{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:IPRSTJ4SAKGF4QNHJHBONYEESB","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":"b624e9d8dd0d044993cc3ab930487b82bcfa859973416b297a0f5685e4d69eab","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-11T12:13:22Z","title_canon_sha256":"41d7df8f49df621bddfa700686745f9cf43515c466aa4588d52fe09a78d2becd"},"schema_version":"1.0","source":{"id":"2110.05204","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.05204","created_at":"2026-07-05T03:22:37Z"},{"alias_kind":"arxiv_version","alias_value":"2110.05204v3","created_at":"2026-07-05T03:22:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05204","created_at":"2026-07-05T03:22:37Z"},{"alias_kind":"pith_short_12","alias_value":"IPRSTJ4SAKGF","created_at":"2026-07-05T03:22:37Z"},{"alias_kind":"pith_short_16","alias_value":"IPRSTJ4SAKGF4QNH","created_at":"2026-07-05T03:22:37Z"},{"alias_kind":"pith_short_8","alias_value":"IPRSTJ4S","created_at":"2026-07-05T03:22:37Z"}],"graph_snapshots":[{"event_id":"sha256:d44462da6a70e5f6a1dd9e5681fb3f0966aa74ddd215ab6dc5662ee05312792d","target":"graph","created_at":"2026-07-05T03:22:37Z","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/2110.05204/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This report describes our solution to the VALUE Challenge 2021 in the captioning task. Our solution, named CLIP4Caption++, is built on X-Linear/X-Transformer, which is an advanced model with encoder-decoder architecture. We make the following improvements on the proposed CLIP4Caption++: We employ an advanced encoder-decoder model architecture X-Transformer as our main framework and make the following improvements: 1) we utilize three strong pre-trained CLIP models to extract the text-related appearance visual features. 2) we adopt the TSN sampling strategy for data enhancement. 3) we involve t","authors_text":"Dian Li, Fengyun Rao, Mingkang Tang, Zhanyu Wang, Zhaoyang Zeng","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-11T12:13:22Z","title":"CLIP4Caption ++: Multi-CLIP for Video Caption"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.05204","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":"sha256:605fb4ac434bd966085e0c042fe2234d277ffadf0d0f198b4348d182c4f78a53","target":"record","created_at":"2026-07-05T03:22:37Z","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":"b624e9d8dd0d044993cc3ab930487b82bcfa859973416b297a0f5685e4d69eab","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-11T12:13:22Z","title_canon_sha256":"41d7df8f49df621bddfa700686745f9cf43515c466aa4588d52fe09a78d2becd"},"schema_version":"1.0","source":{"id":"2110.05204","kind":"arxiv","version":3}},"canonical_sha256":"43e329a792028c5e41a749c2e6e084904a9d59cb2dbc82905ae294bf43babb0a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43e329a792028c5e41a749c2e6e084904a9d59cb2dbc82905ae294bf43babb0a","first_computed_at":"2026-07-05T03:22:37.412464Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:22:37.412464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JVD8UzKRgc/q3HZ/4F6csG1kkBBo3/lCWB/r4ZsNLh98JFufmxhuf97pzOWlI1PVvtGARMEwGIYOJgOK5v4FBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:22:37.412887Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.05204","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:605fb4ac434bd966085e0c042fe2234d277ffadf0d0f198b4348d182c4f78a53","sha256:d44462da6a70e5f6a1dd9e5681fb3f0966aa74ddd215ab6dc5662ee05312792d"],"state_sha256":"0f9ccd992a6be9d6424698aed80470649673959949a86b34ada3e4d608ca9a01"}