{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GRE5F4TWOSXQTQZASUHCZ4ITCK","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":"29f296fa9f2126eb63914f73fb4f7fa08956038ff1c5d606d6f4f72ed91cb872","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-10T06:55:39Z","title_canon_sha256":"51fe508569c8da6b2102af1227d3de97d7d8294c1d53c05b6792522fb51057b7"},"schema_version":"1.0","source":{"id":"2105.04143","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.04143","created_at":"2026-07-05T04:43:17Z"},{"alias_kind":"arxiv_version","alias_value":"2105.04143v2","created_at":"2026-07-05T04:43:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.04143","created_at":"2026-07-05T04:43:17Z"},{"alias_kind":"pith_short_12","alias_value":"GRE5F4TWOSXQ","created_at":"2026-07-05T04:43:17Z"},{"alias_kind":"pith_short_16","alias_value":"GRE5F4TWOSXQTQZA","created_at":"2026-07-05T04:43:17Z"},{"alias_kind":"pith_short_8","alias_value":"GRE5F4TW","created_at":"2026-07-05T04:43:17Z"}],"graph_snapshots":[{"event_id":"sha256:7df1ae98545879e4941f14d3f3447d7b7f7134b13660f7ff9ae632cbd9a91ea7","target":"graph","created_at":"2026-07-05T04:43:17Z","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/2105.04143/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Observing a set of images and their corresponding paragraph-captions, a challenging task is to learn how to produce a semantically coherent paragraph to describe the visual content of an image. Inspired by recent successes in integrating semantic topics into this task, this paper develops a plug-and-play hierarchical-topic-guided image paragraph generation framework, which couples a visual extractor with a deep topic model to guide the learning of a language model. To capture the correlations between the image and text at multiple levels of abstraction and learn the semantic topics from images","authors_text":"Bo Chen, Dandan Guo, Mingyuan Zhou, Ruiying Lu, Zequn Zeng","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-10T06:55:39Z","title":"Matching Visual Features to Hierarchical Semantic Topics for Image Paragraph Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.04143","kind":"arxiv","version":2},"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:c074c58f94806e57f91a5c456e5611d4cb97461f8ae246ebdedc35248799a745","target":"record","created_at":"2026-07-05T04:43:17Z","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":"29f296fa9f2126eb63914f73fb4f7fa08956038ff1c5d606d6f4f72ed91cb872","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-10T06:55:39Z","title_canon_sha256":"51fe508569c8da6b2102af1227d3de97d7d8294c1d53c05b6792522fb51057b7"},"schema_version":"1.0","source":{"id":"2105.04143","kind":"arxiv","version":2}},"canonical_sha256":"3449d2f27674af09c320950e2cf1131288e679e20b7f59491421c5d9d9f1747a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3449d2f27674af09c320950e2cf1131288e679e20b7f59491421c5d9d9f1747a","first_computed_at":"2026-07-05T04:43:17.992038Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:43:17.992038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8o22R+TNPWuDJls87m9cOEijTZhyXazG7NfMbT+pdJxItzax/5z3sa6XUXN6qmfJ4CmjwgE7taPCaX9uql4pAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:43:17.992408Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.04143","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c074c58f94806e57f91a5c456e5611d4cb97461f8ae246ebdedc35248799a745","sha256:7df1ae98545879e4941f14d3f3447d7b7f7134b13660f7ff9ae632cbd9a91ea7"],"state_sha256":"5ae5772d3e945e1b12716798e5456d7daa1687fd923ed2187c22451bac791c7e"}