{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:XLACN233SBWALU6FDCSGLOAU2Y","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":"ccd6cca1a0ecab7cf9ceb8807e8e2ca096ffbb88706f2957e976ffd69c345010","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-09T15:18:21Z","title_canon_sha256":"f6c7958dc94f771b9836c900af5e57df3a320cfdf7b93a2040efc1d81c59ef33"},"schema_version":"1.0","source":{"id":"1909.03918","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.03918","created_at":"2026-07-05T00:03:18Z"},{"alias_kind":"arxiv_version","alias_value":"1909.03918v2","created_at":"2026-07-05T00:03:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.03918","created_at":"2026-07-05T00:03:18Z"},{"alias_kind":"pith_short_12","alias_value":"XLACN233SBWA","created_at":"2026-07-05T00:03:18Z"},{"alias_kind":"pith_short_16","alias_value":"XLACN233SBWALU6F","created_at":"2026-07-05T00:03:18Z"},{"alias_kind":"pith_short_8","alias_value":"XLACN233","created_at":"2026-07-05T00:03:18Z"}],"graph_snapshots":[{"event_id":"sha256:1f4f06e3ae98d983d5e5ed29cd7d4ad03beca700a6c9dc612d8d7d6869d857c2","target":"graph","created_at":"2026-07-05T00:03:18Z","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/1909.03918/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It is always well believed that parsing an image into constituent visual patterns would be helpful for understanding and representing an image. Nevertheless, there has not been evidence in support of the idea on describing an image with a natural-language utterance. In this paper, we introduce a new design to model a hierarchy from instance level (segmentation), region level (detection) to the whole image to delve into a thorough image understanding for captioning. Specifically, we present a HIerarchy Parsing (HIP) architecture that novelly integrates hierarchical structure into image encoder.","authors_text":"Tao Mei, Ting Yao, Yehao Li, Yingwei Pan","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-09T15:18:21Z","title":"Hierarchy Parsing for Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.03918","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":"sha256:59c346f326dc6743447bf75daedfc77dd6b9779b356b742ba78204f5401067de","target":"record","created_at":"2026-07-05T00:03:18Z","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":"ccd6cca1a0ecab7cf9ceb8807e8e2ca096ffbb88706f2957e976ffd69c345010","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-09T15:18:21Z","title_canon_sha256":"f6c7958dc94f771b9836c900af5e57df3a320cfdf7b93a2040efc1d81c59ef33"},"schema_version":"1.0","source":{"id":"1909.03918","kind":"arxiv","version":2}},"canonical_sha256":"bac026eb7b906c05d3c518a465b814d63330052af61b4cb26a700907b16b6da0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bac026eb7b906c05d3c518a465b814d63330052af61b4cb26a700907b16b6da0","first_computed_at":"2026-07-05T00:03:18.311690Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:03:18.311690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MihVVvNjt8bUEHSD7XqCxcPXFoYmcK9NPVlpYLC8OFW06oqgYpbI+4qYknrlPJ8qR87RoCadWJDNLbzLKbmQDA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:03:18.312693Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.03918","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59c346f326dc6743447bf75daedfc77dd6b9779b356b742ba78204f5401067de","sha256:1f4f06e3ae98d983d5e5ed29cd7d4ad03beca700a6c9dc612d8d7d6869d857c2"],"state_sha256":"31e23ff5d57e769beda7af647ce9e2d00e40f8c09ae0e56de594ae04392813dd"}