alias_kind":"pith_short_12","alias_value":"XFEEJUUCRSC3","created_at":"2026-07-05T09:44:56.505259+00:00"},{"alias_kind":"pith_short_16","alias_value":"XFEEJUUCRSC3ABFD","created_at":"2026-07-05T09:44:56.505259+00:00"},{"alias_kind":"pith_short_8","alias_value":"XFEEJUUC","created_at":"2026-07-05T09:44:56.505259+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.09082","citing_title":"AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XFEEJUUCRSC3ABFDPAUSX7WV24","json":"https://pith.science/pith/XFEEJUUCRSC3ABFDPAUSX7WV24.json","graph_json":"https://pith.science/api/pith-number/XFEEJUUCRSC3ABFDPAUSX7WV24/graph.json","events_json":"https://pith.science/api/pith-number/XFEEJUUCRSC3ABFDPAUSX7WV24/events.json","paper":"https://pith.science/paper/XFEEJUUC"},"agent_actions":{"view_html":"https://pith.science/pith/XFEEJUUCRSC3ABFDPAUSX7WV24","download_json":"https://pith.science/pith/XFEEJUUCRSC3ABFDPAUSX7WV24.json","view_paper":"https://pith.science/paper/XFEEJUUC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.03927&json=true","fetch_graph":"https://pith.science/api/pith-number/XFEEJUUCRSC3ABFDPAUSX7WV24/graph.json","fetch_events":"https://pith.science/api/pith-number/XFEEJUUCRSC3ABFDPAUSX7WV24/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XFEEJUUCRSC3ABFDPAUSX7WV24/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XFEEJUUCRSC3ABFDPAUSX7WV24/action/storage_attestation","attest_author":"https://pith.science/pith/XFEEJUUCRSC3ABFDPAUSX7WV24/action/author_attestation","sign_citation":"https://pith.science/pith/XFEEJUUCRSC3ABFDPAUSX7WV24/action/citation_signature","submit_replication":"https://pith.science/pith/XFEEJUUCRSC3ABFDPAUSX7WV24/action/replication_record"}},"created_at":"2026-07-05T09:44:56.505259+00:00","updated_at":"2026-07-05T09:44:56.505259+00:00"}