{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IUK7TYQUOS3YFWH5XZPOMZMOO4","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":"824bec71d27a2dd731870a9ea44af6b15d1296fa12a0600ce84ab6c6ee584715","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-22T08:13:25Z","title_canon_sha256":"1d355d2062f8754552d619348b67730145e83ec9746580b38d963560b8b73297"},"schema_version":"1.0","source":{"id":"2303.12370","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.12370","created_at":"2026-07-05T05:55:22Z"},{"alias_kind":"arxiv_version","alias_value":"2303.12370v2","created_at":"2026-07-05T05:55:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.12370","created_at":"2026-07-05T05:55:22Z"},{"alias_kind":"pith_short_12","alias_value":"IUK7TYQUOS3Y","created_at":"2026-07-05T05:55:22Z"},{"alias_kind":"pith_short_16","alias_value":"IUK7TYQUOS3YFWH5","created_at":"2026-07-05T05:55:22Z"},{"alias_kind":"pith_short_8","alias_value":"IUK7TYQU","created_at":"2026-07-05T05:55:22Z"}],"graph_snapshots":[{"event_id":"sha256:176fcfacc1b35af795db6d834e819ff633e93d18a14ea9e07fa3ac0e9fa7438a","target":"graph","created_at":"2026-07-05T05:55:22Z","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/2303.12370/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sequential video understanding, as an emerging video understanding task, has driven lots of researchers' attention because of its goal-oriented nature. This paper studies weakly supervised sequential video understanding where the accurate time-stamp level text-video alignment is not provided. We solve this task by borrowing ideas from CLIP. Specifically, we use a transformer to aggregate frame-level features for video representation and use a pre-trained text encoder to encode the texts corresponding to each action and the whole video, respectively. To model the correspondence between text and","authors_text":"Dongze Lian, Huazhang Hu, Shenghua Gao, Sixun Dong, Weixin Luo, Yicheng Qian","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-22T08:13:25Z","title":"Weakly Supervised Video Representation Learning with Unaligned Text for Sequential Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.12370","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":"sha256:8cef9db5d79bec4c3880f90ff371035a1478e6e9aba5e3f5bda6bd7dbaa39b75","target":"record","created_at":"2026-07-05T05:55:22Z","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":"824bec71d27a2dd731870a9ea44af6b15d1296fa12a0600ce84ab6c6ee584715","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-22T08:13:25Z","title_canon_sha256":"1d355d2062f8754552d619348b67730145e83ec9746580b38d963560b8b73297"},"schema_version":"1.0","source":{"id":"2303.12370","kind":"arxiv","version":2}},"canonical_sha256":"4515f9e21474b782d8fdbe5ee6658e77122ea2c119081b9934aeec2481a28720","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4515f9e21474b782d8fdbe5ee6658e77122ea2c119081b9934aeec2481a28720","first_computed_at":"2026-07-05T05:55:22.649474Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:55:22.649474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1ahxg2AMGqC8iQHuflqBFddtlq+1ATL3C1zd9ti5PdUwm0lANhYjubSTypwvSs3xoCCq2irvSH798sGg0OIBDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:55:22.649862Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.12370","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8cef9db5d79bec4c3880f90ff371035a1478e6e9aba5e3f5bda6bd7dbaa39b75","sha256:176fcfacc1b35af795db6d834e819ff633e93d18a14ea9e07fa3ac0e9fa7438a"],"state_sha256":"cb3a10cd864f119c814f86bcec36d0823469028906066f7b51fc2c726d4b9838"}