{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:USXFY7WS2PXAGEDHS3JU5JKPCP","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":"23770703cb012af99ce219902fbc314102469b779ccfe312d4bf540bde7e5168","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-14T09:31:34Z","title_canon_sha256":"55c8e902f5afe3cc2425d3d15a1f87a7975e7dff5feb1800b2da562e32c2cc00"},"schema_version":"1.0","source":{"id":"2507.10095","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.10095","created_at":"2026-07-05T11:44:51Z"},{"alias_kind":"arxiv_version","alias_value":"2507.10095v2","created_at":"2026-07-05T11:44:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10095","created_at":"2026-07-05T11:44:51Z"},{"alias_kind":"pith_short_12","alias_value":"USXFY7WS2PXA","created_at":"2026-07-05T11:44:51Z"},{"alias_kind":"pith_short_16","alias_value":"USXFY7WS2PXAGEDH","created_at":"2026-07-05T11:44:51Z"},{"alias_kind":"pith_short_8","alias_value":"USXFY7WS","created_at":"2026-07-05T11:44:51Z"}],"graph_snapshots":[{"event_id":"sha256:88ee34516439990d1bf7e0a2340c2e43edd5e81f99f46af829370113824494bb","target":"graph","created_at":"2026-07-05T11:44:51Z","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/2507.10095/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"CLIP has shown promising performance across many short-text tasks in a zero-shot manner. However, limited by the input length of the text encoder, CLIP struggles on under-stream tasks with long-text inputs ($>77$ tokens). To remedy this issue, we propose FIX-CLIP, which includes three novel modules: (1) A dual-branch training pipeline that aligns short and long texts with masked and raw images, respectively, which boosts the long-text representation while preserving the short-text ability. (2) Multiple learnable regional prompts with unidirectional masks in Transformer layers for regional info","authors_text":"Bingchao Wang, Dongsheng Jiang, Jianyu Ding, Jie Yang, Wei Liu, Xuanang Gao, Yin Li, Zhiwei Ning","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-14T09:31:34Z","title":"FIX-CLIP: Dual-Branch Hierarchical Contrastive Learning via Synthetic Captions for Better Understanding of Long Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10095","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:a0a4a81fadaadcb293cbdf98340e25f9eb9e8f6c645999951f84766a5e51b7c5","target":"record","created_at":"2026-07-05T11:44:51Z","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":"23770703cb012af99ce219902fbc314102469b779ccfe312d4bf540bde7e5168","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-14T09:31:34Z","title_canon_sha256":"55c8e902f5afe3cc2425d3d15a1f87a7975e7dff5feb1800b2da562e32c2cc00"},"schema_version":"1.0","source":{"id":"2507.10095","kind":"arxiv","version":2}},"canonical_sha256":"a4ae5c7ed2d3ee03106796d34ea54f13c825613975d0d8c9f2138ccdbc6a9490","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4ae5c7ed2d3ee03106796d34ea54f13c825613975d0d8c9f2138ccdbc6a9490","first_computed_at":"2026-07-05T11:44:51.313305Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:51.313305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Eox2M69HvvbA39GZmNTNJ8Sz5Qg+5RGbAG8IMrGnsu6dU+ujJWEHTErfeR9nIaDT0nHqdOwKE/hSa0SefGrlDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:51.313933Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.10095","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0a4a81fadaadcb293cbdf98340e25f9eb9e8f6c645999951f84766a5e51b7c5","sha256:88ee34516439990d1bf7e0a2340c2e43edd5e81f99f46af829370113824494bb"],"state_sha256":"ec21eded6d77f95d2cc9cd6e00df7bbc723a1b007ca5d82cfe960188df83ded7"}