{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZYWWR3BYYIWN4GTRXHQO27BE34","short_pith_number":"pith:ZYWWR3BY","canonical_record":{"source":{"id":"2307.16525","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-31T09:47:06Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"26a7def8a77e57736e41d0a4b3111a6060ec9f29ff0eb5f1bc7dfbf7993b82e9","abstract_canon_sha256":"2125b3ca94bde276b60b90052f59b0b5eee07b471dcb9e3010905ee9df37ffd9"},"schema_version":"1.0"},"canonical_sha256":"ce2d68ec38c22cde1a71b9e0ed7c24df3211086fba51087a36c510ccbf583883","source":{"kind":"arxiv","id":"2307.16525","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.16525","created_at":"2026-07-05T06:36:04Z"},{"alias_kind":"arxiv_version","alias_value":"2307.16525v1","created_at":"2026-07-05T06:36:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.16525","created_at":"2026-07-05T06:36:04Z"},{"alias_kind":"pith_short_12","alias_value":"ZYWWR3BYYIWN","created_at":"2026-07-05T06:36:04Z"},{"alias_kind":"pith_short_16","alias_value":"ZYWWR3BYYIWN4GTR","created_at":"2026-07-05T06:36:04Z"},{"alias_kind":"pith_short_8","alias_value":"ZYWWR3BY","created_at":"2026-07-05T06:36:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZYWWR3BYYIWN4GTRXHQO27BE34","target":"record","payload":{"canonical_record":{"source":{"id":"2307.16525","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-31T09:47:06Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"26a7def8a77e57736e41d0a4b3111a6060ec9f29ff0eb5f1bc7dfbf7993b82e9","abstract_canon_sha256":"2125b3ca94bde276b60b90052f59b0b5eee07b471dcb9e3010905ee9df37ffd9"},"schema_version":"1.0"},"canonical_sha256":"ce2d68ec38c22cde1a71b9e0ed7c24df3211086fba51087a36c510ccbf583883","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:36:04.720270Z","signature_b64":"YCS3N6GjpcoC9gdnJ+TChocR4GkwXmjUGd83KOGQC9PK79u+Es6WPWIRQ0zewrl2yP4JTTQ9VGF5NAbqwWzrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce2d68ec38c22cde1a71b9e0ed7c24df3211086fba51087a36c510ccbf583883","last_reissued_at":"2026-07-05T06:36:04.719854Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:36:04.719854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.16525","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:36:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XmY+lDUwUvh4FxXRI7/iyuGPRJiu98JQUV7KJQJ3qWutQ/HAX7scIHwhCx2t6sWjyyyl25hUzES2I7aN6xgnDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T03:17:29.534576Z"},"content_sha256":"d661d642baa23bfbc71a953e44d591e9cb72050995c46ade23eb0676c33f0938","schema_version":"1.0","event_id":"sha256:d661d642baa23bfbc71a953e44d591e9cb72050995c46ade23eb0676c33f0938"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZYWWR3BYYIWN4GTRXHQO27BE34","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transferable Decoding with Visual Entities for Zero-Shot Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chengjie Wang, Feng Zheng, Jinrui Zhang, Junjie Fei, Teng Wang, Zhenyu He","submitted_at":"2023-07-31T09:47:06Z","abstract_excerpt":"Image-to-text generation aims to describe images using natural language. Recently, zero-shot image captioning based on pre-trained vision-language models (VLMs) and large language models (LLMs) has made significant progress. However, we have observed and empirically demonstrated that these methods are susceptible to modality bias induced by LLMs and tend to generate descriptions containing objects (entities) that do not actually exist in the image but frequently appear during training (i.e., object hallucination). In this paper, we propose ViECap, a transferable decoding model that leverages e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.16525","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2307.16525/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:36:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZiYF8Me97daI+7L9owEbjfMTh9cvB5wdGQHRByuTMO2UQwaf5TO9PElyC9llgjm4XGgJq3R+HfpZtWHMdN9GAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T03:17:29.535090Z"},"content_sha256":"3a971183c327ffd3065434713aa045b3a3cb27594ec1cec47367329211a9733a","schema_version":"1.0","event_id":"sha256:3a971183c327ffd3065434713aa045b3a3cb27594ec1cec47367329211a9733a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZYWWR3BYYIWN4GTRXHQO27BE34/bundle.json","state_url":"https://pith.science/pith/ZYWWR3BYYIWN4GTRXHQO27BE34/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZYWWR3BYYIWN4GTRXHQO27BE34/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-13T03:17:29Z","links":{"resolver":"https://pith.science/pith/ZYWWR3BYYIWN4GTRXHQO27BE34","bundle":"https://pith.science/pith/ZYWWR3BYYIWN4GTRXHQO27BE34/bundle.json","state":"https://pith.science/pith/ZYWWR3BYYIWN4GTRXHQO27BE34/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZYWWR3BYYIWN4GTRXHQO27BE34/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZYWWR3BYYIWN4GTRXHQO27BE34","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":"2125b3ca94bde276b60b90052f59b0b5eee07b471dcb9e3010905ee9df37ffd9","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-31T09:47:06Z","title_canon_sha256":"26a7def8a77e57736e41d0a4b3111a6060ec9f29ff0eb5f1bc7dfbf7993b82e9"},"schema_version":"1.0","source":{"id":"2307.16525","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.16525","created_at":"2026-07-05T06:36:04Z"},{"alias_kind":"arxiv_version","alias_value":"2307.16525v1","created_at":"2026-07-05T06:36:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.16525","created_at":"2026-07-05T06:36:04Z"},{"alias_kind":"pith_short_12","alias_value":"ZYWWR3BYYIWN","created_at":"2026-07-05T06:36:04Z"},{"alias_kind":"pith_short_16","alias_value":"ZYWWR3BYYIWN4GTR","created_at":"2026-07-05T06:36:04Z"},{"alias_kind":"pith_short_8","alias_value":"ZYWWR3BY","created_at":"2026-07-05T06:36:04Z"}],"graph_snapshots":[{"event_id":"sha256:3a971183c327ffd3065434713aa045b3a3cb27594ec1cec47367329211a9733a","target":"graph","created_at":"2026-07-05T06:36:04Z","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/2307.16525/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image-to-text generation aims to describe images using natural language. Recently, zero-shot image captioning based on pre-trained vision-language models (VLMs) and large language models (LLMs) has made significant progress. However, we have observed and empirically demonstrated that these methods are susceptible to modality bias induced by LLMs and tend to generate descriptions containing objects (entities) that do not actually exist in the image but frequently appear during training (i.e., object hallucination). In this paper, we propose ViECap, a transferable decoding model that leverages e","authors_text":"Chengjie Wang, Feng Zheng, Jinrui Zhang, Junjie Fei, Teng Wang, Zhenyu He","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-31T09:47:06Z","title":"Transferable Decoding with Visual Entities for Zero-Shot Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.16525","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:d661d642baa23bfbc71a953e44d591e9cb72050995c46ade23eb0676c33f0938","target":"record","created_at":"2026-07-05T06:36:04Z","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":"2125b3ca94bde276b60b90052f59b0b5eee07b471dcb9e3010905ee9df37ffd9","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-31T09:47:06Z","title_canon_sha256":"26a7def8a77e57736e41d0a4b3111a6060ec9f29ff0eb5f1bc7dfbf7993b82e9"},"schema_version":"1.0","source":{"id":"2307.16525","kind":"arxiv","version":1}},"canonical_sha256":"ce2d68ec38c22cde1a71b9e0ed7c24df3211086fba51087a36c510ccbf583883","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce2d68ec38c22cde1a71b9e0ed7c24df3211086fba51087a36c510ccbf583883","first_computed_at":"2026-07-05T06:36:04.719854Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:36:04.719854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YCS3N6GjpcoC9gdnJ+TChocR4GkwXmjUGd83KOGQC9PK79u+Es6WPWIRQ0zewrl2yP4JTTQ9VGF5NAbqwWzrCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:36:04.720270Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.16525","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d661d642baa23bfbc71a953e44d591e9cb72050995c46ade23eb0676c33f0938","sha256:3a971183c327ffd3065434713aa045b3a3cb27594ec1cec47367329211a9733a"],"state_sha256":"6208cfa6184f53c64c29e12ab7d8a380e87cb86c949150d7b6ae09f07a569b9b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UCzxQ0878AlMpchw8o6sTwGp6aEINENLpYfJVkZ8be1s23o/hR4SkY4g9ojpzqJbzRuG0DyNKtHvKaHgZ4DNAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T03:17:29.540514Z","bundle_sha256":"5319acdf7d096b3842f876277658a41c4c4b711012c89ebff39310d24e115482"}}