{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XYHV26NL2U4FM35IFD3FBIQ52J","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":"0620f714eecd5be0c816279499483ff30c1d1f4e84e13a4969d2667c4443d71d","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T03:49:08Z","title_canon_sha256":"90a4b1a946d5a0765b25cf4f54d756421b3b1e46c076c8eccdceba182f6b53cf"},"schema_version":"1.0","source":{"id":"2506.23502","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23502","created_at":"2026-07-05T11:35:57Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23502v2","created_at":"2026-07-05T11:35:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23502","created_at":"2026-07-05T11:35:57Z"},{"alias_kind":"pith_short_12","alias_value":"XYHV26NL2U4F","created_at":"2026-07-05T11:35:57Z"},{"alias_kind":"pith_short_16","alias_value":"XYHV26NL2U4FM35I","created_at":"2026-07-05T11:35:57Z"},{"alias_kind":"pith_short_8","alias_value":"XYHV26NL","created_at":"2026-07-05T11:35:57Z"}],"graph_snapshots":[{"event_id":"sha256:45ca2c554550f59a59c12cfb5423864ea1712a2fd588c9abad3929b7afa6286f","target":"graph","created_at":"2026-07-05T11:35:57Z","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/2506.23502/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Driven by large-scale contrastive vision-language pre-trained models such as CLIP, recent advancements in the image-text matching task have achieved remarkable success in representation learning. Due to image-level visual-language alignment, CLIP falls short in understanding fine-grained details such as object attributes and spatial relationships between objects. Recent efforts have attempted to compel CLIP to acquire structured visual representations by introducing prompt learning to achieve object-level alignment. While achieving promising results, they still lack the capability to perceive ","authors_text":"Mengxiao Tian, Shuo Yang, Xinxiao Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T03:49:08Z","title":"LLM-enhanced Action-aware Multi-modal Prompt Tuning for Image-Text Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23502","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":"sha256:5657bcca494dd89cee65df5da008091abf594effcb8f7939066a122da730af86","target":"record","created_at":"2026-07-05T11:35:57Z","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":"0620f714eecd5be0c816279499483ff30c1d1f4e84e13a4969d2667c4443d71d","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T03:49:08Z","title_canon_sha256":"90a4b1a946d5a0765b25cf4f54d756421b3b1e46c076c8eccdceba182f6b53cf"},"schema_version":"1.0","source":{"id":"2506.23502","kind":"arxiv","version":2}},"canonical_sha256":"be0f5d79abd538566fa828f650a21dd2555702e2b51fc30bd2f21dfee879189e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be0f5d79abd538566fa828f650a21dd2555702e2b51fc30bd2f21dfee879189e","first_computed_at":"2026-07-05T11:35:57.177996Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:57.177996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bOgW5xc32hZuygLcGvPiPBW/00rMTOY58D2rY8acweRuCoCZxA3vaGsKZT3iWYMhrpwm8drKpBR+pVF1cIAqAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:57.178418Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.23502","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5657bcca494dd89cee65df5da008091abf594effcb8f7939066a122da730af86","sha256:45ca2c554550f59a59c12cfb5423864ea1712a2fd588c9abad3929b7afa6286f"],"state_sha256":"f92d2c567f56960d7c92f079213ac90d09c217001b035db9075ee4ac2e7a4064"}