{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DDBUP7C43HAH4TLB6X5ZPQ55I4","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":"d9fa65f387a405e3fdc57e22edc7c8c679fea4a37b56a15a78de35c676fb0d2f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-10T02:16:35Z","title_canon_sha256":"82b21522cb0bbb823a141b6cc8b7f0974f73bf69f5a7e61af0edc718214ecc45"},"schema_version":"1.0","source":{"id":"2303.05657","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.05657","created_at":"2026-07-05T07:57:26Z"},{"alias_kind":"arxiv_version","alias_value":"2303.05657v3","created_at":"2026-07-05T07:57:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.05657","created_at":"2026-07-05T07:57:26Z"},{"alias_kind":"pith_short_12","alias_value":"DDBUP7C43HAH","created_at":"2026-07-05T07:57:26Z"},{"alias_kind":"pith_short_16","alias_value":"DDBUP7C43HAH4TLB","created_at":"2026-07-05T07:57:26Z"},{"alias_kind":"pith_short_8","alias_value":"DDBUP7C4","created_at":"2026-07-05T07:57:26Z"}],"graph_snapshots":[{"event_id":"sha256:959a3844c8df1c778d828b65145cd20aab34674afa033e09828bc818632929b3","target":"graph","created_at":"2026-07-05T07:57:26Z","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/2303.05657/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents Tag2Text, a vision language pre-training (VLP) framework, which introduces image tagging into vision-language models to guide the learning of visual-linguistic features. In contrast to prior works which utilize object tags either manually labeled or automatically detected with an off-the-shelf detector with limited performance, our approach explicitly learns an image tagger using tags parsed from image-paired text and thus provides a strong semantic guidance to vision-language models. In this way, Tag2Text can utilize large-scale annotation-free image tags in accordance wit","authors_text":"Jinyu Ma, Lei Zhang, Rui Feng, Weiwei Tian, Xinyu Huang, Yandong Guo, Yaqian Li, Youcai Zhang, Yuejie Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-10T02:16:35Z","title":"Tag2Text: Guiding Vision-Language Model via Image Tagging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.05657","kind":"arxiv","version":3},"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":"sha256:52ef6ccbdeaaeb9cb074afeceb223dc3047dd7207d359bbef2a9e88dee4412ac","target":"record","created_at":"2026-07-05T07:57:26Z","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":"d9fa65f387a405e3fdc57e22edc7c8c679fea4a37b56a15a78de35c676fb0d2f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-10T02:16:35Z","title_canon_sha256":"82b21522cb0bbb823a141b6cc8b7f0974f73bf69f5a7e61af0edc718214ecc45"},"schema_version":"1.0","source":{"id":"2303.05657","kind":"arxiv","version":3}},"canonical_sha256":"18c347fc5cd9c07e4d61f5fb97c3bd472f12263a57701ea498c19c1cb5f7b67a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18c347fc5cd9c07e4d61f5fb97c3bd472f12263a57701ea498c19c1cb5f7b67a","first_computed_at":"2026-07-05T07:57:26.505426Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:57:26.505426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PHgfFjfPdhAO7iN7ys8czwrSTBAI64RroUi0+VXL/wFtoJqrFhtSZimSum3/gCTzZW+zokGIBFmV+/LIzB8iAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:57:26.505895Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.05657","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52ef6ccbdeaaeb9cb074afeceb223dc3047dd7207d359bbef2a9e88dee4412ac","sha256:959a3844c8df1c778d828b65145cd20aab34674afa033e09828bc818632929b3"],"state_sha256":"80ce219b7d30486a04b644d653b0be115bd8bfb6725321688f02218191c881ee"}