{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:APRIN43TRGFJWQDYIMRGUABSD4","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":"49d9cf65ca342b3f0586b33a9ffa77f2ccfd82ae0980b58fe487e38bc1c4b969","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-30T06:37:44Z","title_canon_sha256":"fbc9f8ae873525dda7ba8875a4ef6427666367da48830da26bbfb122503f005a"},"schema_version":"1.0","source":{"id":"2111.15162","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.15162","created_at":"2026-07-05T04:50:12Z"},{"alias_kind":"arxiv_version","alias_value":"2111.15162v2","created_at":"2026-07-05T04:50:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.15162","created_at":"2026-07-05T04:50:12Z"},{"alias_kind":"pith_short_12","alias_value":"APRIN43TRGFJ","created_at":"2026-07-05T04:50:12Z"},{"alias_kind":"pith_short_16","alias_value":"APRIN43TRGFJWQDY","created_at":"2026-07-05T04:50:12Z"},{"alias_kind":"pith_short_8","alias_value":"APRIN43T","created_at":"2026-07-05T04:50:12Z"}],"graph_snapshots":[{"event_id":"sha256:f9b7da227d96639bdcbdf30963da8af36e9d04ebc90052c9a1156093cb792186","target":"graph","created_at":"2026-07-05T04:50:12Z","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/2111.15162/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"For video captioning, \"pre-training and fine-tuning\" has become a de facto paradigm, where ImageNet Pre-training (INP) is usually used to encode the video content, then a task-oriented network is fine-tuned from scratch to cope with caption generation. This paper first investigates the impact of the recently proposed CLIP (Contrastive Language-Image Pre-training) on video captioning. Through the empirical study on INP vs. CLIP, we identify the potential deficiencies of INP and explore the key factors for accurate description generation. The results show that the INP-based model is tricky to ca","authors_text":"Bang Yang, Tong Zhang, Yuexian Zou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-30T06:37:44Z","title":"CLIP Meets Video Captioning: Concept-Aware Representation Learning Does Matter"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.15162","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":"sha256:1ae99ba999a31b15f2f7defa5b11fe8d898dce00220d246b02d8dcea7a09fc03","target":"record","created_at":"2026-07-05T04:50:12Z","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":"49d9cf65ca342b3f0586b33a9ffa77f2ccfd82ae0980b58fe487e38bc1c4b969","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-30T06:37:44Z","title_canon_sha256":"fbc9f8ae873525dda7ba8875a4ef6427666367da48830da26bbfb122503f005a"},"schema_version":"1.0","source":{"id":"2111.15162","kind":"arxiv","version":2}},"canonical_sha256":"03e286f373898a9b407843226a00321f355806f9c1838c7b9fade7cc660e0091","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03e286f373898a9b407843226a00321f355806f9c1838c7b9fade7cc660e0091","first_computed_at":"2026-07-05T04:50:12.958753Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:50:12.958753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"57l2iJUNweYTutxVNpDtrvzGz/cwx+YBJ9//Amy1pmhuKk93cvwKBW3bioDv43BYszJeD8UjSU2QHIxZd/jmAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:50:12.959095Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.15162","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ae99ba999a31b15f2f7defa5b11fe8d898dce00220d246b02d8dcea7a09fc03","sha256:f9b7da227d96639bdcbdf30963da8af36e9d04ebc90052c9a1156093cb792186"],"state_sha256":"c085143fc17ab1a2c7aad12958843945bc48fc72228f07b5e1e207b277574388"}