{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:5XMGSGPDR47DHTK7CCESWDVOC5","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":"b83c5cf62b0644154ea0894e544dbfd6629ff73e7c5c0e4eb3f4cfc3e17acaac","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-26T15:34:52Z","title_canon_sha256":"63c6f1e1813c0617cf3cd2b5012ca59b3d5e0ace42f471b096fe4aeee81215a4"},"schema_version":"1.0","source":{"id":"2002.11566","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.11566","created_at":"2026-07-05T00:44:03Z"},{"alias_kind":"arxiv_version","alias_value":"2002.11566v1","created_at":"2026-07-05T00:44:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.11566","created_at":"2026-07-05T00:44:03Z"},{"alias_kind":"pith_short_12","alias_value":"5XMGSGPDR47D","created_at":"2026-07-05T00:44:03Z"},{"alias_kind":"pith_short_16","alias_value":"5XMGSGPDR47DHTK7","created_at":"2026-07-05T00:44:03Z"},{"alias_kind":"pith_short_8","alias_value":"5XMGSGPD","created_at":"2026-07-05T00:44:03Z"}],"graph_snapshots":[{"event_id":"sha256:5ac0f8db12200b7cee452f4d29673691bc76dfb02eaf9804c52401e0336fcac9","target":"graph","created_at":"2026-07-05T00:44:03Z","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/2002.11566/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Taking full advantage of the information from both vision and language is critical for the video captioning task. Existing models lack adequate visual representation due to the neglect of interaction between object, and sufficient training for content-related words due to long-tailed problems. In this paper, we propose a complete video captioning system including both a novel model and an effective training strategy. Specifically, we propose an object relational graph (ORG) based encoder, which captures more detailed interaction features to enrich visual representation. Meanwhile, we design a ","authors_text":"Bing Li, Chunfeng Yuan, Peijin Wang, Weiming Hu, Yaya Shi, Zhengjun Zha, Ziqi Zhang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-26T15:34:52Z","title":"Object Relational Graph with Teacher-Recommended Learning for Video Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.11566","kind":"arxiv","version":1},"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":"sha256:2e0a671bb9a1254bf5fa9e5f4f0ee90493affcde89e8a71c611e5ead5cec1ca1","target":"record","created_at":"2026-07-05T00:44:03Z","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":"b83c5cf62b0644154ea0894e544dbfd6629ff73e7c5c0e4eb3f4cfc3e17acaac","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-26T15:34:52Z","title_canon_sha256":"63c6f1e1813c0617cf3cd2b5012ca59b3d5e0ace42f471b096fe4aeee81215a4"},"schema_version":"1.0","source":{"id":"2002.11566","kind":"arxiv","version":1}},"canonical_sha256":"edd86919e38f3e33cd5f10892b0eae17569e61aab72007cd28b9d730fe087442","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"edd86919e38f3e33cd5f10892b0eae17569e61aab72007cd28b9d730fe087442","first_computed_at":"2026-07-05T00:44:03.690321Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:44:03.690321Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y41yaGlSX2lJ7i/l3DSff92Th6t/a2KlBNwF2jPKVtz8lJ1J0UA67F+Rez+815bKFvbPXuglR061AkMXvQmADQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:44:03.690711Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.11566","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e0a671bb9a1254bf5fa9e5f4f0ee90493affcde89e8a71c611e5ead5cec1ca1","sha256:5ac0f8db12200b7cee452f4d29673691bc76dfb02eaf9804c52401e0336fcac9"],"state_sha256":"24f8d03c66822970b9a57372a3f05f31c256efe814121c2df3d76fe08109dacf"}