{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:45344GNCX5D3JSA2RSIAXF7XKC","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"61a031d1f8fe773c206ac2cf3654d0702ff256dd90fe2b3b359832f88e2f5ae9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T17:09:24Z","title_canon_sha256":"6b84e25eddd836ec4e661f3c76b6639ae80b4f275c45108863e905a3e124f2d4"},"schema_version":"1.0","source":{"id":"2608.05260","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.05260","created_at":"2026-08-07T00:46:37Z"},{"alias_kind":"arxiv_version","alias_value":"2608.05260v1","created_at":"2026-08-07T00:46:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05260","created_at":"2026-08-07T00:46:37Z"},{"alias_kind":"pith_short_12","alias_value":"45344GNCX5D3","created_at":"2026-08-07T00:46:37Z"},{"alias_kind":"pith_short_16","alias_value":"45344GNCX5D3JSA2","created_at":"2026-08-07T00:46:37Z"},{"alias_kind":"pith_short_8","alias_value":"45344GNC","created_at":"2026-08-07T00:46:37Z"}],"graph_snapshots":[{"event_id":"sha256:a6575e692b8eef5817910b38bc19a56fb3c7226872c2eb8e8782d617cb8942ca","target":"graph","created_at":"2026-08-07T00:46:37Z","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/2608.05260/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive vision-language models such as CLIP and BLIP are typically trained on short image captions, limiting their ability to retrieve images from detailed textual descriptions. While methods such as Long-CLIP extend the token limit through positional embedding interpolation, we ask a simpler question: does training text granularity alone determine long-text retrieval performance? We present a systematic study of supervision ranging from single captions to multi-sentence paragraphs for contrastive image-text retrieval. Using a synthetic pipeline based on Qwen2-VL and Llama 3.2 Vision, we g","authors_text":"Amin Tabrizian, Arsyi Aziz, Binshuai Wang, Mahyar Ghazanfari, Peng Wei","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T17:09:24Z","title":"A Paragraph is Worth a Thousand Captions: Rethinking Text Supervision for Vision-Language Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05260","kind":"arxiv","version":1},"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:e8429a27d2431c13cfded9ed5dfbb9ccbb07b4188778665d52047d0d68e4532c","target":"record","created_at":"2026-08-07T00:46:37Z","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":"61a031d1f8fe773c206ac2cf3654d0702ff256dd90fe2b3b359832f88e2f5ae9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T17:09:24Z","title_canon_sha256":"6b84e25eddd836ec4e661f3c76b6639ae80b4f275c45108863e905a3e124f2d4"},"schema_version":"1.0","source":{"id":"2608.05260","kind":"arxiv","version":1}},"canonical_sha256":"e777ce19a2bf47b4c81a8c900b97f750bace5ed71dede2a805d6108bab0b453e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e777ce19a2bf47b4c81a8c900b97f750bace5ed71dede2a805d6108bab0b453e","first_computed_at":"2026-08-07T00:46:37.859325Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-07T00:46:37.859325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8+HHLfn3BmWmLj7cm5u1ABBjO6aK4VjyORH5gUFjUC7iypa8+kAKwjwy5C2wm8IWUMBkwYnL40g/QSkFHRWHCQ==","signature_status":"signed_v1","signed_at":"2026-08-07T00:46:37.860718Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.05260","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8429a27d2431c13cfded9ed5dfbb9ccbb07b4188778665d52047d0d68e4532c","sha256:a6575e692b8eef5817910b38bc19a56fb3c7226872c2eb8e8782d617cb8942ca","sha256:887c8ae11a63b08776668f3fc80cbd99e4e0ba811cd9b52f447d336e7c2b3ce4"],"state_sha256":"7f518d75048eb64bb05a27a0a88d99d973d87420c23cf2313778a32e0772266b"}