{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:TMVQOUXJKXDM56Q5KHLBGM3S2A","short_pith_number":"pith:TMVQOUXJ","canonical_record":{"source":{"id":"2206.07160","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-14T20:43:25Z","cross_cats_sorted":[],"title_canon_sha256":"aae7c82716a64a639cbf6be062aede09f8ad962d8b791aad981da4fb1c0bcc20","abstract_canon_sha256":"d512af4a784b16d6c469c493373e0d9e2f29f2f4fb3be69adbfa892917d1b38a"},"schema_version":"1.0"},"canonical_sha256":"9b2b0752e955c6cefa1d51d6133372d00a2ad658bf7413ab9cff5c69b6239058","source":{"kind":"arxiv","id":"2206.07160","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.07160","created_at":"2026-07-05T04:31:50Z"},{"alias_kind":"arxiv_version","alias_value":"2206.07160v1","created_at":"2026-07-05T04:31:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07160","created_at":"2026-07-05T04:31:50Z"},{"alias_kind":"pith_short_12","alias_value":"TMVQOUXJKXDM","created_at":"2026-07-05T04:31:50Z"},{"alias_kind":"pith_short_16","alias_value":"TMVQOUXJKXDM56Q5","created_at":"2026-07-05T04:31:50Z"},{"alias_kind":"pith_short_8","alias_value":"TMVQOUXJ","created_at":"2026-07-05T04:31:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:TMVQOUXJKXDM56Q5KHLBGM3S2A","target":"record","payload":{"canonical_record":{"source":{"id":"2206.07160","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-14T20:43:25Z","cross_cats_sorted":[],"title_canon_sha256":"aae7c82716a64a639cbf6be062aede09f8ad962d8b791aad981da4fb1c0bcc20","abstract_canon_sha256":"d512af4a784b16d6c469c493373e0d9e2f29f2f4fb3be69adbfa892917d1b38a"},"schema_version":"1.0"},"canonical_sha256":"9b2b0752e955c6cefa1d51d6133372d00a2ad658bf7413ab9cff5c69b6239058","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:31:50.510110Z","signature_b64":"42VHUf8LhEROTKW/gPlqAmnEZhUT62/bJQqdfXPIJk24yc1e86kquly3yAPKCz2RQT+o+153ishFb+13sw9pCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b2b0752e955c6cefa1d51d6133372d00a2ad658bf7413ab9cff5c69b6239058","last_reissued_at":"2026-07-05T04:31:50.509711Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:31:50.509711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.07160","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":"2026-07-05T04:31:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+L0SjTolrlh1A36vzPd8WiCKGI0RNx9YFHEj1kHBYp6fLQlZrcLSXy1eM9yEHKLqiDjck1kOszXCeQyDAXsbBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T14:31:03.381052Z"},"content_sha256":"334fdf5b3e2d65c6898927d62767ad64e63f9c28af23de769bf6f0c618a04efd","schema_version":"1.0","event_id":"sha256:334fdf5b3e2d65c6898927d62767ad64e63f9c28af23de769bf6f0c618a04efd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:TMVQOUXJKXDM56Q5KHLBGM3S2A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ce Liu, Chung-Ching Lin, Kevin Lin, Lijuan Wang, Linjie Li, Zhe Gan, Zicheng Liu","submitted_at":"2022-06-14T20:43:25Z","abstract_excerpt":"Unified vision-language frameworks have greatly advanced in recent years, most of which adopt an encoder-decoder architecture to unify image-text tasks as sequence-to-sequence generation. However, existing video-language (VidL) models still require task-specific designs in model architecture and training objectives for each task. In this work, we explore a unified VidL framework LAVENDER, where Masked Language Modeling (MLM) is used as the common interface for all pre-training and downstream tasks. Such unification leads to a simplified model architecture, where only a lightweight MLM head, in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07160","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/2206.07160/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":"2026-07-05T04:31:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fP6SJ5Vy4BsJGbEyC2EfKXvskctzcGDLOhCNCmLPVGMM2RorZqqcWciuVOIPWFiTy+e++egOSUjAG/ofhyVZBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T14:31:03.381571Z"},"content_sha256":"c272d43123bccc2378a0ff3ee34f4e1f29585c427b3b443315c61b1b3e2fb454","schema_version":"1.0","event_id":"sha256:c272d43123bccc2378a0ff3ee34f4e1f29585c427b3b443315c61b1b3e2fb454"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TMVQOUXJKXDM56Q5KHLBGM3S2A/bundle.json","state_url":"https://pith.science/pith/TMVQOUXJKXDM56Q5KHLBGM3S2A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TMVQOUXJKXDM56Q5KHLBGM3S2A/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":"2026-08-11T14:31:03Z","links":{"resolver":"https://pith.science/pith/TMVQOUXJKXDM56Q5KHLBGM3S2A","bundle":"https://pith.science/pith/TMVQOUXJKXDM56Q5KHLBGM3S2A/bundle.json","state":"https://pith.science/pith/TMVQOUXJKXDM56Q5KHLBGM3S2A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TMVQOUXJKXDM56Q5KHLBGM3S2A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TMVQOUXJKXDM56Q5KHLBGM3S2A","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":"d512af4a784b16d6c469c493373e0d9e2f29f2f4fb3be69adbfa892917d1b38a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-14T20:43:25Z","title_canon_sha256":"aae7c82716a64a639cbf6be062aede09f8ad962d8b791aad981da4fb1c0bcc20"},"schema_version":"1.0","source":{"id":"2206.07160","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.07160","created_at":"2026-07-05T04:31:50Z"},{"alias_kind":"arxiv_version","alias_value":"2206.07160v1","created_at":"2026-07-05T04:31:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07160","created_at":"2026-07-05T04:31:50Z"},{"alias_kind":"pith_short_12","alias_value":"TMVQOUXJKXDM","created_at":"2026-07-05T04:31:50Z"},{"alias_kind":"pith_short_16","alias_value":"TMVQOUXJKXDM56Q5","created_at":"2026-07-05T04:31:50Z"},{"alias_kind":"pith_short_8","alias_value":"TMVQOUXJ","created_at":"2026-07-05T04:31:50Z"}],"graph_snapshots":[{"event_id":"sha256:c272d43123bccc2378a0ff3ee34f4e1f29585c427b3b443315c61b1b3e2fb454","target":"graph","created_at":"2026-07-05T04:31:50Z","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/2206.07160/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unified vision-language frameworks have greatly advanced in recent years, most of which adopt an encoder-decoder architecture to unify image-text tasks as sequence-to-sequence generation. However, existing video-language (VidL) models still require task-specific designs in model architecture and training objectives for each task. In this work, we explore a unified VidL framework LAVENDER, where Masked Language Modeling (MLM) is used as the common interface for all pre-training and downstream tasks. Such unification leads to a simplified model architecture, where only a lightweight MLM head, in","authors_text":"Ce Liu, Chung-Ching Lin, Kevin Lin, Lijuan Wang, Linjie Li, Zhe Gan, Zicheng Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-14T20:43:25Z","title":"LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07160","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":"sha256:334fdf5b3e2d65c6898927d62767ad64e63f9c28af23de769bf6f0c618a04efd","target":"record","created_at":"2026-07-05T04:31:50Z","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":"d512af4a784b16d6c469c493373e0d9e2f29f2f4fb3be69adbfa892917d1b38a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-14T20:43:25Z","title_canon_sha256":"aae7c82716a64a639cbf6be062aede09f8ad962d8b791aad981da4fb1c0bcc20"},"schema_version":"1.0","source":{"id":"2206.07160","kind":"arxiv","version":1}},"canonical_sha256":"9b2b0752e955c6cefa1d51d6133372d00a2ad658bf7413ab9cff5c69b6239058","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b2b0752e955c6cefa1d51d6133372d00a2ad658bf7413ab9cff5c69b6239058","first_computed_at":"2026-07-05T04:31:50.509711Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:31:50.509711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"42VHUf8LhEROTKW/gPlqAmnEZhUT62/bJQqdfXPIJk24yc1e86kquly3yAPKCz2RQT+o+153ishFb+13sw9pCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:31:50.510110Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.07160","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:334fdf5b3e2d65c6898927d62767ad64e63f9c28af23de769bf6f0c618a04efd","sha256:c272d43123bccc2378a0ff3ee34f4e1f29585c427b3b443315c61b1b3e2fb454"],"state_sha256":"95e90238db26451fd51557dee6856acae4d6cf97efb5e055e86c8c15f1701b28"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9uk12E3FdwtRuQp8sJX03eIKRx4YHLqqVmPDuOPtbwE0Z9CbiNIxfjOjcVfd5j9A8vkHH8RQ5rYaL/aU5xR2CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T14:31:03.438161Z","bundle_sha256":"3a32cc19fbd1a55dfc24c1a501ba91bb168165f2085a4c4d63eda6fc5f8e3b84"}}