{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:LQ6ZH4FCLXMHVW7EW6ULCAOIRH","short_pith_number":"pith:LQ6ZH4FC","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"},"canonical_sha256":"5c3d93f0a25dd87adbe4b7a8b101c889ff97fb24eb53178f23951de76aff2707","source":{"kind":"arxiv","id":"2211.06774","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.06774","created_at":"2026-07-05T06:55:50Z"},{"alias_kind":"arxiv_version","alias_value":"2211.06774v3","created_at":"2026-07-05T06:55:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.06774","created_at":"2026-07-05T06:55:50Z"},{"alias_kind":"pith_short_12","alias_value":"LQ6ZH4FCLXMH","created_at":"2026-07-05T06:55:50Z"},{"alias_kind":"pith_short_16","alias_value":"LQ6ZH4FCLXMHVW7E","created_at":"2026-07-05T06:55:50Z"},{"alias_kind":"pith_short_8","alias_value":"LQ6ZH4FC","created_at":"2026-07-05T06:55:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:LQ6ZH4FCLXMHVW7EW6ULCAOIRH","target":"record","payload":{"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"},"canonical_sha256":"5c3d93f0a25dd87adbe4b7a8b101c889ff97fb24eb53178f23951de76aff2707","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"},"source_kind":"arxiv","source_id":"2211.06774","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:55:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ywz1oZBVfpbxvRWEM+UCDVI+6lSU7ImYNi7jADS+WqWCFE6ajiJY6cLCNm8hyXY7ryBeQIEbTrF4fULwKywKBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T05:34:59.644158Z"},"content_sha256":"8d2bdfbaaa4204e518cfea7d55ae73892ef6471303c498a76480ea293e37457d","schema_version":"1.0","event_id":"sha256:8d2bdfbaaa4204e518cfea7d55ae73892ef6471303c498a76480ea293e37457d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:LQ6ZH4FCLXMHVW7EW6ULCAOIRH","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:55:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a3wUTj+OGLETJ9CVO3ijAdT2aJVJBEoM1HN9+ELCAGap1AYwh9kwNIxHYmyc0iBieO9yG5HxcUqk7igpxiigDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T05:34:59.644739Z"},"content_sha256":"19d5671c47162986451ae6a4c34fbc5c687e5644b8882c6f779301086ee6b606","schema_version":"1.0","event_id":"sha256:19d5671c47162986451ae6a4c34fbc5c687e5644b8882c6f779301086ee6b606"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LQ6ZH4FCLXMHVW7EW6ULCAOIRH/bundle.json","state_url":"https://pith.science/pith/LQ6ZH4FCLXMHVW7EW6ULCAOIRH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LQ6ZH4FCLXMHVW7EW6ULCAOIRH/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":"2026-08-11T05:34:59Z","links":{"resolver":"https://pith.science/pith/LQ6ZH4FCLXMHVW7EW6ULCAOIRH","bundle":"https://pith.science/pith/LQ6ZH4FCLXMHVW7EW6ULCAOIRH/bundle.json","state":"https://pith.science/pith/LQ6ZH4FCLXMHVW7EW6ULCAOIRH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LQ6ZH4FCLXMHVW7EW6ULCAOIRH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LQ6ZH4FCLXMHVW7EW6ULCAOIRH","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":"128acb16a1a1c4ca5796e2c757f95f7f46224ea349b4391476cf4812c41edff4","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-13T00:09:36Z","title_canon_sha256":"6be0af2bc70561379b5ec5fbae493bb5f0f976d12fa3a735f888bc6fc2119619"},"schema_version":"1.0","source":{"id":"2211.06774","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.06774","created_at":"2026-07-05T06:55:50Z"},{"alias_kind":"arxiv_version","alias_value":"2211.06774v3","created_at":"2026-07-05T06:55:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.06774","created_at":"2026-07-05T06:55:50Z"},{"alias_kind":"pith_short_12","alias_value":"LQ6ZH4FCLXMH","created_at":"2026-07-05T06:55:50Z"},{"alias_kind":"pith_short_16","alias_value":"LQ6ZH4FCLXMHVW7E","created_at":"2026-07-05T06:55:50Z"},{"alias_kind":"pith_short_8","alias_value":"LQ6ZH4FC","created_at":"2026-07-05T06:55:50Z"}],"graph_snapshots":[{"event_id":"sha256:19d5671c47162986451ae6a4c34fbc5c687e5644b8882c6f779301086ee6b606","target":"graph","created_at":"2026-07-05T06:55:50Z","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/2211.06774/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alessandra Sala, Mark Marsden, Pyunghwan Ahn, Sangyun Kim, Seung Hwan Kim, Sihaeng Lee, Taehoon Kim","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-13T00:09:36Z","title":"Large-Scale Bidirectional Training for Zero-Shot Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.06774","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":"sha256:8d2bdfbaaa4204e518cfea7d55ae73892ef6471303c498a76480ea293e37457d","target":"record","created_at":"2026-07-05T06:55:50Z","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":"128acb16a1a1c4ca5796e2c757f95f7f46224ea349b4391476cf4812c41edff4","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-13T00:09:36Z","title_canon_sha256":"6be0af2bc70561379b5ec5fbae493bb5f0f976d12fa3a735f888bc6fc2119619"},"schema_version":"1.0","source":{"id":"2211.06774","kind":"arxiv","version":3}},"canonical_sha256":"5c3d93f0a25dd87adbe4b7a8b101c889ff97fb24eb53178f23951de76aff2707","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c3d93f0a25dd87adbe4b7a8b101c889ff97fb24eb53178f23951de76aff2707","first_computed_at":"2026-07-05T06:55:50.422281Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:55:50.422281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m122H2kHbbnlYjLVoTZZD8ruMTw68hUbcKIySTmAD3hUIaNt1bSaKeLQReKHRchtLoMY5jzbL65fat8+MkJmCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:55:50.422750Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.06774","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d2bdfbaaa4204e518cfea7d55ae73892ef6471303c498a76480ea293e37457d","sha256:19d5671c47162986451ae6a4c34fbc5c687e5644b8882c6f779301086ee6b606"],"state_sha256":"b5b1378fd1a317055012ec28e7c9d30cdb3eb17955b5b80d8983d3baa3a216d5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aLM3IMLWqbGVIwSne+vTk2vwe7iFPAgQjGx49IKOOeA5vrFwv/8T7gaUxXwh0ixThRTMzUlx5qxn5Ed+4CGbDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T05:34:59.648486Z","bundle_sha256":"cca0f581ff176e49fe4dc8a5775dd8575e090f9779879df59d0dec63830dea46"}}