{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:G7E4ITHHK6QYDAQP2MGXTV7WKS","short_pith_number":"pith:G7E4ITHH","schema_version":"1.0","canonical_sha256":"37c9c44ce757a181820fd30d79d7f654b4d5d33b2049c1a12014d31707a59249","source":{"kind":"arxiv","id":"2207.11118","version":1},"attestation_state":"computed","paper":{"title":"Rethinking the Reference-based Distinctive Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Zhang, Jian Shao, Jun Xiao, Long Chen, Yangjun Mao, Zhihong Jiang, Zhimeng Zhang","submitted_at":"2022-07-22T14:49:54Z","abstract_excerpt":"Distinctive Image Captioning (DIC) -- generating distinctive captions that describe the unique details of a target image -- has received considerable attention over the last few years. A recent DIC work proposes to generate distinctive captions by comparing the target image with a set of semantic-similar reference images, i.e., reference-based DIC (Ref-DIC). It aims to make the generated captions can tell apart the target and reference images. Unfortunately, reference images used by existing Ref-DIC works are easy to distinguish: these reference images only resemble the target image at scene-l"},"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":"2207.11118","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-22T14:49:54Z","cross_cats_sorted":[],"title_canon_sha256":"0b89faad05b710274abc267d238705d78a8252a26dd7728fd8360e506da4c277","abstract_canon_sha256":"e769370fcf8b3e438ffa45c5cac652b37ba63bb98e1cc01eecd0b905eb1ab0e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:42:43.814313Z","signature_b64":"8wm/V52bRBD0iW2kANR/4MbuQLqXLwjwLKXICNoez8T7oFOzoEWM+rkK1EDjABidx9yafefTPPx/ol2hkPq4AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37c9c44ce757a181820fd30d79d7f654b4d5d33b2049c1a12014d31707a59249","last_reissued_at":"2026-07-05T04:42:43.813899Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:42:43.813899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking the Reference-based Distinctive Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Zhang, Jian Shao, Jun Xiao, Long Chen, Yangjun Mao, Zhihong Jiang, Zhimeng Zhang","submitted_at":"2022-07-22T14:49:54Z","abstract_excerpt":"Distinctive Image Captioning (DIC) -- generating distinctive captions that describe the unique details of a target image -- has received considerable attention over the last few years. A recent DIC work proposes to generate distinctive captions by comparing the target image with a set of semantic-similar reference images, i.e., reference-based DIC (Ref-DIC). It aims to make the generated captions can tell apart the target and reference images. Unfortunately, reference images used by existing Ref-DIC works are easy to distinguish: these reference images only resemble the target image at scene-l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.11118","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/2207.11118/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":"2207.11118","created_at":"2026-07-05T04:42:43.813959+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.11118v1","created_at":"2026-07-05T04:42:43.813959+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.11118","created_at":"2026-07-05T04:42:43.813959+00:00"},{"alias_kind":"pith_short_12","alias_value":"G7E4ITHHK6QY","created_at":"2026-07-05T04:42:43.813959+00:00"},{"alias_kind":"pith_short_16","alias_value":"G7E4ITHHK6QYDAQP","created_at":"2026-07-05T04:42:43.813959+00:00"},{"alias_kind":"pith_short_8","alias_value":"G7E4ITHH","created_at":"2026-07-05T04:42:43.813959+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/G7E4ITHHK6QYDAQP2MGXTV7WKS","json":"https://pith.science/pith/G7E4ITHHK6QYDAQP2MGXTV7WKS.json","graph_json":"https://pith.science/api/pith-number/G7E4ITHHK6QYDAQP2MGXTV7WKS/graph.json","events_json":"https://pith.science/api/pith-number/G7E4ITHHK6QYDAQP2MGXTV7WKS/events.json","paper":"https://pith.science/paper/G7E4ITHH"},"agent_actions":{"view_html":"https://pith.science/pith/G7E4ITHHK6QYDAQP2MGXTV7WKS","download_json":"https://pith.science/pith/G7E4ITHHK6QYDAQP2MGXTV7WKS.json","view_paper":"https://pith.science/paper/G7E4ITHH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.11118&json=true","fetch_graph":"https://pith.science/api/pith-number/G7E4ITHHK6QYDAQP2MGXTV7WKS/graph.json","fetch_events":"https://pith.science/api/pith-number/G7E4ITHHK6QYDAQP2MGXTV7WKS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G7E4ITHHK6QYDAQP2MGXTV7WKS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G7E4ITHHK6QYDAQP2MGXTV7WKS/action/storage_attestation","attest_author":"https://pith.science/pith/G7E4ITHHK6QYDAQP2MGXTV7WKS/action/author_attestation","sign_citation":"https://pith.science/pith/G7E4ITHHK6QYDAQP2MGXTV7WKS/action/citation_signature","submit_replication":"https://pith.science/pith/G7E4ITHHK6QYDAQP2MGXTV7WKS/action/replication_record"}},"created_at":"2026-07-05T04:42:43.813959+00:00","updated_at":"2026-07-05T04:42:43.813959+00:00"}