{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:O4ECJHK7JEVHATIMJNDHDFLAVT","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":"924ef4b48e2ab2047c0549933d0353f765616165744559b326104585908c8963","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-14T11:12:19Z","title_canon_sha256":"0e4d104a060de199633a0aaf45a81526a09af06d7698c5e5587b0c92500529f8"},"schema_version":"1.0","source":{"id":"2211.07275","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.07275","created_at":"2026-07-05T05:15:51Z"},{"alias_kind":"arxiv_version","alias_value":"2211.07275v1","created_at":"2026-07-05T05:15:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.07275","created_at":"2026-07-05T05:15:51Z"},{"alias_kind":"pith_short_12","alias_value":"O4ECJHK7JEVH","created_at":"2026-07-05T05:15:51Z"},{"alias_kind":"pith_short_16","alias_value":"O4ECJHK7JEVHATIM","created_at":"2026-07-05T05:15:51Z"},{"alias_kind":"pith_short_8","alias_value":"O4ECJHK7","created_at":"2026-07-05T05:15:51Z"}],"graph_snapshots":[{"event_id":"sha256:2d7320c53d01f275c8f60822ef3dfe02649b84d3c8801d02a0018fa44734b404","target":"graph","created_at":"2026-07-05T05:15:51Z","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/2211.07275/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"CLIP (Contrastive Language-Image Pre-Training) has shown remarkable zero-shot transfer capabilities in cross-modal correlation tasks such as visual classification and image retrieval. However, its performance in cross-modal generation tasks like zero-shot image captioning remains unsatisfied. In this work, we discuss that directly employing CLIP for zero-shot image captioning relies more on the textual modality in context and largely ignores the visual information, which we call \\emph{contextual language prior}. To address this, we propose Cross-modal Language Models (CLMs) to facilitate unsup","authors_text":"Jitao Sang, Ji Zhang, Junyang Wang, Ming Yan, Yi Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-14T11:12:19Z","title":"Zero-shot Image Captioning by Anchor-augmented Vision-Language Space Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.07275","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":"sha256:877e1a1d747fb17780c5c3cdd431b600904e37692fdee615190d2c6577564a6a","target":"record","created_at":"2026-07-05T05:15:51Z","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":"924ef4b48e2ab2047c0549933d0353f765616165744559b326104585908c8963","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-14T11:12:19Z","title_canon_sha256":"0e4d104a060de199633a0aaf45a81526a09af06d7698c5e5587b0c92500529f8"},"schema_version":"1.0","source":{"id":"2211.07275","kind":"arxiv","version":1}},"canonical_sha256":"7708249d5f492a704d0c4b46719560acdc6cea486ab813883c5b06c3d8688c78","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7708249d5f492a704d0c4b46719560acdc6cea486ab813883c5b06c3d8688c78","first_computed_at":"2026-07-05T05:15:51.690678Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:15:51.690678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ne/nnfW+kh8flzfYL5x7+bNgwSVK+j5I3kNlGzMRYm/BL6qBgVSfeA0AJcfYsyS3b+qkbDw3iIA0goT1u4NiCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:15:51.691068Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.07275","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:877e1a1d747fb17780c5c3cdd431b600904e37692fdee615190d2c6577564a6a","sha256:2d7320c53d01f275c8f60822ef3dfe02649b84d3c8801d02a0018fa44734b404"],"state_sha256":"22e36bc94489dced118bfa27e8f99c1341b8ead665fe63da7d67b4011d842c72"}