{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:74JBVYMOGBYL56IOZM66DVAOAO","short_pith_number":"pith:74JBVYMO","schema_version":"1.0","canonical_sha256":"ff121ae18e3070bef90ecb3de1d40e0387a1b0815cbe60aa451eb0528f80494c","source":{"kind":"arxiv","id":"2212.12249","version":2},"attestation_state":"computed","paper":{"title":"Do DALL-E and Flamingo Understand Each Other?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hang Li, Jindong Gu, Rajat Koner, Sahand Sharifzadeh, Volker Tresp","submitted_at":"2022-12-23T10:46:56Z","abstract_excerpt":"The field of multimodal research focusing on the comprehension and creation of both images and text has witnessed significant strides. This progress is exemplified by the emergence of sophisticated models dedicated to image captioning at scale, such as the notable Flamingo model and text-to-image generative models, with DALL-E serving as a prominent example. An interesting question worth exploring in this domain is whether Flamingo and DALL-E understand each other. To study this question, we propose a reconstruction task where Flamingo generates a description for a given image and DALL-E uses "},"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":"2212.12249","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-23T10:46:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e9ca5da363f9770e35d61ef3a53207586641078f2392242cee11d2228f7edfcf","abstract_canon_sha256":"d38e0c951cd68f67f881084bebc3aedbe10d0697bdba7713a3aa4bbd59ebf37d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:41.682285Z","signature_b64":"JuV1uINhLUKWk8PrHCGQo8E96B5vN28NxuDtaSyZJAhGvzO4AsNlQa+H5DJedO3iq2uROkKI4TzqTL1+rtqNBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff121ae18e3070bef90ecb3de1d40e0387a1b0815cbe60aa451eb0528f80494c","last_reissued_at":"2026-07-05T06:42:41.681781Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:41.681781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do DALL-E and Flamingo Understand Each Other?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hang Li, Jindong Gu, Rajat Koner, Sahand Sharifzadeh, Volker Tresp","submitted_at":"2022-12-23T10:46:56Z","abstract_excerpt":"The field of multimodal research focusing on the comprehension and creation of both images and text has witnessed significant strides. This progress is exemplified by the emergence of sophisticated models dedicated to image captioning at scale, such as the notable Flamingo model and text-to-image generative models, with DALL-E serving as a prominent example. An interesting question worth exploring in this domain is whether Flamingo and DALL-E understand each other. To study this question, we propose a reconstruction task where Flamingo generates a description for a given image and DALL-E uses "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.12249","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/2212.12249/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":"2212.12249","created_at":"2026-07-05T06:42:41.681848+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.12249v2","created_at":"2026-07-05T06:42:41.681848+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.12249","created_at":"2026-07-05T06:42:41.681848+00:00"},{"alias_kind":"pith_short_12","alias_value":"74JBVYMOGBYL","created_at":"2026-07-05T06:42:41.681848+00:00"},{"alias_kind":"pith_short_16","alias_value":"74JBVYMOGBYL56IO","created_at":"2026-07-05T06:42:41.681848+00:00"},{"alias_kind":"pith_short_8","alias_value":"74JBVYMO","created_at":"2026-07-05T06:42:41.681848+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/74JBVYMOGBYL56IOZM66DVAOAO","json":"https://pith.science/pith/74JBVYMOGBYL56IOZM66DVAOAO.json","graph_json":"https://pith.science/api/pith-number/74JBVYMOGBYL56IOZM66DVAOAO/graph.json","events_json":"https://pith.science/api/pith-number/74JBVYMOGBYL56IOZM66DVAOAO/events.json","paper":"https://pith.science/paper/74JBVYMO"},"agent_actions":{"view_html":"https://pith.science/pith/74JBVYMOGBYL56IOZM66DVAOAO","download_json":"https://pith.science/pith/74JBVYMOGBYL56IOZM66DVAOAO.json","view_paper":"https://pith.science/paper/74JBVYMO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.12249&json=true","fetch_graph":"https://pith.science/api/pith-number/74JBVYMOGBYL56IOZM66DVAOAO/graph.json","fetch_events":"https://pith.science/api/pith-number/74JBVYMOGBYL56IOZM66DVAOAO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/74JBVYMOGBYL56IOZM66DVAOAO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/74JBVYMOGBYL56IOZM66DVAOAO/action/storage_attestation","attest_author":"https://pith.science/pith/74JBVYMOGBYL56IOZM66DVAOAO/action/author_attestation","sign_citation":"https://pith.science/pith/74JBVYMOGBYL56IOZM66DVAOAO/action/citation_signature","submit_replication":"https://pith.science/pith/74JBVYMOGBYL56IOZM66DVAOAO/action/replication_record"}},"created_at":"2026-07-05T06:42:41.681848+00:00","updated_at":"2026-07-05T06:42:41.681848+00:00"}