{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7PHP6OVKEQDVVGUEFE5KQOEUOE","short_pith_number":"pith:7PHP6OVK","schema_version":"1.0","canonical_sha256":"fbceff3aaa24075a9a84293aa83894711cb27d41fc7feef13a5c33058e04b29b","source":{"kind":"arxiv","id":"2605.26615","version":1},"attestation_state":"computed","paper":{"title":"FAST-GOAL: Fast and Efficient Global-local Object Alignment Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chanho Eom, Hyungyu Choi, Young Kyun Jang","submitted_at":"2026-05-26T06:52:46Z","abstract_excerpt":"Vision-language models such as CLIP have shown impressive capabilities in aligning images and text, but they often struggle with lengthy and detailed text descriptions due to pre-training on short and concise captions. We present FAST-GOAL (Fast and Efficient Global-local Object Alignment Learning), an efficient fine-tuning method that enhances ability of CLIP to handle lengthy text through global-local semantic alignment. Our method consists of two key components. First, Fast Local Image-Sentence Matching (FLISM) efficiently extracts local image regions through object detection and spatial di"},"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":"2605.26615","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-26T06:52:46Z","cross_cats_sorted":[],"title_canon_sha256":"36d6cd67ca01cd8750b7764ac5d1d758a866aa685a235016e54b425784fcab3f","abstract_canon_sha256":"a7971fd7a85ecdccf14d2ff07b6eb1bd246cf708869287d03850a30507fbec77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:06:02.258338Z","signature_b64":"CSmN4OHl6YRtRp02YesPdBI6GSmN22qceubN2SJ2+QQ+YDUwi9YUO1hSss+wa4OkQDVrKZGNGtPS6uf2jcdJBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbceff3aaa24075a9a84293aa83894711cb27d41fc7feef13a5c33058e04b29b","last_reissued_at":"2026-05-27T01:06:02.257689Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:06:02.257689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FAST-GOAL: Fast and Efficient Global-local Object Alignment Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chanho Eom, Hyungyu Choi, Young Kyun Jang","submitted_at":"2026-05-26T06:52:46Z","abstract_excerpt":"Vision-language models such as CLIP have shown impressive capabilities in aligning images and text, but they often struggle with lengthy and detailed text descriptions due to pre-training on short and concise captions. We present FAST-GOAL (Fast and Efficient Global-local Object Alignment Learning), an efficient fine-tuning method that enhances ability of CLIP to handle lengthy text through global-local semantic alignment. Our method consists of two key components. First, Fast Local Image-Sentence Matching (FLISM) efficiently extracts local image regions through object detection and spatial di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26615","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/2605.26615/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":"2605.26615","created_at":"2026-05-27T01:06:02.257800+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26615v1","created_at":"2026-05-27T01:06:02.257800+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26615","created_at":"2026-05-27T01:06:02.257800+00:00"},{"alias_kind":"pith_short_12","alias_value":"7PHP6OVKEQDV","created_at":"2026-05-27T01:06:02.257800+00:00"},{"alias_kind":"pith_short_16","alias_value":"7PHP6OVKEQDVVGUE","created_at":"2026-05-27T01:06:02.257800+00:00"},{"alias_kind":"pith_short_8","alias_value":"7PHP6OVK","created_at":"2026-05-27T01:06:02.257800+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7PHP6OVKEQDVVGUEFE5KQOEUOE","json":"https://pith.science/pith/7PHP6OVKEQDVVGUEFE5KQOEUOE.json","graph_json":"https://pith.science/api/pith-number/7PHP6OVKEQDVVGUEFE5KQOEUOE/graph.json","events_json":"https://pith.science/api/pith-number/7PHP6OVKEQDVVGUEFE5KQOEUOE/events.json","paper":"https://pith.science/paper/7PHP6OVK"},"agent_actions":{"view_html":"https://pith.science/pith/7PHP6OVKEQDVVGUEFE5KQOEUOE","download_json":"https://pith.science/pith/7PHP6OVKEQDVVGUEFE5KQOEUOE.json","view_paper":"https://pith.science/paper/7PHP6OVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26615&json=true","fetch_graph":"https://pith.science/api/pith-number/7PHP6OVKEQDVVGUEFE5KQOEUOE/graph.json","fetch_events":"https://pith.science/api/pith-number/7PHP6OVKEQDVVGUEFE5KQOEUOE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7PHP6OVKEQDVVGUEFE5KQOEUOE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7PHP6OVKEQDVVGUEFE5KQOEUOE/action/storage_attestation","attest_author":"https://pith.science/pith/7PHP6OVKEQDVVGUEFE5KQOEUOE/action/author_attestation","sign_citation":"https://pith.science/pith/7PHP6OVKEQDVVGUEFE5KQOEUOE/action/citation_signature","submit_replication":"https://pith.science/pith/7PHP6OVKEQDVVGUEFE5KQOEUOE/action/replication_record"}},"created_at":"2026-05-27T01:06:02.257800+00:00","updated_at":"2026-05-27T01:06:02.257800+00:00"}