{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:UVDJSFZFXASA7ZGJVVJ4JIBYPB","short_pith_number":"pith:UVDJSFZF","canonical_record":{"source":{"id":"2202.06574","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-02-14T09:36:50Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a57e52b222c0e21caa03ce4cddaf84c0c51fce7b40acd7306e7d89ea28de3d02","abstract_canon_sha256":"9260d021dc5d99f009b34b27898a912d14c2d0a6452520c55125c740c4926f05"},"schema_version":"1.0"},"canonical_sha256":"a546991725b8240fe4c9ad53c4a038785d114a7d79d3ce343317985c6fa0b6e1","source":{"kind":"arxiv","id":"2202.06574","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.06574","created_at":"2026-07-05T05:50:04Z"},{"alias_kind":"arxiv_version","alias_value":"2202.06574v3","created_at":"2026-07-05T05:50:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.06574","created_at":"2026-07-05T05:50:04Z"},{"alias_kind":"pith_short_12","alias_value":"UVDJSFZFXASA","created_at":"2026-07-05T05:50:04Z"},{"alias_kind":"pith_short_16","alias_value":"UVDJSFZFXASA7ZGJ","created_at":"2026-07-05T05:50:04Z"},{"alias_kind":"pith_short_8","alias_value":"UVDJSFZF","created_at":"2026-07-05T05:50:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:UVDJSFZFXASA7ZGJVVJ4JIBYPB","target":"record","payload":{"canonical_record":{"source":{"id":"2202.06574","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-02-14T09:36:50Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a57e52b222c0e21caa03ce4cddaf84c0c51fce7b40acd7306e7d89ea28de3d02","abstract_canon_sha256":"9260d021dc5d99f009b34b27898a912d14c2d0a6452520c55125c740c4926f05"},"schema_version":"1.0"},"canonical_sha256":"a546991725b8240fe4c9ad53c4a038785d114a7d79d3ce343317985c6fa0b6e1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:50:04.824065Z","signature_b64":"n7NkwX43M3BNHRJramh3DyT9y5PPaN+pnVJa7y14c3ygSHyThPhDHtDtmzn9jxunJua0UN9xtLFvGhBUSR8uAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a546991725b8240fe4c9ad53c4a038785d114a7d79d3ce343317985c6fa0b6e1","last_reissued_at":"2026-07-05T05:50:04.823737Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:50:04.823737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.06574","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":"2026-07-05T05:50:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xBsPe7klDJI4fl87ALxZB7F+ehbPdsYwAQ0MxE4zW6Aw9GzEPTNrzWv8cOh5rUoEPiJlInX+A88+q9E52JFoBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T11:10:20.142785Z"},"content_sha256":"6e46232ea524e8ad9fefe14f22cf0ae2cedc91cf1fe528cc22fe984f8db61763","schema_version":"1.0","event_id":"sha256:6e46232ea524e8ad9fefe14f22cf0ae2cedc91cf1fe528cc22fe984f8db61763"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:UVDJSFZFXASA7ZGJVVJ4JIBYPB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"I-Tuning: Tuning Frozen Language Models with Image for Lightweight Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Jing Ma, Rongsheng Zhang, Yadong Xi, Zhipeng Hu, Ziyang Luo","submitted_at":"2022-02-14T09:36:50Z","abstract_excerpt":"Image Captioning is a traditional vision-and-language task that aims to generate the language description of an image. Recent studies focus on scaling up the model size and the number of training data, which significantly increase the cost of model training. Different to these heavy-cost models, we introduce a lightweight image captioning framework (I-Tuning), which contains a small number of trainable parameters. We design a novel I-Tuning cross-attention module to connect the non-trainable pre-trained language decoder GPT2 and vision encoder CLIP-ViT. Since most parameters are not required t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.06574","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/2202.06574/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":"2026-07-05T05:50:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XbcADjS9RrQfb3w5s78b8wewYv8YEqvO90H57MACy6NDgO0AA4Oj0amiUKxnb4MNhHmjXxJQV+lWo3iPeT4qAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T11:10:20.143148Z"},"content_sha256":"ef721b5a283c44f02cc188b7c7b803cfc842e421942f3cb0c4435e6e86f2b43e","schema_version":"1.0","event_id":"sha256:ef721b5a283c44f02cc188b7c7b803cfc842e421942f3cb0c4435e6e86f2b43e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UVDJSFZFXASA7ZGJVVJ4JIBYPB/bundle.json","state_url":"https://pith.science/pith/UVDJSFZFXASA7ZGJVVJ4JIBYPB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UVDJSFZFXASA7ZGJVVJ4JIBYPB/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":"2026-07-06T11:10:20Z","links":{"resolver":"https://pith.science/pith/UVDJSFZFXASA7ZGJVVJ4JIBYPB","bundle":"https://pith.science/pith/UVDJSFZFXASA7ZGJVVJ4JIBYPB/bundle.json","state":"https://pith.science/pith/UVDJSFZFXASA7ZGJVVJ4JIBYPB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UVDJSFZFXASA7ZGJVVJ4JIBYPB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UVDJSFZFXASA7ZGJVVJ4JIBYPB","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":"9260d021dc5d99f009b34b27898a912d14c2d0a6452520c55125c740c4926f05","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-02-14T09:36:50Z","title_canon_sha256":"a57e52b222c0e21caa03ce4cddaf84c0c51fce7b40acd7306e7d89ea28de3d02"},"schema_version":"1.0","source":{"id":"2202.06574","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.06574","created_at":"2026-07-05T05:50:04Z"},{"alias_kind":"arxiv_version","alias_value":"2202.06574v3","created_at":"2026-07-05T05:50:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.06574","created_at":"2026-07-05T05:50:04Z"},{"alias_kind":"pith_short_12","alias_value":"UVDJSFZFXASA","created_at":"2026-07-05T05:50:04Z"},{"alias_kind":"pith_short_16","alias_value":"UVDJSFZFXASA7ZGJ","created_at":"2026-07-05T05:50:04Z"},{"alias_kind":"pith_short_8","alias_value":"UVDJSFZF","created_at":"2026-07-05T05:50:04Z"}],"graph_snapshots":[{"event_id":"sha256:ef721b5a283c44f02cc188b7c7b803cfc842e421942f3cb0c4435e6e86f2b43e","target":"graph","created_at":"2026-07-05T05:50:04Z","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/2202.06574/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image Captioning is a traditional vision-and-language task that aims to generate the language description of an image. Recent studies focus on scaling up the model size and the number of training data, which significantly increase the cost of model training. Different to these heavy-cost models, we introduce a lightweight image captioning framework (I-Tuning), which contains a small number of trainable parameters. We design a novel I-Tuning cross-attention module to connect the non-trainable pre-trained language decoder GPT2 and vision encoder CLIP-ViT. Since most parameters are not required t","authors_text":"Jing Ma, Rongsheng Zhang, Yadong Xi, Zhipeng Hu, Ziyang Luo","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-02-14T09:36:50Z","title":"I-Tuning: Tuning Frozen Language Models with Image for Lightweight Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.06574","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":"sha256:6e46232ea524e8ad9fefe14f22cf0ae2cedc91cf1fe528cc22fe984f8db61763","target":"record","created_at":"2026-07-05T05:50:04Z","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":"9260d021dc5d99f009b34b27898a912d14c2d0a6452520c55125c740c4926f05","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-02-14T09:36:50Z","title_canon_sha256":"a57e52b222c0e21caa03ce4cddaf84c0c51fce7b40acd7306e7d89ea28de3d02"},"schema_version":"1.0","source":{"id":"2202.06574","kind":"arxiv","version":3}},"canonical_sha256":"a546991725b8240fe4c9ad53c4a038785d114a7d79d3ce343317985c6fa0b6e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a546991725b8240fe4c9ad53c4a038785d114a7d79d3ce343317985c6fa0b6e1","first_computed_at":"2026-07-05T05:50:04.823737Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:50:04.823737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n7NkwX43M3BNHRJramh3DyT9y5PPaN+pnVJa7y14c3ygSHyThPhDHtDtmzn9jxunJua0UN9xtLFvGhBUSR8uAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:50:04.824065Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.06574","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e46232ea524e8ad9fefe14f22cf0ae2cedc91cf1fe528cc22fe984f8db61763","sha256:ef721b5a283c44f02cc188b7c7b803cfc842e421942f3cb0c4435e6e86f2b43e"],"state_sha256":"5c2081c0f94b483480e51f50c23554a863089c6e2cfd35e4584056096451e906"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p+g5MjXShr6M89M6PnlmjrWZVlYw8hN8urg9QueAW9OD+8rxQm1gIyfyeuDw0jUrlvcWgKZ3CBB1LwEqz2DrCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T11:10:20.145042Z","bundle_sha256":"afceb763fae30b3aca5fdec3bff0a32a22013953efc568abde1bd13a893c310d"}}