{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LQ6ZH4FCLXMHVW7EW6ULCAOIRH","short_pith_number":"pith:LQ6ZH4FC","schema_version":"1.0","canonical_sha256":"5c3d93f0a25dd87adbe4b7a8b101c889ff97fb24eb53178f23951de76aff2707","source":{"kind":"arxiv","id":"2211.06774","version":3},"attestation_state":"computed","paper":{"title":"Large-Scale Bidirectional Training for Zero-Shot Image Captioning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Alessandra Sala, Mark Marsden, Pyunghwan Ahn, Sangyun Kim, Seung Hwan Kim, Sihaeng Lee, Taehoon Kim","submitted_at":"2022-11-13T00:09:36Z","abstract_excerpt":"When trained on large-scale datasets, image captioning models can understand the content of images from a general domain but often fail to generate accurate, detailed captions. To improve performance, pretraining-and-finetuning has been a key strategy for image captioning. However, we find that large-scale bidirectional training between image and text enables zero-shot image captioning. In this paper, we introduce Bidirectional Image Text Training in largER Scale, BITTERS, an efficient training and inference framework for zero-shot image captioning. We also propose a new evaluation benchmark w"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2211.06774","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-13T00:09:36Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6be0af2bc70561379b5ec5fbae493bb5f0f976d12fa3a735f888bc6fc2119619","abstract_canon_sha256":"128acb16a1a1c4ca5796e2c757f95f7f46224ea349b4391476cf4812c41edff4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:50.422750Z","signature_b64":"m122H2kHbbnlYjLVoTZZD8ruMTw68hUbcKIySTmAD3hUIaNt1bSaKeLQReKHRchtLoMY5jzbL65fat8+MkJmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c3d93f0a25dd87adbe4b7a8b101c889ff97fb24eb53178f23951de76aff2707","last_reissued_at":"2026-07-05T06:55:50.422281Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:50.422281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large-Scale Bidirectional Training for Zero-Shot Image Captioning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Alessandra Sala, Mark Marsden, Pyunghwan Ahn, Sangyun Kim, Seung Hwan Kim, Sihaeng Lee, Taehoon Kim","submitted_at":"2022-11-13T00:09:36Z","abstract_excerpt":"When trained on large-scale datasets, image captioning models can understand the content of images from a general domain but often fail to generate accurate, detailed captions. To improve performance, pretraining-and-finetuning has been a key strategy for image captioning. However, we find that large-scale bidirectional training between image and text enables zero-shot image captioning. In this paper, we introduce Bidirectional Image Text Training in largER Scale, BITTERS, an efficient training and inference framework for zero-shot image captioning. We also propose a new evaluation benchmark w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.06774","kind":"arxiv","version":3},"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/2211.06774/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2211.06774","created_at":"2026-07-05T06:55:50.422341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.06774v3","created_at":"2026-07-05T06:55:50.422341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.06774","created_at":"2026-07-05T06:55:50.422341+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQ6ZH4FCLXMH","created_at":"2026-07-05T06:55:50.422341+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQ6ZH4FCLXMHVW7E","created_at":"2026-07-05T06:55:50.422341+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQ6ZH4FC","created_at":"2026-07-05T06:55:50.422341+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LQ6ZH4FCLXMHVW7EW6ULCAOIRH","json":"https://pith.science/pith/LQ6ZH4FCLXMHVW7EW6ULCAOIRH.json","graph_json":"https://pith.science/api/pith-number/LQ6ZH4FCLXMHVW7EW6ULCAOIRH/graph.json","events_json":"https://pith.science/api/pith-number/LQ6ZH4FCLXMHVW7EW6ULCAOIRH/events.json","paper":"https://pith.science/paper/LQ6ZH4FC"},"agent_actions":{"view_html":"https://pith.science/pith/LQ6ZH4FCLXMHVW7EW6ULCAOIRH","download_json":"https://pith.science/pith/LQ6ZH4FCLXMHVW7EW6ULCAOIRH.json","view_paper":"https://pith.science/paper/LQ6ZH4FC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.06774&json=true","fetch_graph":"https://pith.science/api/pith-number/LQ6ZH4FCLXMHVW7EW6ULCAOIRH/graph.json","fetch_events":"https://pith.science/api/pith-number/LQ6ZH4FCLXMHVW7EW6ULCAOIRH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQ6ZH4FCLXMHVW7EW6ULCAOIRH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQ6ZH4FCLXMHVW7EW6ULCAOIRH/action/storage_attestation","attest_author":"https://pith.science/pith/LQ6ZH4FCLXMHVW7EW6ULCAOIRH/action/author_attestation","sign_citation":"https://pith.science/pith/LQ6ZH4FCLXMHVW7EW6ULCAOIRH/action/citation_signature","submit_replication":"https://pith.science/pith/LQ6ZH4FCLXMHVW7EW6ULCAOIRH/action/replication_record"}},"created_at":"2026-07-05T06:55:50.422341+00:00","updated_at":"2026-07-05T06:55:50.422341+00:00"}