{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:6SQCGN7XN2XUANYQN4NRNWIFHO","short_pith_number":"pith:6SQCGN7X","canonical_record":{"source":{"id":"2108.02359","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-05T04:17:20Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"408a87ae1f34f0fd9bf2d287fae2c9d7a9ec4449fb48bb8daf213091eb710766","abstract_canon_sha256":"3df3244384c0eca82d67b09842901d099e4805eb86233ee9fd013b9a00557bb0"},"schema_version":"1.0"},"canonical_sha256":"f4a02337f76eaf4037106f1b16d9053b9bee36b710a8bbe3b8ea25a09142d404","source":{"kind":"arxiv","id":"2108.02359","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.02359","created_at":"2026-07-05T03:47:00Z"},{"alias_kind":"arxiv_version","alias_value":"2108.02359v2","created_at":"2026-07-05T03:47:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.02359","created_at":"2026-07-05T03:47:00Z"},{"alias_kind":"pith_short_12","alias_value":"6SQCGN7XN2XU","created_at":"2026-07-05T03:47:00Z"},{"alias_kind":"pith_short_16","alias_value":"6SQCGN7XN2XUANYQ","created_at":"2026-07-05T03:47:00Z"},{"alias_kind":"pith_short_8","alias_value":"6SQCGN7X","created_at":"2026-07-05T03:47:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:6SQCGN7XN2XUANYQN4NRNWIFHO","target":"record","payload":{"canonical_record":{"source":{"id":"2108.02359","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-05T04:17:20Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"408a87ae1f34f0fd9bf2d287fae2c9d7a9ec4449fb48bb8daf213091eb710766","abstract_canon_sha256":"3df3244384c0eca82d67b09842901d099e4805eb86233ee9fd013b9a00557bb0"},"schema_version":"1.0"},"canonical_sha256":"f4a02337f76eaf4037106f1b16d9053b9bee36b710a8bbe3b8ea25a09142d404","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:47:00.020491Z","signature_b64":"5C0eMN3EnhVODRns0MthFhexhXR0hkbW69Y2mawShxHdkRO9mx84m6ZNjhJLTWkIUhmq7BpnoKtrdj+04HBuCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4a02337f76eaf4037106f1b16d9053b9bee36b710a8bbe3b8ea25a09142d404","last_reissued_at":"2026-07-05T03:47:00.020005Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:47:00.020005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.02359","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:47:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uJVK6Gufa2mC5VFSFk2qtLyIUT5hQ3r8JMFsKX3bymIfW4nf2k/QTl72yV8Pj6onrF6kEXzvoA8Ox+1ilXapBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T18:21:07.351133Z"},"content_sha256":"2f58656efe57226462b99f44845ec19266b4a2870950a71f40926a64fd9ce15d","schema_version":"1.0","event_id":"sha256:2f58656efe57226462b99f44845ec19266b4a2870950a71f40926a64fd9ce15d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:6SQCGN7XN2XUANYQN4NRNWIFHO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"O2NA: An Object-Oriented Non-Autoregressive Approach for Controllable Video Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Bang Yang, Fenglin Liu, Shen Ge, Xian Wu, Xuancheng Ren, Xu Sun, Yuexian Zou","submitted_at":"2021-08-05T04:17:20Z","abstract_excerpt":"Video captioning combines video understanding and language generation. Different from image captioning that describes a static image with details of almost every object, video captioning usually considers a sequence of frames and biases towards focused objects, e.g., the objects that stay in focus regardless of the changing background. Therefore, detecting and properly accommodating focused objects is critical in video captioning. To enforce the description of focused objects and achieve controllable video captioning, we propose an Object-Oriented Non-Autoregressive approach (O2NA), which perf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.02359","kind":"arxiv","version":2},"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/2108.02359/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":"2026-07-05T03:47:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iyKft1RfJkqOdfotMkPX3zHLVfLFpEsLVv1MEBnaUM9rQR8EsplJMe08dzOlRDdiEI2Z+AY0GPe2lOQAvA7hCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T18:21:07.351642Z"},"content_sha256":"44acccea2b201831ff68a791020ca63a1b75e36ca49103d9074a2c0769882828","schema_version":"1.0","event_id":"sha256:44acccea2b201831ff68a791020ca63a1b75e36ca49103d9074a2c0769882828"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6SQCGN7XN2XUANYQN4NRNWIFHO/bundle.json","state_url":"https://pith.science/pith/6SQCGN7XN2XUANYQN4NRNWIFHO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6SQCGN7XN2XUANYQN4NRNWIFHO/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":"2026-08-23T18:21:07Z","links":{"resolver":"https://pith.science/pith/6SQCGN7XN2XUANYQN4NRNWIFHO","bundle":"https://pith.science/pith/6SQCGN7XN2XUANYQN4NRNWIFHO/bundle.json","state":"https://pith.science/pith/6SQCGN7XN2XUANYQN4NRNWIFHO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6SQCGN7XN2XUANYQN4NRNWIFHO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6SQCGN7XN2XUANYQN4NRNWIFHO","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":"3df3244384c0eca82d67b09842901d099e4805eb86233ee9fd013b9a00557bb0","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-05T04:17:20Z","title_canon_sha256":"408a87ae1f34f0fd9bf2d287fae2c9d7a9ec4449fb48bb8daf213091eb710766"},"schema_version":"1.0","source":{"id":"2108.02359","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.02359","created_at":"2026-07-05T03:47:00Z"},{"alias_kind":"arxiv_version","alias_value":"2108.02359v2","created_at":"2026-07-05T03:47:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.02359","created_at":"2026-07-05T03:47:00Z"},{"alias_kind":"pith_short_12","alias_value":"6SQCGN7XN2XU","created_at":"2026-07-05T03:47:00Z"},{"alias_kind":"pith_short_16","alias_value":"6SQCGN7XN2XUANYQ","created_at":"2026-07-05T03:47:00Z"},{"alias_kind":"pith_short_8","alias_value":"6SQCGN7X","created_at":"2026-07-05T03:47:00Z"}],"graph_snapshots":[{"event_id":"sha256:44acccea2b201831ff68a791020ca63a1b75e36ca49103d9074a2c0769882828","target":"graph","created_at":"2026-07-05T03:47:00Z","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/2108.02359/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video captioning combines video understanding and language generation. Different from image captioning that describes a static image with details of almost every object, video captioning usually considers a sequence of frames and biases towards focused objects, e.g., the objects that stay in focus regardless of the changing background. Therefore, detecting and properly accommodating focused objects is critical in video captioning. To enforce the description of focused objects and achieve controllable video captioning, we propose an Object-Oriented Non-Autoregressive approach (O2NA), which perf","authors_text":"Bang Yang, Fenglin Liu, Shen Ge, Xian Wu, Xuancheng Ren, Xu Sun, Yuexian Zou","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-05T04:17:20Z","title":"O2NA: An Object-Oriented Non-Autoregressive Approach for Controllable Video Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.02359","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":"sha256:2f58656efe57226462b99f44845ec19266b4a2870950a71f40926a64fd9ce15d","target":"record","created_at":"2026-07-05T03:47:00Z","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":"3df3244384c0eca82d67b09842901d099e4805eb86233ee9fd013b9a00557bb0","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-05T04:17:20Z","title_canon_sha256":"408a87ae1f34f0fd9bf2d287fae2c9d7a9ec4449fb48bb8daf213091eb710766"},"schema_version":"1.0","source":{"id":"2108.02359","kind":"arxiv","version":2}},"canonical_sha256":"f4a02337f76eaf4037106f1b16d9053b9bee36b710a8bbe3b8ea25a09142d404","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4a02337f76eaf4037106f1b16d9053b9bee36b710a8bbe3b8ea25a09142d404","first_computed_at":"2026-07-05T03:47:00.020005Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:47:00.020005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5C0eMN3EnhVODRns0MthFhexhXR0hkbW69Y2mawShxHdkRO9mx84m6ZNjhJLTWkIUhmq7BpnoKtrdj+04HBuCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:47:00.020491Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.02359","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f58656efe57226462b99f44845ec19266b4a2870950a71f40926a64fd9ce15d","sha256:44acccea2b201831ff68a791020ca63a1b75e36ca49103d9074a2c0769882828"],"state_sha256":"7ffac3e3718d897c38f5ca3a9a342e8cb8b7da77ee118240a4228ebdfa2ab266"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5ehtybrttrnwEs/szs/cOW1DujfyqUWzs65JnS8G0OXeNUQQKSfoEKSC3SYBZgJFXC+BMtizNcPlz3Hd3H+DAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T18:21:07.357368Z","bundle_sha256":"06d8b1d504d4f6319804ebe52e7cb9849884e8475ee39946d286e20a429979c9"}}