{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:J4HQU52OFLD6A5PKHJXVSA5SW4","short_pith_number":"pith:J4HQU52O","canonical_record":{"source":{"id":"1908.02265","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-06T17:33:52Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"af884a273c34948e37f1617bcfbe8996de53d5dea8320754c422fba468da915d","abstract_canon_sha256":"cfac8e11e9223823f8ef7da42d350fea7abba01470a3c33c2be2b405c3f8c7a0"},"schema_version":"1.0"},"canonical_sha256":"4f0f0a774e2ac7e075ea3a6f5903b2b7054790568bf1f9d8d2d8fa3681834461","source":{"kind":"arxiv","id":"1908.02265","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.02265","created_at":"2026-07-04T23:51:52Z"},{"alias_kind":"arxiv_version","alias_value":"1908.02265v1","created_at":"2026-07-04T23:51:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.02265","created_at":"2026-07-04T23:51:52Z"},{"alias_kind":"pith_short_12","alias_value":"J4HQU52OFLD6","created_at":"2026-07-04T23:51:52Z"},{"alias_kind":"pith_short_16","alias_value":"J4HQU52OFLD6A5PK","created_at":"2026-07-04T23:51:52Z"},{"alias_kind":"pith_short_8","alias_value":"J4HQU52O","created_at":"2026-07-04T23:51:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:J4HQU52OFLD6A5PKHJXVSA5SW4","target":"record","payload":{"canonical_record":{"source":{"id":"1908.02265","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-06T17:33:52Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"af884a273c34948e37f1617bcfbe8996de53d5dea8320754c422fba468da915d","abstract_canon_sha256":"cfac8e11e9223823f8ef7da42d350fea7abba01470a3c33c2be2b405c3f8c7a0"},"schema_version":"1.0"},"canonical_sha256":"4f0f0a774e2ac7e075ea3a6f5903b2b7054790568bf1f9d8d2d8fa3681834461","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:51:52.576933Z","signature_b64":"Rd6vx8AvS9GQF5dYKpXaD674qUbCkeAw72Q9esrMXB0C0kQejThejfASmQ11EUPdz0CvRb26yk+wYv6pvFCBAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f0f0a774e2ac7e075ea3a6f5903b2b7054790568bf1f9d8d2d8fa3681834461","last_reissued_at":"2026-07-04T23:51:52.576434Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:51:52.576434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.02265","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T23:51:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+VXIAGzI3NKmKE5Vece8nA7cIjGCIa0eIbb2BM7a3WFsST3q86D6/bYA6MPnUFpEm5PTDvpsJJ2OiVvhn+lFAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:22:23.722841Z"},"content_sha256":"d67cfe2d34b63e701dd9093d5970d1f777abe5f9f871244115d4eecf391d6293","schema_version":"1.0","event_id":"sha256:d67cfe2d34b63e701dd9093d5970d1f777abe5f9f871244115d4eecf391d6293"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:J4HQU52OFLD6A5PKHJXVSA5SW4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Devi Parikh, Dhruv Batra, Jiasen Lu, Stefan Lee","submitted_at":"2019-08-06T17:33:52Z","abstract_excerpt":"We present ViLBERT (short for Vision-and-Language BERT), a model for learning task-agnostic joint representations of image content and natural language. We extend the popular BERT architecture to a multi-modal two-stream model, pro-cessing both visual and textual inputs in separate streams that interact through co-attentional transformer layers. We pretrain our model through two proxy tasks on the large, automatically collected Conceptual Captions dataset and then transfer it to multiple established vision-and-language tasks -- visual question answering, visual commonsense reasoning, referring"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.02265","kind":"arxiv","version":1},"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/1908.02265/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":"2026-07-04T23:51:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LiSkZLXceBh4HgL61MIg0z1HM0UVHA/fuLNHWm7Vv+vQeNTwj2VHdsP9xr8rQcw3jTKJBIh1HNT1ObgVJXlqBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:22:23.723347Z"},"content_sha256":"ea0d8ac68b0643ce77b5750c847fb06bf436308712134811e0939acc569ba76b","schema_version":"1.0","event_id":"sha256:ea0d8ac68b0643ce77b5750c847fb06bf436308712134811e0939acc569ba76b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J4HQU52OFLD6A5PKHJXVSA5SW4/bundle.json","state_url":"https://pith.science/pith/J4HQU52OFLD6A5PKHJXVSA5SW4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J4HQU52OFLD6A5PKHJXVSA5SW4/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":"2026-08-06T06:22:23Z","links":{"resolver":"https://pith.science/pith/J4HQU52OFLD6A5PKHJXVSA5SW4","bundle":"https://pith.science/pith/J4HQU52OFLD6A5PKHJXVSA5SW4/bundle.json","state":"https://pith.science/pith/J4HQU52OFLD6A5PKHJXVSA5SW4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J4HQU52OFLD6A5PKHJXVSA5SW4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:J4HQU52OFLD6A5PKHJXVSA5SW4","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":"cfac8e11e9223823f8ef7da42d350fea7abba01470a3c33c2be2b405c3f8c7a0","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-06T17:33:52Z","title_canon_sha256":"af884a273c34948e37f1617bcfbe8996de53d5dea8320754c422fba468da915d"},"schema_version":"1.0","source":{"id":"1908.02265","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.02265","created_at":"2026-07-04T23:51:52Z"},{"alias_kind":"arxiv_version","alias_value":"1908.02265v1","created_at":"2026-07-04T23:51:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.02265","created_at":"2026-07-04T23:51:52Z"},{"alias_kind":"pith_short_12","alias_value":"J4HQU52OFLD6","created_at":"2026-07-04T23:51:52Z"},{"alias_kind":"pith_short_16","alias_value":"J4HQU52OFLD6A5PK","created_at":"2026-07-04T23:51:52Z"},{"alias_kind":"pith_short_8","alias_value":"J4HQU52O","created_at":"2026-07-04T23:51:52Z"}],"graph_snapshots":[{"event_id":"sha256:ea0d8ac68b0643ce77b5750c847fb06bf436308712134811e0939acc569ba76b","target":"graph","created_at":"2026-07-04T23:51:52Z","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/1908.02265/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present ViLBERT (short for Vision-and-Language BERT), a model for learning task-agnostic joint representations of image content and natural language. We extend the popular BERT architecture to a multi-modal two-stream model, pro-cessing both visual and textual inputs in separate streams that interact through co-attentional transformer layers. We pretrain our model through two proxy tasks on the large, automatically collected Conceptual Captions dataset and then transfer it to multiple established vision-and-language tasks -- visual question answering, visual commonsense reasoning, referring","authors_text":"Devi Parikh, Dhruv Batra, Jiasen Lu, Stefan Lee","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-06T17:33:52Z","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.02265","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:d67cfe2d34b63e701dd9093d5970d1f777abe5f9f871244115d4eecf391d6293","target":"record","created_at":"2026-07-04T23:51:52Z","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":"cfac8e11e9223823f8ef7da42d350fea7abba01470a3c33c2be2b405c3f8c7a0","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-06T17:33:52Z","title_canon_sha256":"af884a273c34948e37f1617bcfbe8996de53d5dea8320754c422fba468da915d"},"schema_version":"1.0","source":{"id":"1908.02265","kind":"arxiv","version":1}},"canonical_sha256":"4f0f0a774e2ac7e075ea3a6f5903b2b7054790568bf1f9d8d2d8fa3681834461","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f0f0a774e2ac7e075ea3a6f5903b2b7054790568bf1f9d8d2d8fa3681834461","first_computed_at":"2026-07-04T23:51:52.576434Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:51:52.576434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rd6vx8AvS9GQF5dYKpXaD674qUbCkeAw72Q9esrMXB0C0kQejThejfASmQ11EUPdz0CvRb26yk+wYv6pvFCBAg==","signature_status":"signed_v1","signed_at":"2026-07-04T23:51:52.576933Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.02265","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d67cfe2d34b63e701dd9093d5970d1f777abe5f9f871244115d4eecf391d6293","sha256:ea0d8ac68b0643ce77b5750c847fb06bf436308712134811e0939acc569ba76b"],"state_sha256":"7173d00e98ffa49f29a86b294f27a193fcdf58f0712be0aaa642dbc6b41e9e80"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SGYpk3K0Oft2NZc6V0SKhG+yXhuU2wm8+xmkGLAY2PC4FneZ1keaM1sfcVTaHJtU2LgmBt5l7RErsHe86M5PAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:22:23.727372Z","bundle_sha256":"54b65cf4f262ad7739c71383f2afe623ed3c68dccc47b257a8f645c6cb73bcb4"}}