{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NHQFB4N2IRLV7332GDFE3N5GMA","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":"0c243addd3a79a3ba9e5d809a65ef7bb57210afb74c33c2a46566f42073c5ed3","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-31T11:32:15Z","title_canon_sha256":"2c73ee6fc16bb5a4954fd9aaa8c10297454b392bd8822b5dbc5257f680abbfe2"},"schema_version":"1.0","source":{"id":"2510.27391","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.27391","created_at":"2026-05-29T02:05:37Z"},{"alias_kind":"arxiv_version","alias_value":"2510.27391v2","created_at":"2026-05-29T02:05:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.27391","created_at":"2026-05-29T02:05:37Z"},{"alias_kind":"pith_short_12","alias_value":"NHQFB4N2IRLV","created_at":"2026-05-29T02:05:37Z"},{"alias_kind":"pith_short_16","alias_value":"NHQFB4N2IRLV7332","created_at":"2026-05-29T02:05:37Z"},{"alias_kind":"pith_short_8","alias_value":"NHQFB4N2","created_at":"2026-05-29T02:05:37Z"}],"graph_snapshots":[{"event_id":"sha256:6946f713894e754c62148e42d34a12a521495c8958a9f9fd4d859f8ae28b2505","target":"graph","created_at":"2026-05-29T02:05:37Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2510.27391/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Mehrtash Harandi, Pengxiang Li, Wei Wu, Xiaomeng Fan, Yunde Jia, Yuwei Wu, Zhi Gao","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-31T11:32:15Z","title":"Modality Alignment across Trees on Heterogeneous Hyperbolic Manifolds"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.27391","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:22a2fccd75f22d3df189fdd3c1838969d1753c57171766861f5042f31db4a4b6","target":"record","created_at":"2026-05-29T02:05:37Z","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":"0c243addd3a79a3ba9e5d809a65ef7bb57210afb74c33c2a46566f42073c5ed3","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-31T11:32:15Z","title_canon_sha256":"2c73ee6fc16bb5a4954fd9aaa8c10297454b392bd8822b5dbc5257f680abbfe2"},"schema_version":"1.0","source":{"id":"2510.27391","kind":"arxiv","version":2}},"canonical_sha256":"69e050f1ba44575fef7a30ca4db7a6600c252bcaedc4e3c934a0cf1a3b64053f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69e050f1ba44575fef7a30ca4db7a6600c252bcaedc4e3c934a0cf1a3b64053f","first_computed_at":"2026-05-29T02:05:37.484543Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:05:37.484543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yk1azc9FSkwnZ4sqkdhVDpK6iy0e0ohac8IzxlEHh7vwdSsBUm+0jczRBCJ3K2SdKgDGzBbG9uxuPEcCjeJPBw==","signature_status":"signed_v1","signed_at":"2026-05-29T02:05:37.485212Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.27391","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22a2fccd75f22d3df189fdd3c1838969d1753c57171766861f5042f31db4a4b6","sha256:6946f713894e754c62148e42d34a12a521495c8958a9f9fd4d859f8ae28b2505"],"state_sha256":"1384939d1eb58ac14087dad4ded907c1f9d273ebabac3e97eb0cad010fa88ab6"}