{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FINFMEF2TV73THXZVK37PBEPNI","short_pith_number":"pith:FINFMEF2","schema_version":"1.0","canonical_sha256":"2a1a5610ba9d7fb99ef9aab7f7848f6a1da8170a7e0136c96821a7af663114ef","source":{"kind":"arxiv","id":"2307.14750","version":3},"attestation_state":"computed","paper":{"title":"Exploring Annotation-free Image Captioning with Retrieval-augmented Pseudo Sentence Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chaoyi Zhang, Dongnan Liu, Heng Wang, Weidong Cai, Zhiyuan Li","submitted_at":"2023-07-27T10:16:13Z","abstract_excerpt":"Recently, training an image captioner without annotated image-sentence pairs has gained traction. Previous methods have faced limitations due to either using mismatched corpora for inaccurate pseudo annotations or relying on resource-intensive pre-training. To alleviate these challenges, we propose a new strategy where the prior knowledge from large pre-trained models (LPMs) is distilled and leveraged as supervision, and a retrieval process is integrated to further reinforce its effectiveness. Specifically, we introduce Retrieval-augmented Pseudo Sentence Generation (RaPSG), which can efficien"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2307.14750","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-27T10:16:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2dfc32b8d81ed0eaee3b328c85aec5973a9779826f844d13545be5244c603789","abstract_canon_sha256":"7e0ab766b3e6c9bc2ebc7b6fd1d92e814139350a6764ef1835efb4f8b4968887"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:51.601415Z","signature_b64":"Q2VpiRCfrTlau/7pZWw4dkPTGJFP3n4MdfVqGuOVCoXmAnL1yHkP3KNjJ1/vbi71yIhfKMSnVRzb/BoivASmAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a1a5610ba9d7fb99ef9aab7f7848f6a1da8170a7e0136c96821a7af663114ef","last_reissued_at":"2026-07-05T09:19:51.600841Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:51.600841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Annotation-free Image Captioning with Retrieval-augmented Pseudo Sentence Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chaoyi Zhang, Dongnan Liu, Heng Wang, Weidong Cai, Zhiyuan Li","submitted_at":"2023-07-27T10:16:13Z","abstract_excerpt":"Recently, training an image captioner without annotated image-sentence pairs has gained traction. Previous methods have faced limitations due to either using mismatched corpora for inaccurate pseudo annotations or relying on resource-intensive pre-training. To alleviate these challenges, we propose a new strategy where the prior knowledge from large pre-trained models (LPMs) is distilled and leveraged as supervision, and a retrieval process is integrated to further reinforce its effectiveness. Specifically, we introduce Retrieval-augmented Pseudo Sentence Generation (RaPSG), which can efficien"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.14750","kind":"arxiv","version":3},"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/2307.14750/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2307.14750","created_at":"2026-07-05T09:19:51.600924+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.14750v3","created_at":"2026-07-05T09:19:51.600924+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.14750","created_at":"2026-07-05T09:19:51.600924+00:00"},{"alias_kind":"pith_short_12","alias_value":"FINFMEF2TV73","created_at":"2026-07-05T09:19:51.600924+00:00"},{"alias_kind":"pith_short_16","alias_value":"FINFMEF2TV73THXZ","created_at":"2026-07-05T09:19:51.600924+00:00"},{"alias_kind":"pith_short_8","alias_value":"FINFMEF2","created_at":"2026-07-05T09:19:51.600924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FINFMEF2TV73THXZVK37PBEPNI","json":"https://pith.science/pith/FINFMEF2TV73THXZVK37PBEPNI.json","graph_json":"https://pith.science/api/pith-number/FINFMEF2TV73THXZVK37PBEPNI/graph.json","events_json":"https://pith.science/api/pith-number/FINFMEF2TV73THXZVK37PBEPNI/events.json","paper":"https://pith.science/paper/FINFMEF2"},"agent_actions":{"view_html":"https://pith.science/pith/FINFMEF2TV73THXZVK37PBEPNI","download_json":"https://pith.science/pith/FINFMEF2TV73THXZVK37PBEPNI.json","view_paper":"https://pith.science/paper/FINFMEF2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.14750&json=true","fetch_graph":"https://pith.science/api/pith-number/FINFMEF2TV73THXZVK37PBEPNI/graph.json","fetch_events":"https://pith.science/api/pith-number/FINFMEF2TV73THXZVK37PBEPNI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FINFMEF2TV73THXZVK37PBEPNI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FINFMEF2TV73THXZVK37PBEPNI/action/storage_attestation","attest_author":"https://pith.science/pith/FINFMEF2TV73THXZVK37PBEPNI/action/author_attestation","sign_citation":"https://pith.science/pith/FINFMEF2TV73THXZVK37PBEPNI/action/citation_signature","submit_replication":"https://pith.science/pith/FINFMEF2TV73THXZVK37PBEPNI/action/replication_record"}},"created_at":"2026-07-05T09:19:51.600924+00:00","updated_at":"2026-07-05T09:19:51.600924+00:00"}