{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:F67KROBVTN46KPTPEOOGOZKRTU","short_pith_number":"pith:F67KROBV","canonical_record":{"source":{"id":"2003.03715","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-08T04:34:58Z","cross_cats_sorted":[],"title_canon_sha256":"29b078b52d79f262fd88115ecd57e18ce8ad3c80c4ffccc9192655f539ed9617","abstract_canon_sha256":"3b1ac68a4f49cc39c3f3a87fb3c73316bff8affc3550f453f8b7f01b205b109a"},"schema_version":"1.0"},"canonical_sha256":"2fbea8b8359b79e53e6f239c6765519d354944fd3e37f39b19de53cb04a4443c","source":{"kind":"arxiv","id":"2003.03715","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:F67KROBVTN46KPTPEOOGOZKRTU","target":"record","payload":{"canonical_record":{"source":{"id":"2003.03715","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-08T04:34:58Z","cross_cats_sorted":[],"title_canon_sha256":"29b078b52d79f262fd88115ecd57e18ce8ad3c80c4ffccc9192655f539ed9617","abstract_canon_sha256":"3b1ac68a4f49cc39c3f3a87fb3c73316bff8affc3550f453f8b7f01b205b109a"},"schema_version":"1.0"},"canonical_sha256":"2fbea8b8359b79e53e6f239c6765519d354944fd3e37f39b19de53cb04a4443c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:18:55.102464Z","signature_b64":"KvjBelkmh/4J9IxHB0u6TOaUfcvRZ8MOYFdgaTxYHx0IQf+6A9L6+I8v5cDAjU5lzLrq9ZoUm5XJZ/d5olr1DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fbea8b8359b79e53e6f239c6765519d354944fd3e37f39b19de53cb04a4443c","last_reissued_at":"2026-07-05T01:18:55.101985Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:18:55.101985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.03715","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:18:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Q4SzCLhEi/Xbwb12H/uovUkhlEwITcJryXeHZsLk+rYh6mRlgLjS7bmoCb16TlHzxI8Sh4d8Bh3/Gmz3t+CBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:24:06.097641Z"},"content_sha256":"699cf4e68f7634ebafab61b897c2808d137383d9a804ca48d9fc669f945d9d47","schema_version":"1.0","event_id":"sha256:699cf4e68f7634ebafab61b897c2808d137383d9a804ca48d9fc669f945d9d47"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:F67KROBVTN46KPTPEOOGOZKRTU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OVC-Net: Object-Oriented Video Captioning with Temporal Graph and Detail Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangyi Zhu, Guang Chen, Jenq-Neng Hwang, Jun Guo, Zhanyu Ma","submitted_at":"2020-03-08T04:34:58Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.03715","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2003.03715/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:18:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZIFFAC10YAF7MUlyDf/Y3h6KRCsh6j/B1DZqmeFpbGVWIeZmH8eMDBFS3PGWAXoCowK2cl59wNAKg9YhiRe4Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:24:06.098148Z"},"content_sha256":"66802ec0bed2b9f6e0f7bed918fa30af4dc97ebde10a3f7ffc0e0386bdbd7530","schema_version":"1.0","event_id":"sha256:66802ec0bed2b9f6e0f7bed918fa30af4dc97ebde10a3f7ffc0e0386bdbd7530"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F67KROBVTN46KPTPEOOGOZKRTU/bundle.json","state_url":"https://pith.science/pith/F67KROBVTN46KPTPEOOGOZKRTU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F67KROBVTN46KPTPEOOGOZKRTU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T18:24:06Z","links":{"resolver":"https://pith.science/pith/F67KROBVTN46KPTPEOOGOZKRTU","bundle":"https://pith.science/pith/F67KROBVTN46KPTPEOOGOZKRTU/bundle.json","state":"https://pith.science/pith/F67KROBVTN46KPTPEOOGOZKRTU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F67KROBVTN46KPTPEOOGOZKRTU/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xP5dmBvZoKuMyQq8G6xxSkrLRcXkbfPGNU0AO0o/jFgIIX3eQJSUZyO/xaT5N7l8YURv1RPzmxxSeKDmmE+SDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:24:06.105028Z","bundle_sha256":"f0a82de9363a9347b7dc6a312666b41fafd5f672417ea1bc0caf71f8ad41d98c"}}