{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:O2WLUGGWDAJ4DIRFRPIQNYTSMU","short_pith_number":"pith:O2WLUGGW","schema_version":"1.0","canonical_sha256":"76acba18d61813c1a2258bd106e2726522a1c910403064cfd0edc1ee3ca575d8","source":{"kind":"arxiv","id":"2606.00014","version":1},"attestation_state":"computed","paper":{"title":"Toward Robust In-Context Learning: Leveraging Out-of-distribution Proxies for Target Inaccessible Demonstration Retrieval","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fausto Giunchiglia, Hao Xu, Rite Bo, Rui Song, Yingji Li","submitted_at":"2026-04-13T10:22:52Z","abstract_excerpt":"Although studies have demonstrated that Large Language Models (LLMs) can perform well on Out-of-Distribution (OOD) tasks, their advantage tends to diminish as the distribution shift becomes more severe. Consequently, researchers aim to retrieve distributionally similar and informative demonstrations from the available source domain to boost the inference capabilities of LLMs. However, in practical scenarios where the target domain is inaccessible, evaluating the unknown distribution is challenging, which indirectly impacts the quality of the selected demonstrations. To address this problem, we"},"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":"2606.00014","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-13T10:22:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1e27bf08592446eb09785ce959ca7ad52c3edf6ab93e98060f5ddcf0d2f31da2","abstract_canon_sha256":"f35a825461c6c1952564aac6e9d64438d968c5af7cd9834efc1bc1055be9f6ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T00:03:12.286498Z","signature_b64":"djCax7dio/h4mUgl7z8TelLpP/tPZMZqPQkeCA6Wc3mDeJNMy3ywwQ9UjSJeLLSo/Gl4pgqwvrApMr5E7tCzCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76acba18d61813c1a2258bd106e2726522a1c910403064cfd0edc1ee3ca575d8","last_reissued_at":"2026-06-02T00:03:12.285932Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T00:03:12.285932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward Robust In-Context Learning: Leveraging Out-of-distribution Proxies for Target Inaccessible Demonstration Retrieval","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fausto Giunchiglia, Hao Xu, Rite Bo, Rui Song, Yingji Li","submitted_at":"2026-04-13T10:22:52Z","abstract_excerpt":"Although studies have demonstrated that Large Language Models (LLMs) can perform well on Out-of-Distribution (OOD) tasks, their advantage tends to diminish as the distribution shift becomes more severe. Consequently, researchers aim to retrieve distributionally similar and informative demonstrations from the available source domain to boost the inference capabilities of LLMs. However, in practical scenarios where the target domain is inaccessible, evaluating the unknown distribution is challenging, which indirectly impacts the quality of the selected demonstrations. To address this problem, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00014","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/2606.00014/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":"2606.00014","created_at":"2026-06-02T00:03:12.285999+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00014v1","created_at":"2026-06-02T00:03:12.285999+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00014","created_at":"2026-06-02T00:03:12.285999+00:00"},{"alias_kind":"pith_short_12","alias_value":"O2WLUGGWDAJ4","created_at":"2026-06-02T00:03:12.285999+00:00"},{"alias_kind":"pith_short_16","alias_value":"O2WLUGGWDAJ4DIRF","created_at":"2026-06-02T00:03:12.285999+00:00"},{"alias_kind":"pith_short_8","alias_value":"O2WLUGGW","created_at":"2026-06-02T00:03:12.285999+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/O2WLUGGWDAJ4DIRFRPIQNYTSMU","json":"https://pith.science/pith/O2WLUGGWDAJ4DIRFRPIQNYTSMU.json","graph_json":"https://pith.science/api/pith-number/O2WLUGGWDAJ4DIRFRPIQNYTSMU/graph.json","events_json":"https://pith.science/api/pith-number/O2WLUGGWDAJ4DIRFRPIQNYTSMU/events.json","paper":"https://pith.science/paper/O2WLUGGW"},"agent_actions":{"view_html":"https://pith.science/pith/O2WLUGGWDAJ4DIRFRPIQNYTSMU","download_json":"https://pith.science/pith/O2WLUGGWDAJ4DIRFRPIQNYTSMU.json","view_paper":"https://pith.science/paper/O2WLUGGW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00014&json=true","fetch_graph":"https://pith.science/api/pith-number/O2WLUGGWDAJ4DIRFRPIQNYTSMU/graph.json","fetch_events":"https://pith.science/api/pith-number/O2WLUGGWDAJ4DIRFRPIQNYTSMU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O2WLUGGWDAJ4DIRFRPIQNYTSMU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O2WLUGGWDAJ4DIRFRPIQNYTSMU/action/storage_attestation","attest_author":"https://pith.science/pith/O2WLUGGWDAJ4DIRFRPIQNYTSMU/action/author_attestation","sign_citation":"https://pith.science/pith/O2WLUGGWDAJ4DIRFRPIQNYTSMU/action/citation_signature","submit_replication":"https://pith.science/pith/O2WLUGGWDAJ4DIRFRPIQNYTSMU/action/replication_record"}},"created_at":"2026-06-02T00:03:12.285999+00:00","updated_at":"2026-06-02T00:03:12.285999+00:00"}