{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:L4Y455WCCSLZTZKN6TVK6YQYAO","short_pith_number":"pith:L4Y455WC","canonical_record":{"source":{"id":"2205.11686","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-24T00:52:40Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a4f9082ad7cb29d5c9da7103f3174ba669070e4c930d36ee6f99951cd5ed96bd","abstract_canon_sha256":"4787aa41738d84ec6edf5f0afd4d802359adf6f0b47f17bdc42dc03b27eefba7"},"schema_version":"1.0"},"canonical_sha256":"5f31cef6c2149799e54df4eaaf621803b75fef3349ecd683340c377a0dbe56bf","source":{"kind":"arxiv","id":"2205.11686","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11686","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11686v2","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11686","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"pith_short_12","alias_value":"L4Y455WCCSLZ","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"pith_short_16","alias_value":"L4Y455WCCSLZTZKN","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"pith_short_8","alias_value":"L4Y455WC","created_at":"2026-07-05T05:09:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:L4Y455WCCSLZTZKN6TVK6YQYAO","target":"record","payload":{"canonical_record":{"source":{"id":"2205.11686","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-24T00:52:40Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a4f9082ad7cb29d5c9da7103f3174ba669070e4c930d36ee6f99951cd5ed96bd","abstract_canon_sha256":"4787aa41738d84ec6edf5f0afd4d802359adf6f0b47f17bdc42dc03b27eefba7"},"schema_version":"1.0"},"canonical_sha256":"5f31cef6c2149799e54df4eaaf621803b75fef3349ecd683340c377a0dbe56bf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:18.405725Z","signature_b64":"EYn8hdukdggiJqfmoxoDx56apCHEJ1i+gi+6Sseq7Yi3jCpVGjZDRaX19a01byIuRzI+EKVANnfaNePs8h4mDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f31cef6c2149799e54df4eaaf621803b75fef3349ecd683340c377a0dbe56bf","last_reissued_at":"2026-07-05T05:09:18.405294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:18.405294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.11686","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:09:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bdYArLMFPytqO+kNEHr8enm4mqiDy3Rb0JT8SAtaCqySncrcELgZbhmFEQy2raDVamQU7ZEuj0bcxWpKdCh7Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T13:13:11.077045Z"},"content_sha256":"637e5e2198915cff3e587d5dc37f4bf99b2d5925210145cf1f45363ca9f31952","schema_version":"1.0","event_id":"sha256:637e5e2198915cff3e587d5dc37f4bf99b2d5925210145cf1f45363ca9f31952"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:L4Y455WCCSLZTZKN6TVK6YQYAO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Advances in Text Generation from Images Beyond Captioning: A Case Study in Self-Rationalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Akshita Bhagia, Alan W Black, Ana Marasovi\\'c, Florian Metze, Shruti Palaskar, Yonatan Bisk","submitted_at":"2022-05-24T00:52:40Z","abstract_excerpt":"Combining the visual modality with pretrained language models has been surprisingly effective for simple descriptive tasks such as image captioning. More general text generation however remains elusive. We take a step back and ask: How do these models work for more complex generative tasks, i.e. conditioning on both text and images? Are multimodal models simply visually adapted language models, or do they combine they reason jointly over modalities?\n  We investigate these questions in the context of self-rationalization (jointly generating task labels/answers and free-text explanations) of thr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11686","kind":"arxiv","version":2},"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/2205.11686/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":"2026-07-05T05:09:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f2qUqfZvxlTM/kiCNmGJcFN1qRLr35xjj5PCMUnSG81GguFfMOBt8gK9j6HTxur7YEb4bnLsNCYoy49SKZfqBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T13:13:11.077540Z"},"content_sha256":"4403b317e1368b81c144b291a3810bc9fcac84055461be6f43c8281e704d5cd4","schema_version":"1.0","event_id":"sha256:4403b317e1368b81c144b291a3810bc9fcac84055461be6f43c8281e704d5cd4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L4Y455WCCSLZTZKN6TVK6YQYAO/bundle.json","state_url":"https://pith.science/pith/L4Y455WCCSLZTZKN6TVK6YQYAO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L4Y455WCCSLZTZKN6TVK6YQYAO/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":"2026-08-14T13:13:11Z","links":{"resolver":"https://pith.science/pith/L4Y455WCCSLZTZKN6TVK6YQYAO","bundle":"https://pith.science/pith/L4Y455WCCSLZTZKN6TVK6YQYAO/bundle.json","state":"https://pith.science/pith/L4Y455WCCSLZTZKN6TVK6YQYAO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L4Y455WCCSLZTZKN6TVK6YQYAO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:L4Y455WCCSLZTZKN6TVK6YQYAO","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":"4787aa41738d84ec6edf5f0afd4d802359adf6f0b47f17bdc42dc03b27eefba7","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-24T00:52:40Z","title_canon_sha256":"a4f9082ad7cb29d5c9da7103f3174ba669070e4c930d36ee6f99951cd5ed96bd"},"schema_version":"1.0","source":{"id":"2205.11686","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11686","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11686v2","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11686","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"pith_short_12","alias_value":"L4Y455WCCSLZ","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"pith_short_16","alias_value":"L4Y455WCCSLZTZKN","created_at":"2026-07-05T05:09:18Z"},{"alias_kind":"pith_short_8","alias_value":"L4Y455WC","created_at":"2026-07-05T05:09:18Z"}],"graph_snapshots":[{"event_id":"sha256:4403b317e1368b81c144b291a3810bc9fcac84055461be6f43c8281e704d5cd4","target":"graph","created_at":"2026-07-05T05:09:18Z","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/2205.11686/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Combining the visual modality with pretrained language models has been surprisingly effective for simple descriptive tasks such as image captioning. More general text generation however remains elusive. We take a step back and ask: How do these models work for more complex generative tasks, i.e. conditioning on both text and images? Are multimodal models simply visually adapted language models, or do they combine they reason jointly over modalities?\n  We investigate these questions in the context of self-rationalization (jointly generating task labels/answers and free-text explanations) of thr","authors_text":"Akshita Bhagia, Alan W Black, Ana Marasovi\\'c, Florian Metze, Shruti Palaskar, Yonatan Bisk","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-24T00:52:40Z","title":"On Advances in Text Generation from Images Beyond Captioning: A Case Study in Self-Rationalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11686","kind":"arxiv","version":2},"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":"sha256:637e5e2198915cff3e587d5dc37f4bf99b2d5925210145cf1f45363ca9f31952","target":"record","created_at":"2026-07-05T05:09:18Z","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":"4787aa41738d84ec6edf5f0afd4d802359adf6f0b47f17bdc42dc03b27eefba7","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-24T00:52:40Z","title_canon_sha256":"a4f9082ad7cb29d5c9da7103f3174ba669070e4c930d36ee6f99951cd5ed96bd"},"schema_version":"1.0","source":{"id":"2205.11686","kind":"arxiv","version":2}},"canonical_sha256":"5f31cef6c2149799e54df4eaaf621803b75fef3349ecd683340c377a0dbe56bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f31cef6c2149799e54df4eaaf621803b75fef3349ecd683340c377a0dbe56bf","first_computed_at":"2026-07-05T05:09:18.405294Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:09:18.405294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EYn8hdukdggiJqfmoxoDx56apCHEJ1i+gi+6Sseq7Yi3jCpVGjZDRaX19a01byIuRzI+EKVANnfaNePs8h4mDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:09:18.405725Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.11686","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:637e5e2198915cff3e587d5dc37f4bf99b2d5925210145cf1f45363ca9f31952","sha256:4403b317e1368b81c144b291a3810bc9fcac84055461be6f43c8281e704d5cd4"],"state_sha256":"d122f03bbc977fe8ac9de151560c743f14483a24c08ddbe722ec4746ff345338"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fpqz9+orTkFSpr/yCsp6+2AatBOAlCQzJFyBDgVY4erh4NPk3/Xit6uyNV7Wtincf0FP97mPeVwt7tOUkaKhBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T13:13:11.081906Z","bundle_sha256":"d4f93eff7bff5427e5f229cc9e7074917d876337d48ffef833867c4faddeb21d"}}