{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:C7WWOSSMJEW2WMUHJPBOAW3HLF","short_pith_number":"pith:C7WWOSSM","schema_version":"1.0","canonical_sha256":"17ed674a4c492dab32874bc2e05b675977047c306f4dcbf0172eeac14c1f3fa6","source":{"kind":"arxiv","id":"2305.14800","version":6},"attestation_state":"computed","paper":{"title":"Exploring Diverse In-Context Configurations for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haokun Chen, Mingzhuo Yang, Xin Geng, Xu Yang, Yongliang Wu","submitted_at":"2023-05-24T06:52:47Z","abstract_excerpt":"After discovering that Language Models (LMs) can be good in-context few-shot learners, numerous strategies have been proposed to optimize in-context sequence configurations. Recently, researchers in Vision-Language (VL) domains also develop their few-shot learners, while they only use the simplest way, ie., randomly sampling, to configure in-context image-text pairs. In order to explore the effects of varying configurations on VL in-context learning, we devised four strategies for image selection and four for caption assignment to configure in-context image-text pairs for image captioning. Her"},"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":"2305.14800","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-24T06:52:47Z","cross_cats_sorted":[],"title_canon_sha256":"71b323712a79df481290c948d470a2c15adcaf83d67fa85922ef1c06bc2c7734","abstract_canon_sha256":"799902830416ceb5b37af780303e2c15ca0a5da5c31061f3c1e28b49593f9919"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:21.316642Z","signature_b64":"2pQ48X0vxpWueMHP0cU0IYHID6ax16tqGe735B8MHKoGpSNaTGwZ1uadYWyAINjQI2vQNCtRXnLWYazieWT2Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17ed674a4c492dab32874bc2e05b675977047c306f4dcbf0172eeac14c1f3fa6","last_reissued_at":"2026-07-05T07:36:21.316044Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:21.316044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Diverse In-Context Configurations for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haokun Chen, Mingzhuo Yang, Xin Geng, Xu Yang, Yongliang Wu","submitted_at":"2023-05-24T06:52:47Z","abstract_excerpt":"After discovering that Language Models (LMs) can be good in-context few-shot learners, numerous strategies have been proposed to optimize in-context sequence configurations. Recently, researchers in Vision-Language (VL) domains also develop their few-shot learners, while they only use the simplest way, ie., randomly sampling, to configure in-context image-text pairs. In order to explore the effects of varying configurations on VL in-context learning, we devised four strategies for image selection and four for caption assignment to configure in-context image-text pairs for image captioning. Her"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14800","kind":"arxiv","version":6},"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/2305.14800/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":"2305.14800","created_at":"2026-07-05T07:36:21.316122+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14800v6","created_at":"2026-07-05T07:36:21.316122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14800","created_at":"2026-07-05T07:36:21.316122+00:00"},{"alias_kind":"pith_short_12","alias_value":"C7WWOSSMJEW2","created_at":"2026-07-05T07:36:21.316122+00:00"},{"alias_kind":"pith_short_16","alias_value":"C7WWOSSMJEW2WMUH","created_at":"2026-07-05T07:36:21.316122+00:00"},{"alias_kind":"pith_short_8","alias_value":"C7WWOSSM","created_at":"2026-07-05T07:36:21.316122+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.04840","citing_title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","ref_index":112,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C7WWOSSMJEW2WMUHJPBOAW3HLF","json":"https://pith.science/pith/C7WWOSSMJEW2WMUHJPBOAW3HLF.json","graph_json":"https://pith.science/api/pith-number/C7WWOSSMJEW2WMUHJPBOAW3HLF/graph.json","events_json":"https://pith.science/api/pith-number/C7WWOSSMJEW2WMUHJPBOAW3HLF/events.json","paper":"https://pith.science/paper/C7WWOSSM"},"agent_actions":{"view_html":"https://pith.science/pith/C7WWOSSMJEW2WMUHJPBOAW3HLF","download_json":"https://pith.science/pith/C7WWOSSMJEW2WMUHJPBOAW3HLF.json","view_paper":"https://pith.science/paper/C7WWOSSM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14800&json=true","fetch_graph":"https://pith.science/api/pith-number/C7WWOSSMJEW2WMUHJPBOAW3HLF/graph.json","fetch_events":"https://pith.science/api/pith-number/C7WWOSSMJEW2WMUHJPBOAW3HLF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C7WWOSSMJEW2WMUHJPBOAW3HLF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C7WWOSSMJEW2WMUHJPBOAW3HLF/action/storage_attestation","attest_author":"https://pith.science/pith/C7WWOSSMJEW2WMUHJPBOAW3HLF/action/author_attestation","sign_citation":"https://pith.science/pith/C7WWOSSMJEW2WMUHJPBOAW3HLF/action/citation_signature","submit_replication":"https://pith.science/pith/C7WWOSSMJEW2WMUHJPBOAW3HLF/action/replication_record"}},"created_at":"2026-07-05T07:36:21.316122+00:00","updated_at":"2026-07-05T07:36:21.316122+00:00"}