{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:OBHA6QBCFBSVPPWZMJJXAZCQ76","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":"58186d83189a37f86b77f19d935bb2111f2d2caf30a9b3d819cd232a6a5eff1b","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-03T18:07:28Z","title_canon_sha256":"2abbbfb9c33d7bc065fcd75cf07ddf8a3c78cfbb0a44953195d239dafa60a2b7"},"schema_version":"1.0","source":{"id":"2012.02128","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.02128","created_at":"2026-07-05T01:56:53Z"},{"alias_kind":"arxiv_version","alias_value":"2012.02128v1","created_at":"2026-07-05T01:56:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02128","created_at":"2026-07-05T01:56:53Z"},{"alias_kind":"pith_short_12","alias_value":"OBHA6QBCFBSV","created_at":"2026-07-05T01:56:53Z"},{"alias_kind":"pith_short_16","alias_value":"OBHA6QBCFBSVPPWZ","created_at":"2026-07-05T01:56:53Z"},{"alias_kind":"pith_short_8","alias_value":"OBHA6QBC","created_at":"2026-07-05T01:56:53Z"}],"graph_snapshots":[{"event_id":"sha256:319d21f3fa23dd32fa65bd04d54d4a89f12a398447c489c1d863193613e35756","target":"graph","created_at":"2026-07-05T01:56:53Z","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/2012.02128/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Frank Guerin, Jing Su, Mian Zhou, QingYun Dai","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-03T18:07:28Z","title":"BERT-hLSTMs: BERT and Hierarchical LSTMs for Visual Storytelling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.02128","kind":"arxiv","version":1},"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:bf46132cd4174cf2c9ac746f097738432ed8bf2e0500cb1bfb779b3dcf051752","target":"record","created_at":"2026-07-05T01:56:53Z","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":"58186d83189a37f86b77f19d935bb2111f2d2caf30a9b3d819cd232a6a5eff1b","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-03T18:07:28Z","title_canon_sha256":"2abbbfb9c33d7bc065fcd75cf07ddf8a3c78cfbb0a44953195d239dafa60a2b7"},"schema_version":"1.0","source":{"id":"2012.02128","kind":"arxiv","version":1}},"canonical_sha256":"704e0f4022286557bed96253706450ffad0ea526fde826ba087754feb23278a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"704e0f4022286557bed96253706450ffad0ea526fde826ba087754feb23278a0","first_computed_at":"2026-07-05T01:56:53.454898Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:56:53.454898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6lGRFIFqy7g9NDx1pGdcwF1Phm+sRr7HET3+gK3UDA0p6L+pxQXHHF71vtH74NQ24SR0ZdWEWi4z5w6UxD8HDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:56:53.455234Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.02128","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf46132cd4174cf2c9ac746f097738432ed8bf2e0500cb1bfb779b3dcf051752","sha256:319d21f3fa23dd32fa65bd04d54d4a89f12a398447c489c1d863193613e35756"],"state_sha256":"ea37270543c72731e08cf4f339b2736a7ecd0bef7b2416e95b32250e3edea74d"}