{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:OBHA6QBCFBSVPPWZMJJXAZCQ76","short_pith_number":"pith:OBHA6QBC","schema_version":"1.0","canonical_sha256":"704e0f4022286557bed96253706450ffad0ea526fde826ba087754feb23278a0","source":{"kind":"arxiv","id":"2012.02128","version":1},"attestation_state":"computed","paper":{"title":"BERT-hLSTMs: BERT and Hierarchical LSTMs for Visual Storytelling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Frank Guerin, Jing Su, Mian Zhou, QingYun Dai","submitted_at":"2020-12-03T18:07:28Z","abstract_excerpt":"Visual storytelling is a creative and challenging task, aiming to automatically generate a story-like description for a sequence of images. The descriptions generated by previous visual storytelling approaches lack coherence because they use word-level sequence generation methods and do not adequately consider sentence-level dependencies. To tackle this problem, we propose a novel hierarchical visual storytelling framework which separately models sentence-level and word-level semantics. We use the transformer-based BERT to obtain embeddings for sentences and words. We then employ a hierarchica"},"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":"2012.02128","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-03T18:07:28Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2abbbfb9c33d7bc065fcd75cf07ddf8a3c78cfbb0a44953195d239dafa60a2b7","abstract_canon_sha256":"58186d83189a37f86b77f19d935bb2111f2d2caf30a9b3d819cd232a6a5eff1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:56:53.455234Z","signature_b64":"6lGRFIFqy7g9NDx1pGdcwF1Phm+sRr7HET3+gK3UDA0p6L+pxQXHHF71vtH74NQ24SR0ZdWEWi4z5w6UxD8HDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"704e0f4022286557bed96253706450ffad0ea526fde826ba087754feb23278a0","last_reissued_at":"2026-07-05T01:56:53.454898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:56:53.454898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BERT-hLSTMs: BERT and Hierarchical LSTMs for Visual Storytelling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Frank Guerin, Jing Su, Mian Zhou, QingYun Dai","submitted_at":"2020-12-03T18:07:28Z","abstract_excerpt":"Visual storytelling is a creative and challenging task, aiming to automatically generate a story-like description for a sequence of images. The descriptions generated by previous visual storytelling approaches lack coherence because they use word-level sequence generation methods and do not adequately consider sentence-level dependencies. To tackle this problem, we propose a novel hierarchical visual storytelling framework which separately models sentence-level and word-level semantics. We use the transformer-based BERT to obtain embeddings for sentences and words. We then employ a hierarchica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.02128","kind":"arxiv","version":1},"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/2012.02128/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":"2012.02128","created_at":"2026-07-05T01:56:53.454952+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.02128v1","created_at":"2026-07-05T01:56:53.454952+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02128","created_at":"2026-07-05T01:56:53.454952+00:00"},{"alias_kind":"pith_short_12","alias_value":"OBHA6QBCFBSV","created_at":"2026-07-05T01:56:53.454952+00:00"},{"alias_kind":"pith_short_16","alias_value":"OBHA6QBCFBSVPPWZ","created_at":"2026-07-05T01:56:53.454952+00:00"},{"alias_kind":"pith_short_8","alias_value":"OBHA6QBC","created_at":"2026-07-05T01:56:53.454952+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.14045","citing_title":"From Image Captioning to Visual Storytelling","ref_index":68,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OBHA6QBCFBSVPPWZMJJXAZCQ76","json":"https://pith.science/pith/OBHA6QBCFBSVPPWZMJJXAZCQ76.json","graph_json":"https://pith.science/api/pith-number/OBHA6QBCFBSVPPWZMJJXAZCQ76/graph.json","events_json":"https://pith.science/api/pith-number/OBHA6QBCFBSVPPWZMJJXAZCQ76/events.json","paper":"https://pith.science/paper/OBHA6QBC"},"agent_actions":{"view_html":"https://pith.science/pith/OBHA6QBCFBSVPPWZMJJXAZCQ76","download_json":"https://pith.science/pith/OBHA6QBCFBSVPPWZMJJXAZCQ76.json","view_paper":"https://pith.science/paper/OBHA6QBC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.02128&json=true","fetch_graph":"https://pith.science/api/pith-number/OBHA6QBCFBSVPPWZMJJXAZCQ76/graph.json","fetch_events":"https://pith.science/api/pith-number/OBHA6QBCFBSVPPWZMJJXAZCQ76/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OBHA6QBCFBSVPPWZMJJXAZCQ76/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OBHA6QBCFBSVPPWZMJJXAZCQ76/action/storage_attestation","attest_author":"https://pith.science/pith/OBHA6QBCFBSVPPWZMJJXAZCQ76/action/author_attestation","sign_citation":"https://pith.science/pith/OBHA6QBCFBSVPPWZMJJXAZCQ76/action/citation_signature","submit_replication":"https://pith.science/pith/OBHA6QBCFBSVPPWZMJJXAZCQ76/action/replication_record"}},"created_at":"2026-07-05T01:56:53.454952+00:00","updated_at":"2026-07-05T01:56:53.454952+00:00"}