{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CDUAE5CSFAK36YVLRLC3W2XCUF","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":"d580ebf976abe0afe9ebe75f9107d453da204b640bcf4cec864cdc7973da4015","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-14T15:51:14Z","title_canon_sha256":"f9d427be42006ff3647e3f3eec5d4e36c62e04219bd7d53f060d88075717d610"},"schema_version":"1.0","source":{"id":"2206.06930","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.06930","created_at":"2026-07-05T04:31:47Z"},{"alias_kind":"arxiv_version","alias_value":"2206.06930v1","created_at":"2026-07-05T04:31:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.06930","created_at":"2026-07-05T04:31:47Z"},{"alias_kind":"pith_short_12","alias_value":"CDUAE5CSFAK3","created_at":"2026-07-05T04:31:47Z"},{"alias_kind":"pith_short_16","alias_value":"CDUAE5CSFAK36YVL","created_at":"2026-07-05T04:31:47Z"},{"alias_kind":"pith_short_8","alias_value":"CDUAE5CS","created_at":"2026-07-05T04:31:47Z"}],"graph_snapshots":[{"event_id":"sha256:bb0a1262efa8b5dda5732ef520133fc28cdb5c60503a0cd014b60db4ceb078db","target":"graph","created_at":"2026-07-05T04:31:47Z","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/2206.06930/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Comprehending the rich semantics in an image and ordering them in linguistic order are essential to compose a visually-grounded and linguistically coherent description for image captioning. Modern techniques commonly capitalize on a pre-trained object detector/classifier to mine the semantics in an image, while leaving the inherent linguistic ordering of semantics under-exploited. In this paper, we propose a new recipe of Transformer-style structure, namely Comprehending and Ordering Semantics Networks (COS-Net), that novelly unifies an enriched semantic comprehending and a learnable semantic ","authors_text":"Tao Mei, Ting Yao, Yehao Li, Yingwei Pan","cross_cats":["cs.AI","cs.CL","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-14T15:51:14Z","title":"Comprehending and Ordering Semantics for Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.06930","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:b8f221e27c82096c9caa0b922f5f641fcddefa29d5183047b85be4ca6ebd242d","target":"record","created_at":"2026-07-05T04:31:47Z","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":"d580ebf976abe0afe9ebe75f9107d453da204b640bcf4cec864cdc7973da4015","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-14T15:51:14Z","title_canon_sha256":"f9d427be42006ff3647e3f3eec5d4e36c62e04219bd7d53f060d88075717d610"},"schema_version":"1.0","source":{"id":"2206.06930","kind":"arxiv","version":1}},"canonical_sha256":"10e80274522815bf62ab8ac5bb6ae2a16b56968aa262357b52e31854528ac1e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"10e80274522815bf62ab8ac5bb6ae2a16b56968aa262357b52e31854528ac1e1","first_computed_at":"2026-07-05T04:31:47.290188Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:31:47.290188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ljOFWDbEJwTocKV8EYkjo7hsh0wQOcyIV0YRknqi2w7JoBDqVRV/BlUnfLQJSuXgGpMMDuMfjWmqQp7n+B1eAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:31:47.290679Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.06930","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b8f221e27c82096c9caa0b922f5f641fcddefa29d5183047b85be4ca6ebd242d","sha256:bb0a1262efa8b5dda5732ef520133fc28cdb5c60503a0cd014b60db4ceb078db"],"state_sha256":"22c1fede404b787db5f14282e1c89209bde146026730de888decd23f63b9dbe0"}