{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:5DUZMD25IINRPZDU5T3QEM5NGB","short_pith_number":"pith:5DUZMD25","canonical_record":{"source":{"id":"2208.09021","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-18T18:51:13Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"6a92d230c23932c6ab741a60f9c329dfa8432ce519754d8107dd39d6e51cbfee","abstract_canon_sha256":"6b4672dcb1f4f32fe67448aed323e634b96b124ee05b546d8ff2b50c7125a428"},"schema_version":"1.0"},"canonical_sha256":"e8e9960f5d421b17e474ecf70233ad305e64c317e12f9a15925b671a44f873ad","source":{"kind":"arxiv","id":"2208.09021","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.09021","created_at":"2026-07-05T05:36:04Z"},{"alias_kind":"arxiv_version","alias_value":"2208.09021v3","created_at":"2026-07-05T05:36:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.09021","created_at":"2026-07-05T05:36:04Z"},{"alias_kind":"pith_short_12","alias_value":"5DUZMD25IINR","created_at":"2026-07-05T05:36:04Z"},{"alias_kind":"pith_short_16","alias_value":"5DUZMD25IINRPZDU","created_at":"2026-07-05T05:36:04Z"},{"alias_kind":"pith_short_8","alias_value":"5DUZMD25","created_at":"2026-07-05T05:36:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:5DUZMD25IINRPZDU5T3QEM5NGB","target":"record","payload":{"canonical_record":{"source":{"id":"2208.09021","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-18T18:51:13Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"6a92d230c23932c6ab741a60f9c329dfa8432ce519754d8107dd39d6e51cbfee","abstract_canon_sha256":"6b4672dcb1f4f32fe67448aed323e634b96b124ee05b546d8ff2b50c7125a428"},"schema_version":"1.0"},"canonical_sha256":"e8e9960f5d421b17e474ecf70233ad305e64c317e12f9a15925b671a44f873ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:04.554277Z","signature_b64":"gEWQOlrPRKESOdYcchSKNK6ADp3/O1wg+sLFq0C1fAWyyFEnOozdKOifzoejHD6jXNNmUoT+mEj4+CVKyV3VDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8e9960f5d421b17e474ecf70233ad305e64c317e12f9a15925b671a44f873ad","last_reissued_at":"2026-07-05T05:36:04.553825Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:04.553825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.09021","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":"2026-07-05T05:36:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tEAiffjVX01gTpIX2SsU9PHP0kVKP3znOQX8rMI0g76AsVQoxbPVgQv8RMw7aBjjGDgh9Y6zmcOrLWy81eRJAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T04:03:24.667010Z"},"content_sha256":"496480a8b73f7e55daea897f00d77d7897a55039f45cc4ebb7edc79c48f3b1ab","schema_version":"1.0","event_id":"sha256:496480a8b73f7e55daea897f00d77d7897a55039f45cc4ebb7edc79c48f3b1ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:5DUZMD25IINRPZDU5T3QEM5NGB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VAuLT: Augmenting the Vision-and-Language Transformer for Sentiment Classification on Social Media","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Georgios Chochlakis, Jesse Thomason, Shrikanth Narayanan (University of Southern California), Tejas Srinivasan","submitted_at":"2022-08-18T18:51:13Z","abstract_excerpt":"We propose the Vision-and-Augmented-Language Transformer (VAuLT). VAuLT is an extension of the popular Vision-and-Language Transformer (ViLT), and improves performance on vision-and-language (VL) tasks that involve more complex text inputs than image captions while having minimal impact on training and inference efficiency. ViLT, importantly, enables efficient training and inference in VL tasks, achieved by encoding images using a linear projection of patches instead of an object detector. However, it is pretrained on captioning datasets, where the language input is simple, literal, and descri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.09021","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/2208.09021/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":"2026-07-05T05:36:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sVcKMGA1Ii4Ebqzv2pKH/lVwrTdiGz4rwRP4pZACXPaEzGtlwzROHop1nhnilsgVkGKVqPt2bDkGxOZBz8wODg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T04:03:24.667383Z"},"content_sha256":"d15332a89b159fa6ac1112034acfbc5ac041aa9bfec1e4fe6c9b52d6fa194bef","schema_version":"1.0","event_id":"sha256:d15332a89b159fa6ac1112034acfbc5ac041aa9bfec1e4fe6c9b52d6fa194bef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5DUZMD25IINRPZDU5T3QEM5NGB/bundle.json","state_url":"https://pith.science/pith/5DUZMD25IINRPZDU5T3QEM5NGB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5DUZMD25IINRPZDU5T3QEM5NGB/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":"2026-08-21T04:03:24Z","links":{"resolver":"https://pith.science/pith/5DUZMD25IINRPZDU5T3QEM5NGB","bundle":"https://pith.science/pith/5DUZMD25IINRPZDU5T3QEM5NGB/bundle.json","state":"https://pith.science/pith/5DUZMD25IINRPZDU5T3QEM5NGB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5DUZMD25IINRPZDU5T3QEM5NGB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:5DUZMD25IINRPZDU5T3QEM5NGB","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":"6b4672dcb1f4f32fe67448aed323e634b96b124ee05b546d8ff2b50c7125a428","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-18T18:51:13Z","title_canon_sha256":"6a92d230c23932c6ab741a60f9c329dfa8432ce519754d8107dd39d6e51cbfee"},"schema_version":"1.0","source":{"id":"2208.09021","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.09021","created_at":"2026-07-05T05:36:04Z"},{"alias_kind":"arxiv_version","alias_value":"2208.09021v3","created_at":"2026-07-05T05:36:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.09021","created_at":"2026-07-05T05:36:04Z"},{"alias_kind":"pith_short_12","alias_value":"5DUZMD25IINR","created_at":"2026-07-05T05:36:04Z"},{"alias_kind":"pith_short_16","alias_value":"5DUZMD25IINRPZDU","created_at":"2026-07-05T05:36:04Z"},{"alias_kind":"pith_short_8","alias_value":"5DUZMD25","created_at":"2026-07-05T05:36:04Z"}],"graph_snapshots":[{"event_id":"sha256:d15332a89b159fa6ac1112034acfbc5ac041aa9bfec1e4fe6c9b52d6fa194bef","target":"graph","created_at":"2026-07-05T05:36:04Z","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/2208.09021/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose the Vision-and-Augmented-Language Transformer (VAuLT). VAuLT is an extension of the popular Vision-and-Language Transformer (ViLT), and improves performance on vision-and-language (VL) tasks that involve more complex text inputs than image captions while having minimal impact on training and inference efficiency. ViLT, importantly, enables efficient training and inference in VL tasks, achieved by encoding images using a linear projection of patches instead of an object detector. However, it is pretrained on captioning datasets, where the language input is simple, literal, and descri","authors_text":"Georgios Chochlakis, Jesse Thomason, Shrikanth Narayanan (University of Southern California), Tejas Srinivasan","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-18T18:51:13Z","title":"VAuLT: Augmenting the Vision-and-Language Transformer for Sentiment Classification on Social Media"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.09021","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":"sha256:496480a8b73f7e55daea897f00d77d7897a55039f45cc4ebb7edc79c48f3b1ab","target":"record","created_at":"2026-07-05T05:36:04Z","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":"6b4672dcb1f4f32fe67448aed323e634b96b124ee05b546d8ff2b50c7125a428","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-18T18:51:13Z","title_canon_sha256":"6a92d230c23932c6ab741a60f9c329dfa8432ce519754d8107dd39d6e51cbfee"},"schema_version":"1.0","source":{"id":"2208.09021","kind":"arxiv","version":3}},"canonical_sha256":"e8e9960f5d421b17e474ecf70233ad305e64c317e12f9a15925b671a44f873ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8e9960f5d421b17e474ecf70233ad305e64c317e12f9a15925b671a44f873ad","first_computed_at":"2026-07-05T05:36:04.553825Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:36:04.553825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gEWQOlrPRKESOdYcchSKNK6ADp3/O1wg+sLFq0C1fAWyyFEnOozdKOifzoejHD6jXNNmUoT+mEj4+CVKyV3VDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:36:04.554277Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.09021","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:496480a8b73f7e55daea897f00d77d7897a55039f45cc4ebb7edc79c48f3b1ab","sha256:d15332a89b159fa6ac1112034acfbc5ac041aa9bfec1e4fe6c9b52d6fa194bef"],"state_sha256":"bcf6b2556d7329cbb361cb2917782be0e8aed8f25fab4de869d0cfa8325a01f8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v62xG3R/ZsG3AlR9RzoA8rC4NUDzoj2VcxRsdJDSsvu6VeG4UCCL+FF0vX3U6MrM1rvzMiEkH7iw9al4xkvJAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T04:03:24.670230Z","bundle_sha256":"4ee9795a7862d56870f2143fe02126ee2f101a79a53e00a6bf6142139c5c6765"}}