{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SFS3YO37NL6VI2E5C7CWPFYPGB","short_pith_number":"pith:SFS3YO37","schema_version":"1.0","canonical_sha256":"9165bc3b7f6afd54689d17c567970f30792b0939f406271de686bf7e3d62743f","source":{"kind":"arxiv","id":"1908.00169","version":2},"attestation_state":"computed","paper":{"title":"Curiosity-driven Reinforcement Learning for Diverse Visual Paragraph Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingjing Li, Yadan Luo, Yang Yang, Zheng Zhang, Zi Huang, Ziwei Wang","submitted_at":"2019-08-01T01:33:28Z","abstract_excerpt":"Visual paragraph generation aims to automatically describe a given image from different perspectives and organize sentences in a coherent way. In this paper, we address three critical challenges for this task in a reinforcement learning setting: the mode collapse, the delayed feedback, and the time-consuming warm-up for policy networks. Generally, we propose a novel Curiosity-driven Reinforcement Learning (CRL) framework to jointly enhance the diversity and accuracy of the generated paragraphs. First, by modeling the paragraph captioning as a long-term decision-making process and measuring the"},"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":"1908.00169","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-08-01T01:33:28Z","cross_cats_sorted":[],"title_canon_sha256":"5804d2e593e1b15ea16ef50169a4cd5dd19a5f8616e76c8862abd595c96818ce","abstract_canon_sha256":"feed494567908660ee404d48b81636d0462e6ed8bc41df57716f7d5d12a2cc27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:00:27.490039Z","signature_b64":"H0x0z4rrx3W33zne4yrJhERC9C0LE3euHGBvXzcypuQQ9U2rZnqn5nq/Fqmh/FhAr3CFkqCdya4lzVkzmQ+4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9165bc3b7f6afd54689d17c567970f30792b0939f406271de686bf7e3d62743f","last_reissued_at":"2026-07-05T00:00:27.489560Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:00:27.489560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Curiosity-driven Reinforcement Learning for Diverse Visual Paragraph Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingjing Li, Yadan Luo, Yang Yang, Zheng Zhang, Zi Huang, Ziwei Wang","submitted_at":"2019-08-01T01:33:28Z","abstract_excerpt":"Visual paragraph generation aims to automatically describe a given image from different perspectives and organize sentences in a coherent way. In this paper, we address three critical challenges for this task in a reinforcement learning setting: the mode collapse, the delayed feedback, and the time-consuming warm-up for policy networks. Generally, we propose a novel Curiosity-driven Reinforcement Learning (CRL) framework to jointly enhance the diversity and accuracy of the generated paragraphs. First, by modeling the paragraph captioning as a long-term decision-making process and measuring the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.00169","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/1908.00169/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":"1908.00169","created_at":"2026-07-05T00:00:27.489610+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.00169v2","created_at":"2026-07-05T00:00:27.489610+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.00169","created_at":"2026-07-05T00:00:27.489610+00:00"},{"alias_kind":"pith_short_12","alias_value":"SFS3YO37NL6V","created_at":"2026-07-05T00:00:27.489610+00:00"},{"alias_kind":"pith_short_16","alias_value":"SFS3YO37NL6VI2E5","created_at":"2026-07-05T00:00:27.489610+00:00"},{"alias_kind":"pith_short_8","alias_value":"SFS3YO37","created_at":"2026-07-05T00:00:27.489610+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/SFS3YO37NL6VI2E5C7CWPFYPGB","json":"https://pith.science/pith/SFS3YO37NL6VI2E5C7CWPFYPGB.json","graph_json":"https://pith.science/api/pith-number/SFS3YO37NL6VI2E5C7CWPFYPGB/graph.json","events_json":"https://pith.science/api/pith-number/SFS3YO37NL6VI2E5C7CWPFYPGB/events.json","paper":"https://pith.science/paper/SFS3YO37"},"agent_actions":{"view_html":"https://pith.science/pith/SFS3YO37NL6VI2E5C7CWPFYPGB","download_json":"https://pith.science/pith/SFS3YO37NL6VI2E5C7CWPFYPGB.json","view_paper":"https://pith.science/paper/SFS3YO37","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.00169&json=true","fetch_graph":"https://pith.science/api/pith-number/SFS3YO37NL6VI2E5C7CWPFYPGB/graph.json","fetch_events":"https://pith.science/api/pith-number/SFS3YO37NL6VI2E5C7CWPFYPGB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SFS3YO37NL6VI2E5C7CWPFYPGB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SFS3YO37NL6VI2E5C7CWPFYPGB/action/storage_attestation","attest_author":"https://pith.science/pith/SFS3YO37NL6VI2E5C7CWPFYPGB/action/author_attestation","sign_citation":"https://pith.science/pith/SFS3YO37NL6VI2E5C7CWPFYPGB/action/citation_signature","submit_replication":"https://pith.science/pith/SFS3YO37NL6VI2E5C7CWPFYPGB/action/replication_record"}},"created_at":"2026-07-05T00:00:27.489610+00:00","updated_at":"2026-07-05T00:00:27.489610+00:00"}