{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:K3M2KEY4JIG2VMVVSACEKVQVKJ","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":"28095f42a00b063a69399b0900d08a74f77eb749c1d04d7c761b197e95084558","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-01-16T08:28:57Z","title_canon_sha256":"e0e28fca3d47c5e1bc1666e405a315bc1494875bb23a7d804b4797f056b1bb7f"},"schema_version":"1.0","source":{"id":"2001.05691","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.05691","created_at":"2026-07-05T02:10:23Z"},{"alias_kind":"arxiv_version","alias_value":"2001.05691v3","created_at":"2026-07-05T02:10:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.05691","created_at":"2026-07-05T02:10:23Z"},{"alias_kind":"pith_short_12","alias_value":"K3M2KEY4JIG2","created_at":"2026-07-05T02:10:23Z"},{"alias_kind":"pith_short_16","alias_value":"K3M2KEY4JIG2VMVV","created_at":"2026-07-05T02:10:23Z"},{"alias_kind":"pith_short_8","alias_value":"K3M2KEY4","created_at":"2026-07-05T02:10:23Z"}],"graph_snapshots":[{"event_id":"sha256:b6c39459c4b38977f364df0d73cfe10ddd67b2130bc1c8edb7db4a11cc8d94f7","target":"graph","created_at":"2026-07-05T02:10:23Z","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/2001.05691/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current video representations heavily rely on learning from manually annotated video datasets which are time-consuming and expensive to acquire. We observe videos are naturally accompanied by abundant text information such as YouTube titles and Instagram captions. In this paper, we leverage this visual-textual connection to learn spatiotemporal features in an efficient weakly-supervised manner. We present a general cross-modal pair discrimination (CPD) framework to capture this correlation between a video and its associated text. Specifically, we adopt noise-contrastive estimation to tackle th","authors_text":"Limin Wang, Tianhao Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-01-16T08:28:57Z","title":"Learning Spatiotemporal Features via Video and Text Pair Discrimination"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.05691","kind":"arxiv","version":3},"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:a63db148e02fe7ee720cc4363849663c0e1603e1ed25a6a035f5b564b18df60b","target":"record","created_at":"2026-07-05T02:10:23Z","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":"28095f42a00b063a69399b0900d08a74f77eb749c1d04d7c761b197e95084558","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-01-16T08:28:57Z","title_canon_sha256":"e0e28fca3d47c5e1bc1666e405a315bc1494875bb23a7d804b4797f056b1bb7f"},"schema_version":"1.0","source":{"id":"2001.05691","kind":"arxiv","version":3}},"canonical_sha256":"56d9a5131c4a0daab2b59004455615524302b8d8440d32a2669cb26c15839884","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56d9a5131c4a0daab2b59004455615524302b8d8440d32a2669cb26c15839884","first_computed_at":"2026-07-05T02:10:23.856407Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:10:23.856407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8N1W2qa+daa19IPc921KC+xxyyr9F4CaBjD0Ml2T9+wQhWNQGLmKquhAzi2DRdcdgF8nRiXcUSYNipyAmu/hDA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:10:23.856846Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.05691","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a63db148e02fe7ee720cc4363849663c0e1603e1ed25a6a035f5b564b18df60b","sha256:b6c39459c4b38977f364df0d73cfe10ddd67b2130bc1c8edb7db4a11cc8d94f7"],"state_sha256":"3b1c8c1060144ebb8e747a8a7d1b7fcc60939829217e1a67f6b6f2e5893edd29"}