{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:S644O7FLM6W7PE5FHLZRWB7SYS","short_pith_number":"pith:S644O7FL","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"},"canonical_sha256":"97b9c77cab67adf793a53af31b07f2c48a410044b822197921209968f94d9c93","source":{"kind":"arxiv","id":"2602.02977","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.02977","created_at":"2026-05-18T03:09:23Z"},{"alias_kind":"arxiv_version","alias_value":"2602.02977v2","created_at":"2026-05-18T03:09:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.02977","created_at":"2026-05-18T03:09:23Z"},{"alias_kind":"pith_short_12","alias_value":"S644O7FLM6W7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"S644O7FLM6W7PE5F","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"S644O7FL","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:S644O7FLM6W7PE5FHLZRWB7SYS","target":"record","payload":{"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"},"canonical_sha256":"97b9c77cab67adf793a53af31b07f2c48a410044b822197921209968f94d9c93","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"},"source_kind":"arxiv","source_id":"2602.02977","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":"2026-05-18T03:09:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4zX2HIE66q+9CUgxh//2c65GxKB92VgaaZb0BD9oXwfEAKI2s07gVgGYUsHrMw7DqQ3vhrZ4qOkuBexetiO9Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T04:36:15.000003Z"},"content_sha256":"d0c5e55929b11ff6b1830428410462f4e3d06b719a868a2d1976d6f8fdaa680d","schema_version":"1.0","event_id":"sha256:d0c5e55929b11ff6b1830428410462f4e3d06b719a868a2d1976d6f8fdaa680d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:S644O7FLM6W7PE5FHLZRWB7SYS","target":"graph","payload":{"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"},"verdict_id":"ba226ff3-e405-4282-b468-ec9830987666"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zexPg36M5+kbv7uQWDuXqz+A6fVYoGS9JvGT/9uZbOXxSlF79DwJ34yt3eXceUQreHpLa4OePM3B7b99MLegDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T04:36:15.000861Z"},"content_sha256":"d7e251f4c41d0b4765e2e2057552c84dda6b2b42b3735e6117d43d2306c8e0d8","schema_version":"1.0","event_id":"sha256:d7e251f4c41d0b4765e2e2057552c84dda6b2b42b3735e6117d43d2306c8e0d8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S644O7FLM6W7PE5FHLZRWB7SYS/bundle.json","state_url":"https://pith.science/pith/S644O7FLM6W7PE5FHLZRWB7SYS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S644O7FLM6W7PE5FHLZRWB7SYS/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":"2026-05-22T04:36:15Z","links":{"resolver":"https://pith.science/pith/S644O7FLM6W7PE5FHLZRWB7SYS","bundle":"https://pith.science/pith/S644O7FLM6W7PE5FHLZRWB7SYS/bundle.json","state":"https://pith.science/pith/S644O7FLM6W7PE5FHLZRWB7SYS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S644O7FLM6W7PE5FHLZRWB7SYS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:S644O7FLM6W7PE5FHLZRWB7SYS","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":"a9483e4f2a9cf675310f24a032f416d25b9131252d80a2286a9966dd07f9d022","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-03T01:31:55Z","title_canon_sha256":"3618d2c65be29b341249d95664bd7f14d9028d16bf7c984a1900de44fc446b2c"},"schema_version":"1.0","source":{"id":"2602.02977","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.02977","created_at":"2026-05-18T03:09:23Z"},{"alias_kind":"arxiv_version","alias_value":"2602.02977v2","created_at":"2026-05-18T03:09:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.02977","created_at":"2026-05-18T03:09:23Z"},{"alias_kind":"pith_short_12","alias_value":"S644O7FLM6W7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"S644O7FLM6W7PE5F","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"S644O7FL","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:d7e251f4c41d0b4765e2e2057552c84dda6b2b42b3735e6117d43d2306c8e0d8","target":"graph","created_at":"2026-05-18T03:09:23Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"CAFT aligns local descriptions in long captions to image regions before forming global scene representations."}],"snapshot_sha256":"cdafd1a4fb73a5b2628f2b19b232934e702e23c6aa45d35cd110fdaa821467e7"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"a349154a9bcf3d230e6f0fe39dc318a25a9a21e1bacd683f5d954d6b1f9e92dd"},"paper":{"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","authors_text":"Byeonghyun Pak, Byeongju Woo, Sangwoo Mo, Stella X. Yu, Zilin Wang","cross_cats":["cs.AI","cs.LG"],"headline":"CAFT aligns local descriptions in long captions to image regions before forming global scene representations.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-03T01:31:55Z","title":"Aligning Forest and Trees in Images & Long Captions for Visually Grounded Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.02977","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-16T08:42:39.275338Z","id":"ba226ff3-e405-4282-b468-ec9830987666","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"CAFT aligns local descriptions in long captions to image regions before forming global scene representations.","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.","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."}},"verdict_id":"ba226ff3-e405-4282-b468-ec9830987666"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d0c5e55929b11ff6b1830428410462f4e3d06b719a868a2d1976d6f8fdaa680d","target":"record","created_at":"2026-05-18T03:09:23Z","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":"a9483e4f2a9cf675310f24a032f416d25b9131252d80a2286a9966dd07f9d022","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-03T01:31:55Z","title_canon_sha256":"3618d2c65be29b341249d95664bd7f14d9028d16bf7c984a1900de44fc446b2c"},"schema_version":"1.0","source":{"id":"2602.02977","kind":"arxiv","version":2}},"canonical_sha256":"97b9c77cab67adf793a53af31b07f2c48a410044b822197921209968f94d9c93","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97b9c77cab67adf793a53af31b07f2c48a410044b822197921209968f94d9c93","first_computed_at":"2026-05-18T03:09:23.985521Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:23.985521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"upYKWFP3jl+TU7teBcKYfe26D6ZWzWO7pazigJASGCAPQyE+Gcp6RQR6qY7dCY/g+WGd+GEIMOW8FVpyNjWpDw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:23.986201Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.02977","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d0c5e55929b11ff6b1830428410462f4e3d06b719a868a2d1976d6f8fdaa680d","sha256:d7e251f4c41d0b4765e2e2057552c84dda6b2b42b3735e6117d43d2306c8e0d8"],"state_sha256":"19174a38d79acc73a5a028620d317855612790a3560fb7b4c8bccfee0726ccaf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y1Jhub5NSguRe/e7IkG0ppCEv3fnRVUeFODYRKmCOPpJ6r67/6JiluxdAVtUU4q57YoP4rqhjTss3BWXg0WxAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T04:36:15.004890Z","bundle_sha256":"9dbbed50842f95f64e85d161f0abd9401ee6346ff8b3d677b5fb9d20b703dc62"}}