{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6SYLY55ZIX3UKC765K6FG4NWZA","short_pith_number":"pith:6SYLY55Z","canonical_record":{"source":{"id":"2303.12423","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-22T09:49:53Z","cross_cats_sorted":[],"title_canon_sha256":"66426d4610b562fb7b30d36d598c30e77ec6da744f95a3af9d3c6b44587d4458","abstract_canon_sha256":"6754107cb6a4337d3712c06be09c205c17a789d87be5b7c036834adc675ce31a"},"schema_version":"1.0"},"canonical_sha256":"f4b0bc77b945f7450bfeeabc5371b6c807c36f0c4a9e518d1846d31e71d799d7","source":{"kind":"arxiv","id":"2303.12423","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.12423","created_at":"2026-07-05T05:54:37Z"},{"alias_kind":"arxiv_version","alias_value":"2303.12423v2","created_at":"2026-07-05T05:54:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.12423","created_at":"2026-07-05T05:54:37Z"},{"alias_kind":"pith_short_12","alias_value":"6SYLY55ZIX3U","created_at":"2026-07-05T05:54:37Z"},{"alias_kind":"pith_short_16","alias_value":"6SYLY55ZIX3UKC76","created_at":"2026-07-05T05:54:37Z"},{"alias_kind":"pith_short_8","alias_value":"6SYLY55Z","created_at":"2026-07-05T05:54:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6SYLY55ZIX3UKC765K6FG4NWZA","target":"record","payload":{"canonical_record":{"source":{"id":"2303.12423","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-22T09:49:53Z","cross_cats_sorted":[],"title_canon_sha256":"66426d4610b562fb7b30d36d598c30e77ec6da744f95a3af9d3c6b44587d4458","abstract_canon_sha256":"6754107cb6a4337d3712c06be09c205c17a789d87be5b7c036834adc675ce31a"},"schema_version":"1.0"},"canonical_sha256":"f4b0bc77b945f7450bfeeabc5371b6c807c36f0c4a9e518d1846d31e71d799d7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:37.494387Z","signature_b64":"/Ns84Ix2beSvYwdaZjssEntdMFsqoSKjXpek4R1M6dDg6JGBF+TMjXva079BqAcAjp2wp7d48YXrMe91BMqJBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4b0bc77b945f7450bfeeabc5371b6c807c36f0c4a9e518d1846d31e71d799d7","last_reissued_at":"2026-07-05T05:54:37.494012Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:37.494012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.12423","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":"2026-07-05T05:54:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m3fhB2jpgcEsF6QGFfhMP1Q/F3XLAHpWTx0Dq9EJZKQpAQC7AuUNGPnZYnA4XQzZnRg++RWPmrIM8lpeMiAoCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:53:43.207479Z"},"content_sha256":"9bca137eab83e9491c0c94664761d5fbc6ca0bc57ca12f9ca70c0917924376fd","schema_version":"1.0","event_id":"sha256:9bca137eab83e9491c0c94664761d5fbc6ca0bc57ca12f9ca70c0917924376fd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6SYLY55ZIX3UKC765K6FG4NWZA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text with Knowledge Graph Augmented Transformer for Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guang Chen, Libo Zhang, Longyin Wen, Tiejian Luo, Xin Gu, Yufei Wang","submitted_at":"2023-03-22T09:49:53Z","abstract_excerpt":"Video captioning aims to describe the content of videos using natural language. Although significant progress has been made, there is still much room to improve the performance for real-world applications, mainly due to the long-tail words challenge. In this paper, we propose a text with knowledge graph augmented transformer (TextKG) for video captioning. Notably, TextKG is a two-stream transformer, formed by the external stream and internal stream. The external stream is designed to absorb additional knowledge, which models the interactions between the additional knowledge, e.g., pre-built kn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.12423","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/2303.12423/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":"2026-07-05T05:54:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EOeOYDGlLnLeOkCAGHt/LJ7HI2bGtaEQWsgqSsFrG0Z2+qjM46n0RulzQQYP33Dht9tl3BeLKSVvh8HbFiS0Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:53:43.208388Z"},"content_sha256":"6db504958beb761d095e967a472b602fbf0b663e29fd809f215535ee8a561a31","schema_version":"1.0","event_id":"sha256:6db504958beb761d095e967a472b602fbf0b663e29fd809f215535ee8a561a31"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6SYLY55ZIX3UKC765K6FG4NWZA/bundle.json","state_url":"https://pith.science/pith/6SYLY55ZIX3UKC765K6FG4NWZA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6SYLY55ZIX3UKC765K6FG4NWZA/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":"2026-08-03T17:53:43Z","links":{"resolver":"https://pith.science/pith/6SYLY55ZIX3UKC765K6FG4NWZA","bundle":"https://pith.science/pith/6SYLY55ZIX3UKC765K6FG4NWZA/bundle.json","state":"https://pith.science/pith/6SYLY55ZIX3UKC765K6FG4NWZA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6SYLY55ZIX3UKC765K6FG4NWZA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6SYLY55ZIX3UKC765K6FG4NWZA","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":"6754107cb6a4337d3712c06be09c205c17a789d87be5b7c036834adc675ce31a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-22T09:49:53Z","title_canon_sha256":"66426d4610b562fb7b30d36d598c30e77ec6da744f95a3af9d3c6b44587d4458"},"schema_version":"1.0","source":{"id":"2303.12423","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.12423","created_at":"2026-07-05T05:54:37Z"},{"alias_kind":"arxiv_version","alias_value":"2303.12423v2","created_at":"2026-07-05T05:54:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.12423","created_at":"2026-07-05T05:54:37Z"},{"alias_kind":"pith_short_12","alias_value":"6SYLY55ZIX3U","created_at":"2026-07-05T05:54:37Z"},{"alias_kind":"pith_short_16","alias_value":"6SYLY55ZIX3UKC76","created_at":"2026-07-05T05:54:37Z"},{"alias_kind":"pith_short_8","alias_value":"6SYLY55Z","created_at":"2026-07-05T05:54:37Z"}],"graph_snapshots":[{"event_id":"sha256:6db504958beb761d095e967a472b602fbf0b663e29fd809f215535ee8a561a31","target":"graph","created_at":"2026-07-05T05:54:37Z","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/2303.12423/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video captioning aims to describe the content of videos using natural language. Although significant progress has been made, there is still much room to improve the performance for real-world applications, mainly due to the long-tail words challenge. In this paper, we propose a text with knowledge graph augmented transformer (TextKG) for video captioning. Notably, TextKG is a two-stream transformer, formed by the external stream and internal stream. The external stream is designed to absorb additional knowledge, which models the interactions between the additional knowledge, e.g., pre-built kn","authors_text":"Guang Chen, Libo Zhang, Longyin Wen, Tiejian Luo, Xin Gu, Yufei Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-22T09:49:53Z","title":"Text with Knowledge Graph Augmented Transformer for Video Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.12423","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":"sha256:9bca137eab83e9491c0c94664761d5fbc6ca0bc57ca12f9ca70c0917924376fd","target":"record","created_at":"2026-07-05T05:54:37Z","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":"6754107cb6a4337d3712c06be09c205c17a789d87be5b7c036834adc675ce31a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-22T09:49:53Z","title_canon_sha256":"66426d4610b562fb7b30d36d598c30e77ec6da744f95a3af9d3c6b44587d4458"},"schema_version":"1.0","source":{"id":"2303.12423","kind":"arxiv","version":2}},"canonical_sha256":"f4b0bc77b945f7450bfeeabc5371b6c807c36f0c4a9e518d1846d31e71d799d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4b0bc77b945f7450bfeeabc5371b6c807c36f0c4a9e518d1846d31e71d799d7","first_computed_at":"2026-07-05T05:54:37.494012Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:54:37.494012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/Ns84Ix2beSvYwdaZjssEntdMFsqoSKjXpek4R1M6dDg6JGBF+TMjXva079BqAcAjp2wp7d48YXrMe91BMqJBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:54:37.494387Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.12423","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9bca137eab83e9491c0c94664761d5fbc6ca0bc57ca12f9ca70c0917924376fd","sha256:6db504958beb761d095e967a472b602fbf0b663e29fd809f215535ee8a561a31"],"state_sha256":"2c07237d3bf6c511652e46b9ce9ef5688594a6e7b3e0087365d28773de361336"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZyH3qs+jDWLLlt6X+ocdOk0lZ5MuIoIOQy0RhQPvVo9ugUqj270HrAqJ5AVFQ31wKkaP1UdPJA13/NutsvImCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:53:43.214068Z","bundle_sha256":"f2d630370df651f283f4b6bf1fe701bbd97ae0f1d9de1a3c6d55d1daff422a93"}}