{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:7C4ZBCOVQRGUXPZHS3B22N4UTV","short_pith_number":"pith:7C4ZBCOV","schema_version":"1.0","canonical_sha256":"f8b99089d5844d4bbf2796c3ad37949d6db117af0fc95f69961173233a490047","source":{"kind":"arxiv","id":"1805.08191","version":3},"attestation_state":"computed","paper":{"title":"Hierarchically Structured Reinforcement Learning for Topically Coherent Visual Story Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Asli Celikyilmaz, Dapeng Wu, Jianfeng Wang, Qiuyuan Huang, Xiaodong He, Zhe Gan","submitted_at":"2018-05-21T17:23:31Z","abstract_excerpt":"We propose a hierarchically structured reinforcement learning approach to address the challenges of planning for generating coherent multi-sentence stories for the visual storytelling task. Within our framework, the task of generating a story given a sequence of images is divided across a two-level hierarchical decoder. The high-level decoder constructs a plan by generating a semantic concept (i.e., topic) for each image in sequence. The low-level decoder generates a sentence for each image using a semantic compositional network, which effectively grounds the sentence generation conditioned on"},"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":"1805.08191","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-21T17:23:31Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"title_canon_sha256":"b5402adfa144262f1cd87c90e50f500e6cfe38954759383996074fd3e27d1823","abstract_canon_sha256":"d7570409e3c26cfa8a39824b678f1f9f9850096dab0e402b74618de6a33b39d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:05.331895Z","signature_b64":"H3FcB/s6XiH0Hka1VZFIMNBs+zGaFZZZtGwqVk7/wwNGudB6HzA9D7p+pGnDhucfqTNWoDAD1L4SrG98y+cABg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8b99089d5844d4bbf2796c3ad37949d6db117af0fc95f69961173233a490047","last_reissued_at":"2026-05-17T23:56:05.331392Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:05.331392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchically Structured Reinforcement Learning for Topically Coherent Visual Story Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Asli Celikyilmaz, Dapeng Wu, Jianfeng Wang, Qiuyuan Huang, Xiaodong He, Zhe Gan","submitted_at":"2018-05-21T17:23:31Z","abstract_excerpt":"We propose a hierarchically structured reinforcement learning approach to address the challenges of planning for generating coherent multi-sentence stories for the visual storytelling task. Within our framework, the task of generating a story given a sequence of images is divided across a two-level hierarchical decoder. The high-level decoder constructs a plan by generating a semantic concept (i.e., topic) for each image in sequence. The low-level decoder generates a sentence for each image using a semantic compositional network, which effectively grounds the sentence generation conditioned on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08191","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1805.08191","created_at":"2026-05-17T23:56:05.331468+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.08191v3","created_at":"2026-05-17T23:56:05.331468+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08191","created_at":"2026-05-17T23:56:05.331468+00:00"},{"alias_kind":"pith_short_12","alias_value":"7C4ZBCOVQRGU","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"7C4ZBCOVQRGUXPZH","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"7C4ZBCOV","created_at":"2026-05-18T12:32:11.075285+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.08259","citing_title":"WriterForcing: Generating more interesting story endings","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7C4ZBCOVQRGUXPZHS3B22N4UTV","json":"https://pith.science/pith/7C4ZBCOVQRGUXPZHS3B22N4UTV.json","graph_json":"https://pith.science/api/pith-number/7C4ZBCOVQRGUXPZHS3B22N4UTV/graph.json","events_json":"https://pith.science/api/pith-number/7C4ZBCOVQRGUXPZHS3B22N4UTV/events.json","paper":"https://pith.science/paper/7C4ZBCOV"},"agent_actions":{"view_html":"https://pith.science/pith/7C4ZBCOVQRGUXPZHS3B22N4UTV","download_json":"https://pith.science/pith/7C4ZBCOVQRGUXPZHS3B22N4UTV.json","view_paper":"https://pith.science/paper/7C4ZBCOV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.08191&json=true","fetch_graph":"https://pith.science/api/pith-number/7C4ZBCOVQRGUXPZHS3B22N4UTV/graph.json","fetch_events":"https://pith.science/api/pith-number/7C4ZBCOVQRGUXPZHS3B22N4UTV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7C4ZBCOVQRGUXPZHS3B22N4UTV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7C4ZBCOVQRGUXPZHS3B22N4UTV/action/storage_attestation","attest_author":"https://pith.science/pith/7C4ZBCOVQRGUXPZHS3B22N4UTV/action/author_attestation","sign_citation":"https://pith.science/pith/7C4ZBCOVQRGUXPZHS3B22N4UTV/action/citation_signature","submit_replication":"https://pith.science/pith/7C4ZBCOVQRGUXPZHS3B22N4UTV/action/replication_record"}},"created_at":"2026-05-17T23:56:05.331468+00:00","updated_at":"2026-05-17T23:56:05.331468+00:00"}