{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:CDUAE5CSFAK36YVLRLC3W2XCUF","short_pith_number":"pith:CDUAE5CS","canonical_record":{"source":{"id":"2206.06930","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-14T15:51:14Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"title_canon_sha256":"f9d427be42006ff3647e3f3eec5d4e36c62e04219bd7d53f060d88075717d610","abstract_canon_sha256":"d580ebf976abe0afe9ebe75f9107d453da204b640bcf4cec864cdc7973da4015"},"schema_version":"1.0"},"canonical_sha256":"10e80274522815bf62ab8ac5bb6ae2a16b56968aa262357b52e31854528ac1e1","source":{"kind":"arxiv","id":"2206.06930","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:CDUAE5CSFAK36YVLRLC3W2XCUF","target":"record","payload":{"canonical_record":{"source":{"id":"2206.06930","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-14T15:51:14Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"title_canon_sha256":"f9d427be42006ff3647e3f3eec5d4e36c62e04219bd7d53f060d88075717d610","abstract_canon_sha256":"d580ebf976abe0afe9ebe75f9107d453da204b640bcf4cec864cdc7973da4015"},"schema_version":"1.0"},"canonical_sha256":"10e80274522815bf62ab8ac5bb6ae2a16b56968aa262357b52e31854528ac1e1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:31:47.290679Z","signature_b64":"ljOFWDbEJwTocKV8EYkjo7hsh0wQOcyIV0YRknqi2w7JoBDqVRV/BlUnfLQJSuXgGpMMDuMfjWmqQp7n+B1eAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10e80274522815bf62ab8ac5bb6ae2a16b56968aa262357b52e31854528ac1e1","last_reissued_at":"2026-07-05T04:31:47.290188Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:31:47.290188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.06930","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:31:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kO5kxTmTQzVwZHiHp175HjqK3LJWhG6RbMZOc3K/Ew70UnL7xVdXzMyK7xTzMFy6o6Xky4UGi/I2Sp5hha71AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T04:14:28.334962Z"},"content_sha256":"b8f221e27c82096c9caa0b922f5f641fcddefa29d5183047b85be4ca6ebd242d","schema_version":"1.0","event_id":"sha256:b8f221e27c82096c9caa0b922f5f641fcddefa29d5183047b85be4ca6ebd242d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:CDUAE5CSFAK36YVLRLC3W2XCUF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Comprehending and Ordering Semantics for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Tao Mei, Ting Yao, Yehao Li, Yingwei Pan","submitted_at":"2022-06-14T15:51:14Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.06930","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/2206.06930/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:31:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uiNDeuHOyR4WcGUSKSxx1n9nbVnKfEusNmbEpk9rQ9V43PTYdWOXOs/k/UjLWLa4R8SvrXCwYrpzDozxHL3wAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T04:14:28.335464Z"},"content_sha256":"bb0a1262efa8b5dda5732ef520133fc28cdb5c60503a0cd014b60db4ceb078db","schema_version":"1.0","event_id":"sha256:bb0a1262efa8b5dda5732ef520133fc28cdb5c60503a0cd014b60db4ceb078db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CDUAE5CSFAK36YVLRLC3W2XCUF/bundle.json","state_url":"https://pith.science/pith/CDUAE5CSFAK36YVLRLC3W2XCUF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CDUAE5CSFAK36YVLRLC3W2XCUF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T04:14:28Z","links":{"resolver":"https://pith.science/pith/CDUAE5CSFAK36YVLRLC3W2XCUF","bundle":"https://pith.science/pith/CDUAE5CSFAK36YVLRLC3W2XCUF/bundle.json","state":"https://pith.science/pith/CDUAE5CSFAK36YVLRLC3W2XCUF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CDUAE5CSFAK36YVLRLC3W2XCUF/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s/tVAiI3VtiytqhJ2xD2ecRzSoFW0YfueGm35NuX86tQf1VEY/VWblCjHeniFksdv2v9N/kRkoJKKV4VHoYmDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T04:14:28.340642Z","bundle_sha256":"5ede409fb1a4d556e652a8c1d8daeaaf97a61cd6eeacdab88a3f502adc72f913"}}