{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:3YKOLNB252OK673EYNNHG4OLNE","short_pith_number":"pith:3YKOLNB2","canonical_record":{"source":{"id":"2003.13198","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-03-30T03:13:22Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"67735cbbd1b80a6af92e4b8634740334567dbaa2d06ff6ffb01dba215a41d898","abstract_canon_sha256":"dcf98e5eddfe14dea2cc209c59598c6afea210890943da01d540112eb71cfcec"},"schema_version":"1.0"},"canonical_sha256":"de14e5b43aee9caf7f64c35a7371cb69190c8a53e04f5f0219fdb4b0cf753880","source":{"kind":"arxiv","id":"2003.13198","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.13198","created_at":"2026-07-05T02:34:07Z"},{"alias_kind":"arxiv_version","alias_value":"2003.13198v4","created_at":"2026-07-05T02:34:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.13198","created_at":"2026-07-05T02:34:07Z"},{"alias_kind":"pith_short_12","alias_value":"3YKOLNB252OK","created_at":"2026-07-05T02:34:07Z"},{"alias_kind":"pith_short_16","alias_value":"3YKOLNB252OK673E","created_at":"2026-07-05T02:34:07Z"},{"alias_kind":"pith_short_8","alias_value":"3YKOLNB2","created_at":"2026-07-05T02:34:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:3YKOLNB252OK673EYNNHG4OLNE","target":"record","payload":{"canonical_record":{"source":{"id":"2003.13198","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-03-30T03:13:22Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"67735cbbd1b80a6af92e4b8634740334567dbaa2d06ff6ffb01dba215a41d898","abstract_canon_sha256":"dcf98e5eddfe14dea2cc209c59598c6afea210890943da01d540112eb71cfcec"},"schema_version":"1.0"},"canonical_sha256":"de14e5b43aee9caf7f64c35a7371cb69190c8a53e04f5f0219fdb4b0cf753880","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:34:07.679247Z","signature_b64":"fNkroyTIcbgoFywqRZFdmA1P2HSydDfNgrymyo/zh88BCiMq0/kfBGICzsx1anJXR68HAgvf15eXNZLMWUt9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de14e5b43aee9caf7f64c35a7371cb69190c8a53e04f5f0219fdb4b0cf753880","last_reissued_at":"2026-07-05T02:34:07.678752Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:34:07.678752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.13198","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:34:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vTW6ig93+WIeuI7Nrzgb7ePsQW2IXA5TbtSmt42JcJmm1utOa0LR8Tbovka/AoxsFNBVwzXzhKp7k3llg9DADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:02:50.752440Z"},"content_sha256":"a8f43598f1f46465e358100b65e49321d9abb70fdf9d8bbe60a546b4f5eb806a","schema_version":"1.0","event_id":"sha256:a8f43598f1f46465e358100b65e49321d9abb70fdf9d8bbe60a546b4f5eb806a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:3YKOLNB252OK673EYNNHG4OLNE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"InterBERT: Vision-and-Language Interaction for Multi-modal Pretraining","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"An Yang, Hongxia Yang, Jie Liu, Jingren Zhou, Junyang Lin, Yichang Zhang","submitted_at":"2020-03-30T03:13:22Z","abstract_excerpt":"Multi-modal pretraining for learning high-level multi-modal representation is a further step towards deep learning and artificial intelligence. In this work, we propose a novel model, namely InterBERT (BERT for Interaction), which is the first model of our series of multimodal pretraining methods M6 (MultiModality-to-MultiModality Multitask Mega-transformer). The model owns strong capability of modeling interaction between the information flows of different modalities. The single-stream interaction module is capable of effectively processing information of multiple modalilties, and the two-str"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.13198","kind":"arxiv","version":4},"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/2003.13198/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":"2026-07-05T02:34:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FduO9dJXDtDfcsjDG9hDJrkv7IW8u8/phZ4z9qOtfJsmQYKhGCiNLhMKmGCRzOWIXVP500TYXMHecEyvoaAoCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:02:50.753458Z"},"content_sha256":"840f63daa8a9ce6359545544cb73036ddd8d38afe8af1dcc0b287e19c40cd641","schema_version":"1.0","event_id":"sha256:840f63daa8a9ce6359545544cb73036ddd8d38afe8af1dcc0b287e19c40cd641"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3YKOLNB252OK673EYNNHG4OLNE/bundle.json","state_url":"https://pith.science/pith/3YKOLNB252OK673EYNNHG4OLNE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3YKOLNB252OK673EYNNHG4OLNE/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":"2026-08-17T23:02:50Z","links":{"resolver":"https://pith.science/pith/3YKOLNB252OK673EYNNHG4OLNE","bundle":"https://pith.science/pith/3YKOLNB252OK673EYNNHG4OLNE/bundle.json","state":"https://pith.science/pith/3YKOLNB252OK673EYNNHG4OLNE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3YKOLNB252OK673EYNNHG4OLNE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:3YKOLNB252OK673EYNNHG4OLNE","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":"dcf98e5eddfe14dea2cc209c59598c6afea210890943da01d540112eb71cfcec","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-03-30T03:13:22Z","title_canon_sha256":"67735cbbd1b80a6af92e4b8634740334567dbaa2d06ff6ffb01dba215a41d898"},"schema_version":"1.0","source":{"id":"2003.13198","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.13198","created_at":"2026-07-05T02:34:07Z"},{"alias_kind":"arxiv_version","alias_value":"2003.13198v4","created_at":"2026-07-05T02:34:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.13198","created_at":"2026-07-05T02:34:07Z"},{"alias_kind":"pith_short_12","alias_value":"3YKOLNB252OK","created_at":"2026-07-05T02:34:07Z"},{"alias_kind":"pith_short_16","alias_value":"3YKOLNB252OK673E","created_at":"2026-07-05T02:34:07Z"},{"alias_kind":"pith_short_8","alias_value":"3YKOLNB2","created_at":"2026-07-05T02:34:07Z"}],"graph_snapshots":[{"event_id":"sha256:840f63daa8a9ce6359545544cb73036ddd8d38afe8af1dcc0b287e19c40cd641","target":"graph","created_at":"2026-07-05T02:34:07Z","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/2003.13198/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal pretraining for learning high-level multi-modal representation is a further step towards deep learning and artificial intelligence. In this work, we propose a novel model, namely InterBERT (BERT for Interaction), which is the first model of our series of multimodal pretraining methods M6 (MultiModality-to-MultiModality Multitask Mega-transformer). The model owns strong capability of modeling interaction between the information flows of different modalities. The single-stream interaction module is capable of effectively processing information of multiple modalilties, and the two-str","authors_text":"An Yang, Hongxia Yang, Jie Liu, Jingren Zhou, Junyang Lin, Yichang Zhang","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-03-30T03:13:22Z","title":"InterBERT: Vision-and-Language Interaction for Multi-modal Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.13198","kind":"arxiv","version":4},"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:a8f43598f1f46465e358100b65e49321d9abb70fdf9d8bbe60a546b4f5eb806a","target":"record","created_at":"2026-07-05T02:34:07Z","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":"dcf98e5eddfe14dea2cc209c59598c6afea210890943da01d540112eb71cfcec","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-03-30T03:13:22Z","title_canon_sha256":"67735cbbd1b80a6af92e4b8634740334567dbaa2d06ff6ffb01dba215a41d898"},"schema_version":"1.0","source":{"id":"2003.13198","kind":"arxiv","version":4}},"canonical_sha256":"de14e5b43aee9caf7f64c35a7371cb69190c8a53e04f5f0219fdb4b0cf753880","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de14e5b43aee9caf7f64c35a7371cb69190c8a53e04f5f0219fdb4b0cf753880","first_computed_at":"2026-07-05T02:34:07.678752Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:34:07.678752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fNkroyTIcbgoFywqRZFdmA1P2HSydDfNgrymyo/zh88BCiMq0/kfBGICzsx1anJXR68HAgvf15eXNZLMWUt9Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:34:07.679247Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.13198","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8f43598f1f46465e358100b65e49321d9abb70fdf9d8bbe60a546b4f5eb806a","sha256:840f63daa8a9ce6359545544cb73036ddd8d38afe8af1dcc0b287e19c40cd641"],"state_sha256":"9a0ee16cbf86e697d9e61a104f7b7af78c5ea44fb4d49fb92eac8caa05eb3c72"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DPhSKz/IETubfPfxR6HJJZZgavzCFFZZ32i51dsAPP23QYxDpx0bjV2Gxp66dRzK2j9K5o2LmLxsD64pNvnCCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T23:02:50.758885Z","bundle_sha256":"02aa65cd2becd78c5eda068f7ef96a297b25afd6c4092bb036fbe8499b65c35b"}}