{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:6HUFES4UCGBBD6BJDXAQ5ICPHS","short_pith_number":"pith:6HUFES4U","canonical_record":{"source":{"id":"2005.00200","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-01T03:49:26Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"d1890376bdc589429020297e8015ff31945cc7334419c6243fa1954d89c01796","abstract_canon_sha256":"d098df32be7da8f41f6f2b5abeb0c24bca43ee76018172f5a5a43dda3082d884"},"schema_version":"1.0"},"canonical_sha256":"f1e8524b94118211f8291dc10ea04f3c8559dd8e20761d195187108c966050e1","source":{"kind":"arxiv","id":"2005.00200","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.00200","created_at":"2026-07-05T01:39:13Z"},{"alias_kind":"arxiv_version","alias_value":"2005.00200v2","created_at":"2026-07-05T01:39:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00200","created_at":"2026-07-05T01:39:13Z"},{"alias_kind":"pith_short_12","alias_value":"6HUFES4UCGBB","created_at":"2026-07-05T01:39:13Z"},{"alias_kind":"pith_short_16","alias_value":"6HUFES4UCGBBD6BJ","created_at":"2026-07-05T01:39:13Z"},{"alias_kind":"pith_short_8","alias_value":"6HUFES4U","created_at":"2026-07-05T01:39:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:6HUFES4UCGBBD6BJDXAQ5ICPHS","target":"record","payload":{"canonical_record":{"source":{"id":"2005.00200","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-01T03:49:26Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"d1890376bdc589429020297e8015ff31945cc7334419c6243fa1954d89c01796","abstract_canon_sha256":"d098df32be7da8f41f6f2b5abeb0c24bca43ee76018172f5a5a43dda3082d884"},"schema_version":"1.0"},"canonical_sha256":"f1e8524b94118211f8291dc10ea04f3c8559dd8e20761d195187108c966050e1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:39:13.339862Z","signature_b64":"SK32HdA3X/hOAyR66YcQOh3KSDERJosFyj/6C7tg5oiwXHS2M1FN+6xtHI724n2s4i5/fHvvv8HAoW1qf96KDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1e8524b94118211f8291dc10ea04f3c8559dd8e20761d195187108c966050e1","last_reissued_at":"2026-07-05T01:39:13.339296Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:39:13.339296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.00200","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":"2026-07-05T01:39:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ffusGexe/vOF3B0Yh8bFC0ecG7f4RiY8VTk309qg6g2gVwHUQjxNCohrnZ/4VEK0i6L4nn7GspE+JwpYM2EIDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T10:41:44.198272Z"},"content_sha256":"7564f116d0d7e12b19e54248ba33c23527083daab4334290a0190375ce361805","schema_version":"1.0","event_id":"sha256:7564f116d0d7e12b19e54248ba33c23527083daab4334290a0190375ce361805"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:6HUFES4UCGBBD6BJDXAQ5ICPHS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jingjing Liu, Licheng Yu, Linjie Li, Yen-Chun Chen, Yu Cheng, Zhe Gan","submitted_at":"2020-05-01T03:49:26Z","abstract_excerpt":"We present HERO, a novel framework for large-scale video+language omni-representation learning. HERO encodes multimodal inputs in a hierarchical structure, where local context of a video frame is captured by a Cross-modal Transformer via multimodal fusion, and global video context is captured by a Temporal Transformer. In addition to standard Masked Language Modeling (MLM) and Masked Frame Modeling (MFM) objectives, we design two new pre-training tasks: (i) Video-Subtitle Matching (VSM), where the model predicts both global and local temporal alignment; and (ii) Frame Order Modeling (FOM), whe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00200","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/2005.00200/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":"2026-07-05T01:39:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GwzFEIGwqxFRzwhJ8Zi0uRxT23fh1GbWKFveCNCTFa8OmStqoigO+56sbt/Dp4MJQxw79cHsAcXPymJfH9T8CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T10:41:44.199266Z"},"content_sha256":"3c71be5d616ac37eea0ea593d88d4bea52746ef38b4248ae8187bf0db849bbe5","schema_version":"1.0","event_id":"sha256:3c71be5d616ac37eea0ea593d88d4bea52746ef38b4248ae8187bf0db849bbe5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6HUFES4UCGBBD6BJDXAQ5ICPHS/bundle.json","state_url":"https://pith.science/pith/6HUFES4UCGBBD6BJDXAQ5ICPHS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6HUFES4UCGBBD6BJDXAQ5ICPHS/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":"2026-08-14T10:41:44Z","links":{"resolver":"https://pith.science/pith/6HUFES4UCGBBD6BJDXAQ5ICPHS","bundle":"https://pith.science/pith/6HUFES4UCGBBD6BJDXAQ5ICPHS/bundle.json","state":"https://pith.science/pith/6HUFES4UCGBBD6BJDXAQ5ICPHS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6HUFES4UCGBBD6BJDXAQ5ICPHS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:6HUFES4UCGBBD6BJDXAQ5ICPHS","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":"d098df32be7da8f41f6f2b5abeb0c24bca43ee76018172f5a5a43dda3082d884","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-01T03:49:26Z","title_canon_sha256":"d1890376bdc589429020297e8015ff31945cc7334419c6243fa1954d89c01796"},"schema_version":"1.0","source":{"id":"2005.00200","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.00200","created_at":"2026-07-05T01:39:13Z"},{"alias_kind":"arxiv_version","alias_value":"2005.00200v2","created_at":"2026-07-05T01:39:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00200","created_at":"2026-07-05T01:39:13Z"},{"alias_kind":"pith_short_12","alias_value":"6HUFES4UCGBB","created_at":"2026-07-05T01:39:13Z"},{"alias_kind":"pith_short_16","alias_value":"6HUFES4UCGBBD6BJ","created_at":"2026-07-05T01:39:13Z"},{"alias_kind":"pith_short_8","alias_value":"6HUFES4U","created_at":"2026-07-05T01:39:13Z"}],"graph_snapshots":[{"event_id":"sha256:3c71be5d616ac37eea0ea593d88d4bea52746ef38b4248ae8187bf0db849bbe5","target":"graph","created_at":"2026-07-05T01:39:13Z","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/2005.00200/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present HERO, a novel framework for large-scale video+language omni-representation learning. HERO encodes multimodal inputs in a hierarchical structure, where local context of a video frame is captured by a Cross-modal Transformer via multimodal fusion, and global video context is captured by a Temporal Transformer. In addition to standard Masked Language Modeling (MLM) and Masked Frame Modeling (MFM) objectives, we design two new pre-training tasks: (i) Video-Subtitle Matching (VSM), where the model predicts both global and local temporal alignment; and (ii) Frame Order Modeling (FOM), whe","authors_text":"Jingjing Liu, Licheng Yu, Linjie Li, Yen-Chun Chen, Yu Cheng, Zhe Gan","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-01T03:49:26Z","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00200","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":"sha256:7564f116d0d7e12b19e54248ba33c23527083daab4334290a0190375ce361805","target":"record","created_at":"2026-07-05T01:39:13Z","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":"d098df32be7da8f41f6f2b5abeb0c24bca43ee76018172f5a5a43dda3082d884","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-01T03:49:26Z","title_canon_sha256":"d1890376bdc589429020297e8015ff31945cc7334419c6243fa1954d89c01796"},"schema_version":"1.0","source":{"id":"2005.00200","kind":"arxiv","version":2}},"canonical_sha256":"f1e8524b94118211f8291dc10ea04f3c8559dd8e20761d195187108c966050e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1e8524b94118211f8291dc10ea04f3c8559dd8e20761d195187108c966050e1","first_computed_at":"2026-07-05T01:39:13.339296Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:39:13.339296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SK32HdA3X/hOAyR66YcQOh3KSDERJosFyj/6C7tg5oiwXHS2M1FN+6xtHI724n2s4i5/fHvvv8HAoW1qf96KDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:39:13.339862Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.00200","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7564f116d0d7e12b19e54248ba33c23527083daab4334290a0190375ce361805","sha256:3c71be5d616ac37eea0ea593d88d4bea52746ef38b4248ae8187bf0db849bbe5"],"state_sha256":"16e125f6d29ceb19caa428d176623f6b69b8a794e2dce0f5bc03118f3a764af1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MEnJvv2xSdPvEuzRJ24q2EwvD+mrQJ3vFdheNGLxtYWIMTch22YcgHaY9uCBq+AsTpDh9i9gxdaM0WBav193Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T10:41:44.205114Z","bundle_sha256":"d4aa0dcf06db98ab7a819b58d0961387846357e8464c88afbd48f27b99b45b1b"}}