{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:5XBUYHSW7YHM2GUX2NY2NIDQ3O","short_pith_number":"pith:5XBUYHSW","canonical_record":{"source":{"id":"2107.02681","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-07-06T15:41:32Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"d520de8c6e6cba620e119fb2d9e1582d67e85a1e58f57b33b2a2278e5864ffc7","abstract_canon_sha256":"211b184a44cfafbbdd8ee8cc26b916d832f9e82f90e5b78dde86bcb9162111dc"},"schema_version":"1.0"},"canonical_sha256":"edc34c1e56fe0ecd1a97d371a6a070db888708f848995069f1acb4b4ad672854","source":{"kind":"arxiv","id":"2107.02681","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.02681","created_at":"2026-07-05T03:23:44Z"},{"alias_kind":"arxiv_version","alias_value":"2107.02681v2","created_at":"2026-07-05T03:23:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.02681","created_at":"2026-07-05T03:23:44Z"},{"alias_kind":"pith_short_12","alias_value":"5XBUYHSW7YHM","created_at":"2026-07-05T03:23:44Z"},{"alias_kind":"pith_short_16","alias_value":"5XBUYHSW7YHM2GUX","created_at":"2026-07-05T03:23:44Z"},{"alias_kind":"pith_short_8","alias_value":"5XBUYHSW","created_at":"2026-07-05T03:23:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:5XBUYHSW7YHM2GUX2NY2NIDQ3O","target":"record","payload":{"canonical_record":{"source":{"id":"2107.02681","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-07-06T15:41:32Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"d520de8c6e6cba620e119fb2d9e1582d67e85a1e58f57b33b2a2278e5864ffc7","abstract_canon_sha256":"211b184a44cfafbbdd8ee8cc26b916d832f9e82f90e5b78dde86bcb9162111dc"},"schema_version":"1.0"},"canonical_sha256":"edc34c1e56fe0ecd1a97d371a6a070db888708f848995069f1acb4b4ad672854","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:23:44.029728Z","signature_b64":"VFCOsemmzSrRZgmv5AgrjlE8Hm4pL4TWHei/5Iv2if+YyTTgzFTVZcM6oVDv/LtYuNAaIQz1mmseSKpPFn4qAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edc34c1e56fe0ecd1a97d371a6a070db888708f848995069f1acb4b4ad672854","last_reissued_at":"2026-07-05T03:23:44.029244Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:23:44.029244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.02681","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:23:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yHu2mUndAtN9IbXxd01D5VfdBJrckhoghXqTXbEoRfJiDqmiyZYNFxtzEbSK2jnNU9XEQPgxsMemy3Q/PE7pDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T17:00:29.854230Z"},"content_sha256":"96bfd5667ba7140063c6601b0e1f477d095e7f12992f2b6dfea1ae9daa616441","schema_version":"1.0","event_id":"sha256:96bfd5667ba7140063c6601b0e1f477d095e7f12992f2b6dfea1ae9daa616441"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:5XBUYHSW7YHM2GUX2NY2NIDQ3O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hao Tan, Jaemin Cho, Mohit Bansal, Zineng Tang","submitted_at":"2021-07-06T15:41:32Z","abstract_excerpt":"Since visual perception can give rich information beyond text descriptions for world understanding, there has been increasing interest in leveraging visual grounding for language learning. Recently, vokenization (Tan and Bansal, 2020) has attracted attention by using the predictions of a text-to-image retrieval model as labels for language model supervision. Despite its success, the method suffers from approximation error of using finite image labels and the lack of vocabulary diversity of a small image-text dataset. To overcome these limitations, we present VidLanKD, a video-language knowledg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.02681","kind":"arxiv","version":2},"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/2107.02681/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":"2026-07-05T03:23:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P6T1F1wHRsiFyMV6gBvbcqSMhL38wdQT9E09DdtxMvMMMaN9IdzKGsRWDNfyFp1aNdUXouESsampXK5Q9B2oCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T17:00:29.854990Z"},"content_sha256":"06addf0a95586034fccafee0c83a216cf84014986d0df47d9c573a415f1ba6d5","schema_version":"1.0","event_id":"sha256:06addf0a95586034fccafee0c83a216cf84014986d0df47d9c573a415f1ba6d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5XBUYHSW7YHM2GUX2NY2NIDQ3O/bundle.json","state_url":"https://pith.science/pith/5XBUYHSW7YHM2GUX2NY2NIDQ3O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5XBUYHSW7YHM2GUX2NY2NIDQ3O/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":"2026-08-19T17:00:29Z","links":{"resolver":"https://pith.science/pith/5XBUYHSW7YHM2GUX2NY2NIDQ3O","bundle":"https://pith.science/pith/5XBUYHSW7YHM2GUX2NY2NIDQ3O/bundle.json","state":"https://pith.science/pith/5XBUYHSW7YHM2GUX2NY2NIDQ3O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5XBUYHSW7YHM2GUX2NY2NIDQ3O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:5XBUYHSW7YHM2GUX2NY2NIDQ3O","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":"211b184a44cfafbbdd8ee8cc26b916d832f9e82f90e5b78dde86bcb9162111dc","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-07-06T15:41:32Z","title_canon_sha256":"d520de8c6e6cba620e119fb2d9e1582d67e85a1e58f57b33b2a2278e5864ffc7"},"schema_version":"1.0","source":{"id":"2107.02681","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.02681","created_at":"2026-07-05T03:23:44Z"},{"alias_kind":"arxiv_version","alias_value":"2107.02681v2","created_at":"2026-07-05T03:23:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.02681","created_at":"2026-07-05T03:23:44Z"},{"alias_kind":"pith_short_12","alias_value":"5XBUYHSW7YHM","created_at":"2026-07-05T03:23:44Z"},{"alias_kind":"pith_short_16","alias_value":"5XBUYHSW7YHM2GUX","created_at":"2026-07-05T03:23:44Z"},{"alias_kind":"pith_short_8","alias_value":"5XBUYHSW","created_at":"2026-07-05T03:23:44Z"}],"graph_snapshots":[{"event_id":"sha256:06addf0a95586034fccafee0c83a216cf84014986d0df47d9c573a415f1ba6d5","target":"graph","created_at":"2026-07-05T03:23:44Z","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/2107.02681/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Since visual perception can give rich information beyond text descriptions for world understanding, there has been increasing interest in leveraging visual grounding for language learning. Recently, vokenization (Tan and Bansal, 2020) has attracted attention by using the predictions of a text-to-image retrieval model as labels for language model supervision. Despite its success, the method suffers from approximation error of using finite image labels and the lack of vocabulary diversity of a small image-text dataset. To overcome these limitations, we present VidLanKD, a video-language knowledg","authors_text":"Hao Tan, Jaemin Cho, Mohit Bansal, Zineng Tang","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-07-06T15:41:32Z","title":"VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.02681","kind":"arxiv","version":2},"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":"sha256:96bfd5667ba7140063c6601b0e1f477d095e7f12992f2b6dfea1ae9daa616441","target":"record","created_at":"2026-07-05T03:23:44Z","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":"211b184a44cfafbbdd8ee8cc26b916d832f9e82f90e5b78dde86bcb9162111dc","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-07-06T15:41:32Z","title_canon_sha256":"d520de8c6e6cba620e119fb2d9e1582d67e85a1e58f57b33b2a2278e5864ffc7"},"schema_version":"1.0","source":{"id":"2107.02681","kind":"arxiv","version":2}},"canonical_sha256":"edc34c1e56fe0ecd1a97d371a6a070db888708f848995069f1acb4b4ad672854","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"edc34c1e56fe0ecd1a97d371a6a070db888708f848995069f1acb4b4ad672854","first_computed_at":"2026-07-05T03:23:44.029244Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:23:44.029244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VFCOsemmzSrRZgmv5AgrjlE8Hm4pL4TWHei/5Iv2if+YyTTgzFTVZcM6oVDv/LtYuNAaIQz1mmseSKpPFn4qAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:23:44.029728Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.02681","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96bfd5667ba7140063c6601b0e1f477d095e7f12992f2b6dfea1ae9daa616441","sha256:06addf0a95586034fccafee0c83a216cf84014986d0df47d9c573a415f1ba6d5"],"state_sha256":"2cedbb6aa9d3fc12c100735f81a8adb9d4af2d70093c520f486ec72ddb24b92f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V+vsglzC/ApaJBoc5PnGMsqbZtS2OhzrG28fL77TJEjHUT4CVlVDslQb21S0Tsk1yGYgrESTvslQ6DyHK8FtAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T17:00:29.860677Z","bundle_sha256":"a38ede6dff3f7d4708be261286665debe1ffb03ba3d1320cb3b7a27a1bd0fc1f"}}