{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CYAYYXLIR4TDRDSRADQ2KNATZR","short_pith_number":"pith:CYAYYXLI","schema_version":"1.0","canonical_sha256":"16018c5d688f26388e5100e1a53413cc6182f0b7cc73395aa8d30a1a77c04e4b","source":{"kind":"arxiv","id":"2205.14458","version":2},"attestation_state":"computed","paper":{"title":"Variational Transformer: A Framework Beyond the Trade-off between Accuracy and Diversity for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Lianghua He, Longzhen Yang, Yihang Liu, Yitao Peng","submitted_at":"2022-05-28T15:29:14Z","abstract_excerpt":"Accuracy and Diversity are two essential metrizable manifestations in generating natural and semantically correct captions. Many efforts have been made to enhance one of them with another decayed due to the trade-off gap. In this work, we will show that the inferior standard of accuracy draws from human annotations (leave-one-out) are not appropriate for machine-generated captions. To improve diversity with a solid accuracy performance, we exploited a novel Variational Transformer framework. By introducing the \"Invisible Information Prior\" and the \"Auto-selectable GMM\", we instruct the encoder"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2205.14458","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-28T15:29:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f1d0c2302ce4c60564e524399ab0b21d25086ad71ae9f8bfbb2526a8249ab18c","abstract_canon_sha256":"af879fec59df06d2c20fc819cdb21a3f9d715ef127d5070b0f7baaf11d127ecf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:59:41.106244Z","signature_b64":"mAFp+5K3+GSD4Z9Ci6K7sNK9h+QRJ04+YY8XLD7xvJFmB7D4ljQUueq1jLsJYuaV56WS/12tYlnQLM371lnnBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16018c5d688f26388e5100e1a53413cc6182f0b7cc73395aa8d30a1a77c04e4b","last_reissued_at":"2026-07-05T04:59:41.105746Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:59:41.105746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational Transformer: A Framework Beyond the Trade-off between Accuracy and Diversity for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Lianghua He, Longzhen Yang, Yihang Liu, Yitao Peng","submitted_at":"2022-05-28T15:29:14Z","abstract_excerpt":"Accuracy and Diversity are two essential metrizable manifestations in generating natural and semantically correct captions. Many efforts have been made to enhance one of them with another decayed due to the trade-off gap. In this work, we will show that the inferior standard of accuracy draws from human annotations (leave-one-out) are not appropriate for machine-generated captions. To improve diversity with a solid accuracy performance, we exploited a novel Variational Transformer framework. By introducing the \"Invisible Information Prior\" and the \"Auto-selectable GMM\", we instruct the encoder"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14458","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/2205.14458/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2205.14458","created_at":"2026-07-05T04:59:41.105805+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.14458v2","created_at":"2026-07-05T04:59:41.105805+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14458","created_at":"2026-07-05T04:59:41.105805+00:00"},{"alias_kind":"pith_short_12","alias_value":"CYAYYXLIR4TD","created_at":"2026-07-05T04:59:41.105805+00:00"},{"alias_kind":"pith_short_16","alias_value":"CYAYYXLIR4TDRDSR","created_at":"2026-07-05T04:59:41.105805+00:00"},{"alias_kind":"pith_short_8","alias_value":"CYAYYXLI","created_at":"2026-07-05T04:59:41.105805+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CYAYYXLIR4TDRDSRADQ2KNATZR","json":"https://pith.science/pith/CYAYYXLIR4TDRDSRADQ2KNATZR.json","graph_json":"https://pith.science/api/pith-number/CYAYYXLIR4TDRDSRADQ2KNATZR/graph.json","events_json":"https://pith.science/api/pith-number/CYAYYXLIR4TDRDSRADQ2KNATZR/events.json","paper":"https://pith.science/paper/CYAYYXLI"},"agent_actions":{"view_html":"https://pith.science/pith/CYAYYXLIR4TDRDSRADQ2KNATZR","download_json":"https://pith.science/pith/CYAYYXLIR4TDRDSRADQ2KNATZR.json","view_paper":"https://pith.science/paper/CYAYYXLI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.14458&json=true","fetch_graph":"https://pith.science/api/pith-number/CYAYYXLIR4TDRDSRADQ2KNATZR/graph.json","fetch_events":"https://pith.science/api/pith-number/CYAYYXLIR4TDRDSRADQ2KNATZR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CYAYYXLIR4TDRDSRADQ2KNATZR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CYAYYXLIR4TDRDSRADQ2KNATZR/action/storage_attestation","attest_author":"https://pith.science/pith/CYAYYXLIR4TDRDSRADQ2KNATZR/action/author_attestation","sign_citation":"https://pith.science/pith/CYAYYXLIR4TDRDSRADQ2KNATZR/action/citation_signature","submit_replication":"https://pith.science/pith/CYAYYXLIR4TDRDSRADQ2KNATZR/action/replication_record"}},"created_at":"2026-07-05T04:59:41.105805+00:00","updated_at":"2026-07-05T04:59:41.105805+00:00"}