{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WIETTVMBQE7UVI6GFMVKVTBBRN","short_pith_number":"pith:WIETTVMB","schema_version":"1.0","canonical_sha256":"b20939d581813f4aa3c62b2aaacc218b73ef9dcc8e798114f3c4c5d8af0c380c","source":{"kind":"arxiv","id":"2212.13563","version":2},"attestation_state":"computed","paper":{"title":"Noise-aware Learning from Web-crawled Image-Text Data for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Byungseok Roh, Jonghwan Mun, Sungjun Lee, Wooyoung Kang","submitted_at":"2022-12-27T17:33:40Z","abstract_excerpt":"Image captioning is one of the straightforward tasks that can take advantage of large-scale web-crawled data which provides rich knowledge about the visual world for a captioning model. However, since web-crawled data contains image-text pairs that are aligned at different levels, the inherent noises (e.g., misaligned pairs) make it difficult to learn a precise captioning model. While the filtering strategy can effectively remove noisy data, it leads to a decrease in learnable knowledge and sometimes brings about a new problem of data deficiency. To take the best of both worlds, we propose a N"},"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":"2212.13563","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-27T17:33:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d4d8719b6c45d48050ce64fa7af0dee61bc7096083cfabdf1f1b4a88d01e0beb","abstract_canon_sha256":"e7088884bfe27e844f4d7c68329a488a7fd31adfa51c26ffbff871b065b73aa8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:36.858091Z","signature_b64":"q4UXpVT89FjdunM7EED1tZBMXBAmHkuwCcamT9k/11m2ERFAIWMd5PvPdSGoeDV9+DVy7YDGQzUbHkkkA1uIAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b20939d581813f4aa3c62b2aaacc218b73ef9dcc8e798114f3c4c5d8af0c380c","last_reissued_at":"2026-07-05T06:54:36.857639Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:36.857639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Noise-aware Learning from Web-crawled Image-Text Data for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Byungseok Roh, Jonghwan Mun, Sungjun Lee, Wooyoung Kang","submitted_at":"2022-12-27T17:33:40Z","abstract_excerpt":"Image captioning is one of the straightforward tasks that can take advantage of large-scale web-crawled data which provides rich knowledge about the visual world for a captioning model. However, since web-crawled data contains image-text pairs that are aligned at different levels, the inherent noises (e.g., misaligned pairs) make it difficult to learn a precise captioning model. While the filtering strategy can effectively remove noisy data, it leads to a decrease in learnable knowledge and sometimes brings about a new problem of data deficiency. To take the best of both worlds, we propose a N"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.13563","kind":"arxiv","version":2},"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/2212.13563/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":"2212.13563","created_at":"2026-07-05T06:54:36.857698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.13563v2","created_at":"2026-07-05T06:54:36.857698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.13563","created_at":"2026-07-05T06:54:36.857698+00:00"},{"alias_kind":"pith_short_12","alias_value":"WIETTVMBQE7U","created_at":"2026-07-05T06:54:36.857698+00:00"},{"alias_kind":"pith_short_16","alias_value":"WIETTVMBQE7UVI6G","created_at":"2026-07-05T06:54:36.857698+00:00"},{"alias_kind":"pith_short_8","alias_value":"WIETTVMB","created_at":"2026-07-05T06:54:36.857698+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/WIETTVMBQE7UVI6GFMVKVTBBRN","json":"https://pith.science/pith/WIETTVMBQE7UVI6GFMVKVTBBRN.json","graph_json":"https://pith.science/api/pith-number/WIETTVMBQE7UVI6GFMVKVTBBRN/graph.json","events_json":"https://pith.science/api/pith-number/WIETTVMBQE7UVI6GFMVKVTBBRN/events.json","paper":"https://pith.science/paper/WIETTVMB"},"agent_actions":{"view_html":"https://pith.science/pith/WIETTVMBQE7UVI6GFMVKVTBBRN","download_json":"https://pith.science/pith/WIETTVMBQE7UVI6GFMVKVTBBRN.json","view_paper":"https://pith.science/paper/WIETTVMB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.13563&json=true","fetch_graph":"https://pith.science/api/pith-number/WIETTVMBQE7UVI6GFMVKVTBBRN/graph.json","fetch_events":"https://pith.science/api/pith-number/WIETTVMBQE7UVI6GFMVKVTBBRN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WIETTVMBQE7UVI6GFMVKVTBBRN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WIETTVMBQE7UVI6GFMVKVTBBRN/action/storage_attestation","attest_author":"https://pith.science/pith/WIETTVMBQE7UVI6GFMVKVTBBRN/action/author_attestation","sign_citation":"https://pith.science/pith/WIETTVMBQE7UVI6GFMVKVTBBRN/action/citation_signature","submit_replication":"https://pith.science/pith/WIETTVMBQE7UVI6GFMVKVTBBRN/action/replication_record"}},"created_at":"2026-07-05T06:54:36.857698+00:00","updated_at":"2026-07-05T06:54:36.857698+00:00"}