{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:I4BTBGLKDV36ZQ2PQRU4N5YKAU","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":"b58408eb83f5c7a2e0ec9d7310178a2f0ca9a4057d6b8cc5d8c78beae5fb583d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-26T08:45:14Z","title_canon_sha256":"9e154c3d67361848c36bee2e9992d90121ccf0c9ab7e632d92e6ad7f51f21eb9"},"schema_version":"1.0","source":{"id":"2506.21096","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21096","created_at":"2026-07-05T11:30:02Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21096v2","created_at":"2026-07-05T11:30:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21096","created_at":"2026-07-05T11:30:02Z"},{"alias_kind":"pith_short_12","alias_value":"I4BTBGLKDV36","created_at":"2026-07-05T11:30:02Z"},{"alias_kind":"pith_short_16","alias_value":"I4BTBGLKDV36ZQ2P","created_at":"2026-07-05T11:30:02Z"},{"alias_kind":"pith_short_8","alias_value":"I4BTBGLK","created_at":"2026-07-05T11:30:02Z"}],"graph_snapshots":[{"event_id":"sha256:24801e54240cb8381a0d078596d66b289803bf09d6d411bfa4b9f98208b6eb60","target":"graph","created_at":"2026-07-05T11:30:02Z","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/2506.21096/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Previous multimodal sentence representation learning methods have achieved impressive performance. However, most approaches focus on aligning images and text at a coarse level, facing two critical challenges:cross-modal misalignment bias and intra-modal semantic divergence, which significantly degrade sentence representation quality. To address these challenges, we propose DALR (Dual-level Alignment Learning for Multimodal Sentence Representation). For cross-modal alignment, we propose a consistency learning module that softens negative samples and utilizes semantic similarity from an auxiliar","authors_text":"Chong Teng, Donghong Ji, Fei Li, Haining Wang, Kang He, Yuzhe Ding","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-26T08:45:14Z","title":"DALR: Dual-level Alignment Learning for Multimodal Sentence Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21096","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":"sha256:4ad8028530c67f2d8ac94ba8606bd1a44673f145e17faa1cdfd2efccd5dc76e7","target":"record","created_at":"2026-07-05T11:30:02Z","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":"b58408eb83f5c7a2e0ec9d7310178a2f0ca9a4057d6b8cc5d8c78beae5fb583d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-26T08:45:14Z","title_canon_sha256":"9e154c3d67361848c36bee2e9992d90121ccf0c9ab7e632d92e6ad7f51f21eb9"},"schema_version":"1.0","source":{"id":"2506.21096","kind":"arxiv","version":2}},"canonical_sha256":"470330996a1d77ecc34f8469c6f70a0500d71cfa6eccde6351d30418bd7813a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"470330996a1d77ecc34f8469c6f70a0500d71cfa6eccde6351d30418bd7813a4","first_computed_at":"2026-07-05T11:30:02.673667Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:02.673667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8aNT7R5Vy+OArvj7SgI2fcNfgVkbMFxYp4pO1NTwofjdqgbqv5wD3GYfPWrzXxyjHR71bgHxylsGScMAQ5AKBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:02.674164Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.21096","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ad8028530c67f2d8ac94ba8606bd1a44673f145e17faa1cdfd2efccd5dc76e7","sha256:24801e54240cb8381a0d078596d66b289803bf09d6d411bfa4b9f98208b6eb60"],"state_sha256":"8f89d5a9f791f51906573ed9dbd22836616795d1d11baee129d64704e0d3d45d"}