{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:MYXDCFQE4DFQXIGBWJ5RURIEGK","short_pith_number":"pith:MYXDCFQE","canonical_record":{"source":{"id":"2111.10337","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-19T17:36:01Z","cross_cats_sorted":[],"title_canon_sha256":"5e0291ddbac3393797bb22f929fc0f82b8ab39f6e88f254936ab4cd0bf96b615","abstract_canon_sha256":"37696fb243612d661d16bcb812e2dba3b3ffd0bb83b54306273d496754236541"},"schema_version":"1.0"},"canonical_sha256":"662e311604e0cb0ba0c1b27b1a450432bc7dea5447d62a0769d9eb7fbb31bf97","source":{"kind":"arxiv","id":"2111.10337","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.10337","created_at":"2026-07-05T04:38:34Z"},{"alias_kind":"arxiv_version","alias_value":"2111.10337v2","created_at":"2026-07-05T04:38:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.10337","created_at":"2026-07-05T04:38:34Z"},{"alias_kind":"pith_short_12","alias_value":"MYXDCFQE4DFQ","created_at":"2026-07-05T04:38:34Z"},{"alias_kind":"pith_short_16","alias_value":"MYXDCFQE4DFQXIGB","created_at":"2026-07-05T04:38:34Z"},{"alias_kind":"pith_short_8","alias_value":"MYXDCFQE","created_at":"2026-07-05T04:38:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:MYXDCFQE4DFQXIGBWJ5RURIEGK","target":"record","payload":{"canonical_record":{"source":{"id":"2111.10337","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-19T17:36:01Z","cross_cats_sorted":[],"title_canon_sha256":"5e0291ddbac3393797bb22f929fc0f82b8ab39f6e88f254936ab4cd0bf96b615","abstract_canon_sha256":"37696fb243612d661d16bcb812e2dba3b3ffd0bb83b54306273d496754236541"},"schema_version":"1.0"},"canonical_sha256":"662e311604e0cb0ba0c1b27b1a450432bc7dea5447d62a0769d9eb7fbb31bf97","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:38:34.671328Z","signature_b64":"sDBXUBpXyqlVKEiSc+TYtIZliAITEs3PUEfjTgUuIBwdthsatbu2nd2tKLpaYF+IrEVy1LEqRhuiV3igjsWeDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"662e311604e0cb0ba0c1b27b1a450432bc7dea5447d62a0769d9eb7fbb31bf97","last_reissued_at":"2026-07-05T04:38:34.670875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:38:34.670875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.10337","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":"2026-07-05T04:38:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i1isjORziPGfO6/qEkazPElHAQKnARmi57xOroy1/2IX7aGoAkYrBB2jnQ2yz8Hh5+hIlKxtn+H5nvaNlKeEAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:54:37.569958Z"},"content_sha256":"81e3b510e1253a6bb48a2c63b871a3b875b1e42d33ca7c9b1be8bc3dbb1279f6","schema_version":"1.0","event_id":"sha256:81e3b510e1253a6bb48a2c63b871a3b875b1e42d33ca7c9b1be8bc3dbb1279f6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:MYXDCFQE4DFQXIGBWJ5RURIEGK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baining Guo, Bei Liu, Hongwei Xue, Huan Yang, Jianlong Fu, Tiankai Hang, Yanhong Zeng, Yuchong Sun","submitted_at":"2021-11-19T17:36:01Z","abstract_excerpt":"We study joint video and language (VL) pre-training to enable cross-modality learning and benefit plentiful downstream VL tasks. Existing works either extract low-quality video features or learn limited text embedding, while neglecting that high-resolution videos and diversified semantics can significantly improve cross-modality learning. In this paper, we propose a novel High-resolution and Diversified VIdeo-LAnguage pre-training model (HD-VILA) for many visual tasks. In particular, we collect a large dataset with two distinct properties: 1) the first high-resolution dataset including 371.5k "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.10337","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/2111.10337/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":"2026-07-05T04:38:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bGQU5c9vK7xDNEh2izo1G34OOil1V+8SGFTJvG1+ipIJs/Pn4Zb3dcpVeDMnBPNTRCzvvkPTVygnPVZ8UvdLAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:54:37.570620Z"},"content_sha256":"3ce4ee8614c921ffad5847a77f8329ffdda8e1240513de646b81c1861e066292","schema_version":"1.0","event_id":"sha256:3ce4ee8614c921ffad5847a77f8329ffdda8e1240513de646b81c1861e066292"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MYXDCFQE4DFQXIGBWJ5RURIEGK/bundle.json","state_url":"https://pith.science/pith/MYXDCFQE4DFQXIGBWJ5RURIEGK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MYXDCFQE4DFQXIGBWJ5RURIEGK/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":"2026-07-09T06:54:37Z","links":{"resolver":"https://pith.science/pith/MYXDCFQE4DFQXIGBWJ5RURIEGK","bundle":"https://pith.science/pith/MYXDCFQE4DFQXIGBWJ5RURIEGK/bundle.json","state":"https://pith.science/pith/MYXDCFQE4DFQXIGBWJ5RURIEGK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MYXDCFQE4DFQXIGBWJ5RURIEGK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MYXDCFQE4DFQXIGBWJ5RURIEGK","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":"37696fb243612d661d16bcb812e2dba3b3ffd0bb83b54306273d496754236541","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-19T17:36:01Z","title_canon_sha256":"5e0291ddbac3393797bb22f929fc0f82b8ab39f6e88f254936ab4cd0bf96b615"},"schema_version":"1.0","source":{"id":"2111.10337","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.10337","created_at":"2026-07-05T04:38:34Z"},{"alias_kind":"arxiv_version","alias_value":"2111.10337v2","created_at":"2026-07-05T04:38:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.10337","created_at":"2026-07-05T04:38:34Z"},{"alias_kind":"pith_short_12","alias_value":"MYXDCFQE4DFQ","created_at":"2026-07-05T04:38:34Z"},{"alias_kind":"pith_short_16","alias_value":"MYXDCFQE4DFQXIGB","created_at":"2026-07-05T04:38:34Z"},{"alias_kind":"pith_short_8","alias_value":"MYXDCFQE","created_at":"2026-07-05T04:38:34Z"}],"graph_snapshots":[{"event_id":"sha256:3ce4ee8614c921ffad5847a77f8329ffdda8e1240513de646b81c1861e066292","target":"graph","created_at":"2026-07-05T04:38:34Z","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/2111.10337/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study joint video and language (VL) pre-training to enable cross-modality learning and benefit plentiful downstream VL tasks. Existing works either extract low-quality video features or learn limited text embedding, while neglecting that high-resolution videos and diversified semantics can significantly improve cross-modality learning. In this paper, we propose a novel High-resolution and Diversified VIdeo-LAnguage pre-training model (HD-VILA) for many visual tasks. In particular, we collect a large dataset with two distinct properties: 1) the first high-resolution dataset including 371.5k ","authors_text":"Baining Guo, Bei Liu, Hongwei Xue, Huan Yang, Jianlong Fu, Tiankai Hang, Yanhong Zeng, Yuchong Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-19T17:36:01Z","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.10337","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":"sha256:81e3b510e1253a6bb48a2c63b871a3b875b1e42d33ca7c9b1be8bc3dbb1279f6","target":"record","created_at":"2026-07-05T04:38:34Z","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":"37696fb243612d661d16bcb812e2dba3b3ffd0bb83b54306273d496754236541","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-19T17:36:01Z","title_canon_sha256":"5e0291ddbac3393797bb22f929fc0f82b8ab39f6e88f254936ab4cd0bf96b615"},"schema_version":"1.0","source":{"id":"2111.10337","kind":"arxiv","version":2}},"canonical_sha256":"662e311604e0cb0ba0c1b27b1a450432bc7dea5447d62a0769d9eb7fbb31bf97","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"662e311604e0cb0ba0c1b27b1a450432bc7dea5447d62a0769d9eb7fbb31bf97","first_computed_at":"2026-07-05T04:38:34.670875Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:38:34.670875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sDBXUBpXyqlVKEiSc+TYtIZliAITEs3PUEfjTgUuIBwdthsatbu2nd2tKLpaYF+IrEVy1LEqRhuiV3igjsWeDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:38:34.671328Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.10337","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81e3b510e1253a6bb48a2c63b871a3b875b1e42d33ca7c9b1be8bc3dbb1279f6","sha256:3ce4ee8614c921ffad5847a77f8329ffdda8e1240513de646b81c1861e066292"],"state_sha256":"845b0b93b506f28bba84229222e04b228817f6aa2d5e312ca0bff0e0e7228c1f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ItSvA9A5qrcBhfQFofrcrbFeujy+nlgfuEbNjhRlEwkgi8z51xmvFW3qqmsJ0XBCaz9dB29Suirr5WZZqFiRAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:54:37.574177Z","bundle_sha256":"3a8d677fcdef37cc9e7cd962c0eb9c134b31e1c508340bab91d94b9aa412b38c"}}