{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:P7BGN5J3WWMZD2IIBP5OEKRTNN","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":"1c163a01f207829879bcdabf78403b95d93dae6886d6bc1374d477b35fdea771","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-22T11:48:26Z","title_canon_sha256":"6b4b58bea1964e58613cc694df85f079bd4556d2b72c672d970071bdf26f03b7"},"schema_version":"1.0","source":{"id":"2111.11133","kind":"arxiv","version":11}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.11133","created_at":"2026-07-05T04:12:04Z"},{"alias_kind":"arxiv_version","alias_value":"2111.11133v11","created_at":"2026-07-05T04:12:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.11133","created_at":"2026-07-05T04:12:04Z"},{"alias_kind":"pith_short_12","alias_value":"P7BGN5J3WWMZ","created_at":"2026-07-05T04:12:04Z"},{"alias_kind":"pith_short_16","alias_value":"P7BGN5J3WWMZD2II","created_at":"2026-07-05T04:12:04Z"},{"alias_kind":"pith_short_8","alias_value":"P7BGN5J3","created_at":"2026-07-05T04:12:04Z"}],"graph_snapshots":[{"event_id":"sha256:06b1dc0862d57d880bb560dfc2725131d9c10cf21ee69a99481555d4e586b638","target":"graph","created_at":"2026-07-05T04:12:04Z","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/2111.11133/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Far beyond learning long-range interactions of natural language, transformers are becoming the de-facto standard for many vision tasks with their power and scalability. Especially with cross-modal tasks between image and text, vector quantized variational autoencoders (VQ-VAEs) are widely used to make a raw RGB image into a sequence of feature vectors. To better leverage the correlation between image and text, we propose L-Verse, a novel architecture consisting of feature-augmented variational autoencoder (AugVAE) and bidirectional auto-regressive transformer (BiART) for image-to-text and text","authors_text":"Gwangmo Song, Honglak Lee, Kyunghoon Bae, Sangyun Kim, Seung Hwan Kim, Sihaeng Lee, Soonyoung Lee, Taehoon Kim, Yewon Seo","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-22T11:48:26Z","title":"L-Verse: Bidirectional Generation Between Image and Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.11133","kind":"arxiv","version":11},"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":"sha256:71f8f79bdf97649700c2379ed1db042cfdfe2996335099c9ccb0427f449cb769","target":"record","created_at":"2026-07-05T04:12:04Z","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":"1c163a01f207829879bcdabf78403b95d93dae6886d6bc1374d477b35fdea771","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-22T11:48:26Z","title_canon_sha256":"6b4b58bea1964e58613cc694df85f079bd4556d2b72c672d970071bdf26f03b7"},"schema_version":"1.0","source":{"id":"2111.11133","kind":"arxiv","version":11}},"canonical_sha256":"7fc266f53bb59991e9080bfae22a336b6df091bd755d6ca2157d6a344b4e94f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7fc266f53bb59991e9080bfae22a336b6df091bd755d6ca2157d6a344b4e94f9","first_computed_at":"2026-07-05T04:12:04.262076Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:12:04.262076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wIHx6DSh+5SeYK5ysvKiG+tFt2aJaFFyvAdR/+1NdPJLD6Ig6tpNUW+g5zH7iQvd98Q6qPi7/22tW7yyjMwpAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:12:04.262556Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.11133","source_kind":"arxiv","source_version":11}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71f8f79bdf97649700c2379ed1db042cfdfe2996335099c9ccb0427f449cb769","sha256:06b1dc0862d57d880bb560dfc2725131d9c10cf21ee69a99481555d4e586b638"],"state_sha256":"55ca86b10a4feed1369c2b3637997cc9cfe4d1ac6a434c154a8c6d905ed230e2"}