{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:F67KROBVTN46KPTPEOOGOZKRTU","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":"3b1ac68a4f49cc39c3f3a87fb3c73316bff8affc3550f453f8b7f01b205b109a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-08T04:34:58Z","title_canon_sha256":"29b078b52d79f262fd88115ecd57e18ce8ad3c80c4ffccc9192655f539ed9617"},"schema_version":"1.0","source":{"id":"2003.03715","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.03715","created_at":"2026-07-05T01:18:55Z"},{"alias_kind":"arxiv_version","alias_value":"2003.03715v5","created_at":"2026-07-05T01:18:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.03715","created_at":"2026-07-05T01:18:55Z"},{"alias_kind":"pith_short_12","alias_value":"F67KROBVTN46","created_at":"2026-07-05T01:18:55Z"},{"alias_kind":"pith_short_16","alias_value":"F67KROBVTN46KPTP","created_at":"2026-07-05T01:18:55Z"},{"alias_kind":"pith_short_8","alias_value":"F67KROBV","created_at":"2026-07-05T01:18:55Z"}],"graph_snapshots":[{"event_id":"sha256:66802ec0bed2b9f6e0f7bed918fa30af4dc97ebde10a3f7ffc0e0386bdbd7530","target":"graph","created_at":"2026-07-05T01:18:55Z","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/2003.03715/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional video captioning requests a holistic description of the video, yet the detailed descriptions of the specific objects may not be available. Without associating the moving trajectories, these image-based data-driven methods cannot understand the activities from the spatio-temporal transitions in the inter-object visual features. Besides, adopting ambiguous clip-sentence pairs in training, it goes against learning the multi-modal functional mappings owing to the one-to-many nature. In this paper, we propose a novel task to understand the videos in object-level, named object-oriented v","authors_text":"Fangyi Zhu, Guang Chen, Jenq-Neng Hwang, Jun Guo, Zhanyu Ma","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-08T04:34:58Z","title":"OVC-Net: Object-Oriented Video Captioning with Temporal Graph and Detail Enhancement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.03715","kind":"arxiv","version":5},"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":"sha256:699cf4e68f7634ebafab61b897c2808d137383d9a804ca48d9fc669f945d9d47","target":"record","created_at":"2026-07-05T01:18:55Z","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":"3b1ac68a4f49cc39c3f3a87fb3c73316bff8affc3550f453f8b7f01b205b109a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-08T04:34:58Z","title_canon_sha256":"29b078b52d79f262fd88115ecd57e18ce8ad3c80c4ffccc9192655f539ed9617"},"schema_version":"1.0","source":{"id":"2003.03715","kind":"arxiv","version":5}},"canonical_sha256":"2fbea8b8359b79e53e6f239c6765519d354944fd3e37f39b19de53cb04a4443c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fbea8b8359b79e53e6f239c6765519d354944fd3e37f39b19de53cb04a4443c","first_computed_at":"2026-07-05T01:18:55.101985Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:18:55.101985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KvjBelkmh/4J9IxHB0u6TOaUfcvRZ8MOYFdgaTxYHx0IQf+6A9L6+I8v5cDAjU5lzLrq9ZoUm5XJZ/d5olr1DA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:18:55.102464Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.03715","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:699cf4e68f7634ebafab61b897c2808d137383d9a804ca48d9fc669f945d9d47","sha256:66802ec0bed2b9f6e0f7bed918fa30af4dc97ebde10a3f7ffc0e0386bdbd7530"],"state_sha256":"11431171e6d47317e7e0a8deecc381ec32f2a1672a5a8319e32c72526c966618"}