{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:C7WWOSSMJEW2WMUHJPBOAW3HLF","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":"799902830416ceb5b37af780303e2c15ca0a5da5c31061f3c1e28b49593f9919","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-24T06:52:47Z","title_canon_sha256":"71b323712a79df481290c948d470a2c15adcaf83d67fa85922ef1c06bc2c7734"},"schema_version":"1.0","source":{"id":"2305.14800","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14800","created_at":"2026-07-05T07:36:21Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14800v6","created_at":"2026-07-05T07:36:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14800","created_at":"2026-07-05T07:36:21Z"},{"alias_kind":"pith_short_12","alias_value":"C7WWOSSMJEW2","created_at":"2026-07-05T07:36:21Z"},{"alias_kind":"pith_short_16","alias_value":"C7WWOSSMJEW2WMUH","created_at":"2026-07-05T07:36:21Z"},{"alias_kind":"pith_short_8","alias_value":"C7WWOSSM","created_at":"2026-07-05T07:36:21Z"}],"graph_snapshots":[{"event_id":"sha256:a174fd2a9b19566e17241069bfdd899a6be76a12510d33ce048635bdd20a64a0","target":"graph","created_at":"2026-07-05T07:36:21Z","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/2305.14800/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Haokun Chen, Mingzhuo Yang, Xin Geng, Xu Yang, Yongliang Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-24T06:52:47Z","title":"Exploring Diverse In-Context Configurations for Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14800","kind":"arxiv","version":6},"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":"sha256:4c43a6f3415a99ca55274fb7569b26d574bdbf4f29918fbb014884609d7566ee","target":"record","created_at":"2026-07-05T07:36:21Z","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":"799902830416ceb5b37af780303e2c15ca0a5da5c31061f3c1e28b49593f9919","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-24T06:52:47Z","title_canon_sha256":"71b323712a79df481290c948d470a2c15adcaf83d67fa85922ef1c06bc2c7734"},"schema_version":"1.0","source":{"id":"2305.14800","kind":"arxiv","version":6}},"canonical_sha256":"17ed674a4c492dab32874bc2e05b675977047c306f4dcbf0172eeac14c1f3fa6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17ed674a4c492dab32874bc2e05b675977047c306f4dcbf0172eeac14c1f3fa6","first_computed_at":"2026-07-05T07:36:21.316044Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:36:21.316044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2pQ48X0vxpWueMHP0cU0IYHID6ax16tqGe735B8MHKoGpSNaTGwZ1uadYWyAINjQI2vQNCtRXnLWYazieWT2Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:36:21.316642Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14800","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c43a6f3415a99ca55274fb7569b26d574bdbf4f29918fbb014884609d7566ee","sha256:a174fd2a9b19566e17241069bfdd899a6be76a12510d33ce048635bdd20a64a0"],"state_sha256":"6dcc4422efacf8427a64f8070af0686397650db516bc10046b6e455b90ac2d9d"}