{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NHQFB4N2IRLV7332GDFE3N5GMA","short_pith_number":"pith:NHQFB4N2","schema_version":"1.0","canonical_sha256":"69e050f1ba44575fef7a30ca4db7a6600c252bcaedc4e3c934a0cf1a3b64053f","source":{"kind":"arxiv","id":"2510.27391","version":2},"attestation_state":"computed","paper":{"title":"Modality Alignment across Trees on Heterogeneous Hyperbolic Manifolds","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Mehrtash Harandi, Pengxiang Li, Wei Wu, Xiaomeng Fan, Yunde Jia, Yuwei Wu, Zhi Gao","submitted_at":"2025-10-31T11:32:15Z","abstract_excerpt":"Modality alignment is critical for vision-language models (VLMs) to effectively integrate information across modalities. However, existing methods extract hierarchical features from text while representing each image with a single feature, leading to asymmetric and suboptimal alignment. To address this, we propose Alignment across Trees, a method that constructs and aligns tree-like hierarchical features for both image and text modalities. Specifically, we introduce a semantic-aware visual feature extraction framework that applies a cross-attention mechanism to visual class tokens from interme"},"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":"2510.27391","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-31T11:32:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2c73ee6fc16bb5a4954fd9aaa8c10297454b392bd8822b5dbc5257f680abbfe2","abstract_canon_sha256":"0c243addd3a79a3ba9e5d809a65ef7bb57210afb74c33c2a46566f42073c5ed3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:05:37.485212Z","signature_b64":"yk1azc9FSkwnZ4sqkdhVDpK6iy0e0ohac8IzxlEHh7vwdSsBUm+0jczRBCJ3K2SdKgDGzBbG9uxuPEcCjeJPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69e050f1ba44575fef7a30ca4db7a6600c252bcaedc4e3c934a0cf1a3b64053f","last_reissued_at":"2026-05-29T02:05:37.484543Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:05:37.484543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modality Alignment across Trees on Heterogeneous Hyperbolic Manifolds","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Mehrtash Harandi, Pengxiang Li, Wei Wu, Xiaomeng Fan, Yunde Jia, Yuwei Wu, Zhi Gao","submitted_at":"2025-10-31T11:32:15Z","abstract_excerpt":"Modality alignment is critical for vision-language models (VLMs) to effectively integrate information across modalities. However, existing methods extract hierarchical features from text while representing each image with a single feature, leading to asymmetric and suboptimal alignment. To address this, we propose Alignment across Trees, a method that constructs and aligns tree-like hierarchical features for both image and text modalities. Specifically, we introduce a semantic-aware visual feature extraction framework that applies a cross-attention mechanism to visual class tokens from interme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.27391","kind":"arxiv","version":2},"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/2510.27391/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":"2510.27391","created_at":"2026-05-29T02:05:37.484633+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.27391v2","created_at":"2026-05-29T02:05:37.484633+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.27391","created_at":"2026-05-29T02:05:37.484633+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHQFB4N2IRLV","created_at":"2026-05-29T02:05:37.484633+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHQFB4N2IRLV7332","created_at":"2026-05-29T02:05:37.484633+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHQFB4N2","created_at":"2026-05-29T02:05:37.484633+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/NHQFB4N2IRLV7332GDFE3N5GMA","json":"https://pith.science/pith/NHQFB4N2IRLV7332GDFE3N5GMA.json","graph_json":"https://pith.science/api/pith-number/NHQFB4N2IRLV7332GDFE3N5GMA/graph.json","events_json":"https://pith.science/api/pith-number/NHQFB4N2IRLV7332GDFE3N5GMA/events.json","paper":"https://pith.science/paper/NHQFB4N2"},"agent_actions":{"view_html":"https://pith.science/pith/NHQFB4N2IRLV7332GDFE3N5GMA","download_json":"https://pith.science/pith/NHQFB4N2IRLV7332GDFE3N5GMA.json","view_paper":"https://pith.science/paper/NHQFB4N2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.27391&json=true","fetch_graph":"https://pith.science/api/pith-number/NHQFB4N2IRLV7332GDFE3N5GMA/graph.json","fetch_events":"https://pith.science/api/pith-number/NHQFB4N2IRLV7332GDFE3N5GMA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHQFB4N2IRLV7332GDFE3N5GMA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHQFB4N2IRLV7332GDFE3N5GMA/action/storage_attestation","attest_author":"https://pith.science/pith/NHQFB4N2IRLV7332GDFE3N5GMA/action/author_attestation","sign_citation":"https://pith.science/pith/NHQFB4N2IRLV7332GDFE3N5GMA/action/citation_signature","submit_replication":"https://pith.science/pith/NHQFB4N2IRLV7332GDFE3N5GMA/action/replication_record"}},"created_at":"2026-05-29T02:05:37.484633+00:00","updated_at":"2026-05-29T02:05:37.484633+00:00"}