{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:S644O7FLM6W7PE5FHLZRWB7SYS","short_pith_number":"pith:S644O7FL","schema_version":"1.0","canonical_sha256":"97b9c77cab67adf793a53af31b07f2c48a410044b822197921209968f94d9c93","source":{"kind":"arxiv","id":"2602.02977","version":2},"attestation_state":"computed","paper":{"title":"Aligning Forest and Trees in Images & Long Captions for Visually Grounded Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"CAFT aligns local descriptions in long captions to image regions before forming global scene representations.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Byeonghyun Pak, Byeongju Woo, Sangwoo Mo, Stella X. Yu, Zilin Wang","submitted_at":"2026-02-03T01:31:55Z","abstract_excerpt":"Vision-language models such as CLIP often struggle to faithfully understand long, detail-rich captions, relying on dominant scene cues while overlooking fine-grained visual evidence. We propose a hierarchical vision-language learning principle for understanding scenes as part-to-whole compositions: before forming a whole-scene representation, a model should uncover what semantic parts appear where in the image. To this end, we propose CAFT (Cross-domain Alignment of Forests and Trees), a vision-language model that jointly learns local text-region alignment at intermediate representations and g"},"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":true},"canonical_record":{"source":{"id":"2602.02977","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-03T01:31:55Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3618d2c65be29b341249d95664bd7f14d9028d16bf7c984a1900de44fc446b2c","abstract_canon_sha256":"a9483e4f2a9cf675310f24a032f416d25b9131252d80a2286a9966dd07f9d022"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:23.986201Z","signature_b64":"upYKWFP3jl+TU7teBcKYfe26D6ZWzWO7pazigJASGCAPQyE+Gcp6RQR6qY7dCY/g+WGd+GEIMOW8FVpyNjWpDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97b9c77cab67adf793a53af31b07f2c48a410044b822197921209968f94d9c93","last_reissued_at":"2026-05-18T03:09:23.985521Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:23.985521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aligning Forest and Trees in Images & Long Captions for Visually Grounded Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"CAFT aligns local descriptions in long captions to image regions before forming global scene representations.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Byeonghyun Pak, Byeongju Woo, Sangwoo Mo, Stella X. Yu, Zilin Wang","submitted_at":"2026-02-03T01:31:55Z","abstract_excerpt":"Vision-language models such as CLIP often struggle to faithfully understand long, detail-rich captions, relying on dominant scene cues while overlooking fine-grained visual evidence. We propose a hierarchical vision-language learning principle for understanding scenes as part-to-whole compositions: before forming a whole-scene representation, a model should uncover what semantic parts appear where in the image. To this end, we propose CAFT (Cross-domain Alignment of Forests and Trees), a vision-language model that jointly learns local text-region alignment at intermediate representations and g"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"CAFT achieves state-of-the-art performance on six long-text retrieval benchmarks and exhibits strong scaling behavior. Experiments show that CAFT learns fine-grained representations that localize textual semantics in image regions without explicit region-level supervision.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that long captions naturally contain local descriptions that correspond to distinct scene parts, allowing the model to discover localized alignments without any region-level supervision or explicit part annotations.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CAFT achieves state-of-the-art results on long-text image retrieval benchmarks by jointly learning local text-region alignments and global image-text alignments through fine-to-coarse encoders.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CAFT aligns local descriptions in long captions to image regions before forming global scene representations.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"cdafd1a4fb73a5b2628f2b19b232934e702e23c6aa45d35cd110fdaa821467e7"},"source":{"id":"2602.02977","kind":"arxiv","version":2},"verdict":{"id":"ba226ff3-e405-4282-b468-ec9830987666","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T08:42:39.275338Z","strongest_claim":"CAFT achieves state-of-the-art performance on six long-text retrieval benchmarks and exhibits strong scaling behavior. Experiments show that CAFT learns fine-grained representations that localize textual semantics in image regions without explicit region-level supervision.","one_line_summary":"CAFT achieves state-of-the-art results on long-text image retrieval benchmarks by jointly learning local text-region alignments and global image-text alignments through fine-to-coarse encoders.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that long captions naturally contain local descriptions that correspond to distinct scene parts, allowing the model to discover localized alignments without any region-level supervision or explicit part annotations.","pith_extraction_headline":"CAFT aligns local descriptions in long captions to image regions before forming global scene representations."},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"a349154a9bcf3d230e6f0fe39dc318a25a9a21e1bacd683f5d954d6b1f9e92dd"},"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":"2602.02977","created_at":"2026-05-18T03:09:23.985618+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.02977v2","created_at":"2026-05-18T03:09:23.985618+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.02977","created_at":"2026-05-18T03:09:23.985618+00:00"},{"alias_kind":"pith_short_12","alias_value":"S644O7FLM6W7","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"S644O7FLM6W7PE5F","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"S644O7FL","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.19410","citing_title":"Vision Harnessing Agent for Open Ad-hoc Segmentation","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S644O7FLM6W7PE5FHLZRWB7SYS","json":"https://pith.science/pith/S644O7FLM6W7PE5FHLZRWB7SYS.json","graph_json":"https://pith.science/api/pith-number/S644O7FLM6W7PE5FHLZRWB7SYS/graph.json","events_json":"https://pith.science/api/pith-number/S644O7FLM6W7PE5FHLZRWB7SYS/events.json","paper":"https://pith.science/paper/S644O7FL"},"agent_actions":{"view_html":"https://pith.science/pith/S644O7FLM6W7PE5FHLZRWB7SYS","download_json":"https://pith.science/pith/S644O7FLM6W7PE5FHLZRWB7SYS.json","view_paper":"https://pith.science/paper/S644O7FL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.02977&json=true","fetch_graph":"https://pith.science/api/pith-number/S644O7FLM6W7PE5FHLZRWB7SYS/graph.json","fetch_events":"https://pith.science/api/pith-number/S644O7FLM6W7PE5FHLZRWB7SYS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S644O7FLM6W7PE5FHLZRWB7SYS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S644O7FLM6W7PE5FHLZRWB7SYS/action/storage_attestation","attest_author":"https://pith.science/pith/S644O7FLM6W7PE5FHLZRWB7SYS/action/author_attestation","sign_citation":"https://pith.science/pith/S644O7FLM6W7PE5FHLZRWB7SYS/action/citation_signature","submit_replication":"https://pith.science/pith/S644O7FLM6W7PE5FHLZRWB7SYS/action/replication_record"}},"created_at":"2026-05-18T03:09:23.985618+00:00","updated_at":"2026-05-18T03:09:23.985618+00:00"}