{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:Z4EHBPAIXB7W5OQZDE7GUOB6GM","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":"2bedf446447bf4f0b07003bbc84a035e67ccfa8bd3783d22051a44720ee42edf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-19T03:43:56Z","title_canon_sha256":"1f92d8fc541911bcc1be93a1153f94a0dbb55ad85c46201a61ab5d01faaf6f47"},"schema_version":"1.0","source":{"id":"2011.09634","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.09634","created_at":"2026-07-05T02:05:45Z"},{"alias_kind":"arxiv_version","alias_value":"2011.09634v2","created_at":"2026-07-05T02:05:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.09634","created_at":"2026-07-05T02:05:45Z"},{"alias_kind":"pith_short_12","alias_value":"Z4EHBPAIXB7W","created_at":"2026-07-05T02:05:45Z"},{"alias_kind":"pith_short_16","alias_value":"Z4EHBPAIXB7W5OQZ","created_at":"2026-07-05T02:05:45Z"},{"alias_kind":"pith_short_8","alias_value":"Z4EHBPAI","created_at":"2026-07-05T02:05:45Z"}],"graph_snapshots":[{"event_id":"sha256:fe6b32ea892f52e7163229a9e981eb7dee532f19f10c023f5456e1feac99792f","target":"graph","created_at":"2026-07-05T02:05:45Z","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/2011.09634/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we teach machines to understand visuals and natural language by learning the mapping between sentences and noisy video snippets without explicit annotations. Firstly, we define a self-supervised learning framework that captures the cross-modal information. A novel adversarial learning module is then introduced to explicitly handle the noises in the natural videos, where the subtitle sentences are not guaranteed to be strongly corresponded to the video snippets. For training and evaluation, we contribute a new dataset `ApartmenTour' that contains a large number of online videos a","authors_text":"Linhai Xie, Lucia Specia, Sen Wang, Yishu Miao, Yujie Zhong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-19T03:43:56Z","title":"Watch and Learn: Mapping Language and Noisy Real-world Videos with Self-supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.09634","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":"sha256:81875cb7c8fc7c97cdbb937e1597c1b54438b9ad3700cb9f9236020eb4d95101","target":"record","created_at":"2026-07-05T02:05:45Z","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":"2bedf446447bf4f0b07003bbc84a035e67ccfa8bd3783d22051a44720ee42edf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-19T03:43:56Z","title_canon_sha256":"1f92d8fc541911bcc1be93a1153f94a0dbb55ad85c46201a61ab5d01faaf6f47"},"schema_version":"1.0","source":{"id":"2011.09634","kind":"arxiv","version":2}},"canonical_sha256":"cf0870bc08b87f6eba19193e6a383e333874e522f440b0c1093c722c2e4934cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf0870bc08b87f6eba19193e6a383e333874e522f440b0c1093c722c2e4934cf","first_computed_at":"2026-07-05T02:05:45.336309Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:05:45.336309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wKQJwc/h3nEHkm4M/FfAQzSln7zKDu4u2dM3kgc8A40W05jgC57nDkbqcxGf9zY7hr4HLITrYouKTNb2RCkPCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:05:45.336733Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.09634","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81875cb7c8fc7c97cdbb937e1597c1b54438b9ad3700cb9f9236020eb4d95101","sha256:fe6b32ea892f52e7163229a9e981eb7dee532f19f10c023f5456e1feac99792f"],"state_sha256":"cf2e583acd81179dcd201095114c219dea62a9ab79dcd1d1c7c468f5c3ae80f0"}