{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YUMTDN4YBJFASKKAIV6P77VROG","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":"f359b03d90b9aa369d54ea73dcc680160a86bef43d004f7970fb1721f63ce9e0","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-09T17:12:20Z","title_canon_sha256":"de62636ff49aa7b2650ea7967908f86cbcda2a6765a66390395be3efadf2c1d7"},"schema_version":"1.0","source":{"id":"2109.04422","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.04422","created_at":"2026-07-05T03:12:58Z"},{"alias_kind":"arxiv_version","alias_value":"2109.04422v1","created_at":"2026-07-05T03:12:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.04422","created_at":"2026-07-05T03:12:58Z"},{"alias_kind":"pith_short_12","alias_value":"YUMTDN4YBJFA","created_at":"2026-07-05T03:12:58Z"},{"alias_kind":"pith_short_16","alias_value":"YUMTDN4YBJFASKKA","created_at":"2026-07-05T03:12:58Z"},{"alias_kind":"pith_short_8","alias_value":"YUMTDN4Y","created_at":"2026-07-05T03:12:58Z"}],"graph_snapshots":[{"event_id":"sha256:b4c7dda981b302838a7b3a80f0959e4c5f4561b9f7bb24ab2d444bc4161a01f0","target":"graph","created_at":"2026-07-05T03:12:58Z","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/2109.04422/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reasoning over multiple modalities, e.g. in Visual Question Answering (VQA), requires an alignment of semantic concepts across domains. Despite the widespread success of end-to-end learning, today's multimodal pipelines by and large leverage pre-extracted, fixed features from object detectors, typically Faster R-CNN, as representations of the visual world. The obvious downside is that the visual representation is not specifically tuned to the multimodal task at hand. At the same time, while transformer-based object detectors have gained popularity, they have not been employed in today's multim","authors_text":"Iryna Gurevych, Jan-Martin O. Steitz, Jonas Pfeiffer, Stefan Roth","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-09T17:12:20Z","title":"TxT: Crossmodal End-to-End Learning with Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.04422","kind":"arxiv","version":1},"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:be01c17ec9f5189af4cdf78eff52ff6d09cba7095e86c3260126081e164ffa1a","target":"record","created_at":"2026-07-05T03:12:58Z","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":"f359b03d90b9aa369d54ea73dcc680160a86bef43d004f7970fb1721f63ce9e0","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-09T17:12:20Z","title_canon_sha256":"de62636ff49aa7b2650ea7967908f86cbcda2a6765a66390395be3efadf2c1d7"},"schema_version":"1.0","source":{"id":"2109.04422","kind":"arxiv","version":1}},"canonical_sha256":"c51931b7980a4a092940457cfffeb17184fd18dd45aec7200c0bd1e6253e5ae5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c51931b7980a4a092940457cfffeb17184fd18dd45aec7200c0bd1e6253e5ae5","first_computed_at":"2026-07-05T03:12:58.319739Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:12:58.319739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F8/uEaZJtLIjG7JYHteZOGxhjjkJP6xjCuErHRUEDJ6rd0SXN2E6PUU2ibAOjUD8pGsmUOEklG9M5anW0AIcAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:12:58.320161Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.04422","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be01c17ec9f5189af4cdf78eff52ff6d09cba7095e86c3260126081e164ffa1a","sha256:b4c7dda981b302838a7b3a80f0959e4c5f4561b9f7bb24ab2d444bc4161a01f0"],"state_sha256":"f3afba0ad50fa7e25322d4581b3bd247ab62dd23c87a8d6ceff51d7b1e9ab878"}