{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZMX36POZJRDUWTNPV7LOG3H7WF","short_pith_number":"pith:ZMX36POZ","schema_version":"1.0","canonical_sha256":"cb2fbf3dd94c474b4dafafd6e36cffb1739d5c7f5a9a7c2c3b161dca2e16f596","source":{"kind":"arxiv","id":"2305.14171","version":3},"attestation_state":"computed","paper":{"title":"In-Context Probing: Toward Building Robust Classifiers via Probing Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Afra Amini, Massimiliano Ciaramita","submitted_at":"2023-05-23T15:43:04Z","abstract_excerpt":"Large language models are able to learn new tasks in context, where they are provided with instructions and a few annotated examples. However, the effectiveness of in-context learning is dependent on the provided context, and the performance on a downstream task can vary considerably, depending on the instruction. Importantly, such dependency on the context can surface in unpredictable ways, e.g., a seemingly more informative instruction might lead to a worse performance. In this paper, we propose an alternative approach, which we term In-Context Probing (ICP). Similar to in-context learning, "},"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":"2305.14171","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T15:43:04Z","cross_cats_sorted":[],"title_canon_sha256":"0ed806554a079e9af7c1047c52568b59160f695ffa4275bd2e0f93aee5926cb3","abstract_canon_sha256":"9b8847e86c320960dddd6c441d4dda94051e54404bc4ac796e3180ff6a993683"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:04.708217Z","signature_b64":"l/1V1RpPIYbNgkoLjp+dW9Z8wiptaVREJ5cfzA65OMg0P4BfeVuFhCYf2S+r6nM7FeM7mpHqgeuPE934k6DvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb2fbf3dd94c474b4dafafd6e36cffb1739d5c7f5a9a7c2c3b161dca2e16f596","last_reissued_at":"2026-07-05T07:27:04.707748Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:04.707748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In-Context Probing: Toward Building Robust Classifiers via Probing Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Afra Amini, Massimiliano Ciaramita","submitted_at":"2023-05-23T15:43:04Z","abstract_excerpt":"Large language models are able to learn new tasks in context, where they are provided with instructions and a few annotated examples. However, the effectiveness of in-context learning is dependent on the provided context, and the performance on a downstream task can vary considerably, depending on the instruction. Importantly, such dependency on the context can surface in unpredictable ways, e.g., a seemingly more informative instruction might lead to a worse performance. In this paper, we propose an alternative approach, which we term In-Context Probing (ICP). Similar to in-context learning, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14171","kind":"arxiv","version":3},"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/2305.14171/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":"2305.14171","created_at":"2026-07-05T07:27:04.707810+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14171v3","created_at":"2026-07-05T07:27:04.707810+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14171","created_at":"2026-07-05T07:27:04.707810+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZMX36POZJRDU","created_at":"2026-07-05T07:27:04.707810+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZMX36POZJRDUWTNP","created_at":"2026-07-05T07:27:04.707810+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZMX36POZ","created_at":"2026-07-05T07:27:04.707810+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/ZMX36POZJRDUWTNPV7LOG3H7WF","json":"https://pith.science/pith/ZMX36POZJRDUWTNPV7LOG3H7WF.json","graph_json":"https://pith.science/api/pith-number/ZMX36POZJRDUWTNPV7LOG3H7WF/graph.json","events_json":"https://pith.science/api/pith-number/ZMX36POZJRDUWTNPV7LOG3H7WF/events.json","paper":"https://pith.science/paper/ZMX36POZ"},"agent_actions":{"view_html":"https://pith.science/pith/ZMX36POZJRDUWTNPV7LOG3H7WF","download_json":"https://pith.science/pith/ZMX36POZJRDUWTNPV7LOG3H7WF.json","view_paper":"https://pith.science/paper/ZMX36POZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14171&json=true","fetch_graph":"https://pith.science/api/pith-number/ZMX36POZJRDUWTNPV7LOG3H7WF/graph.json","fetch_events":"https://pith.science/api/pith-number/ZMX36POZJRDUWTNPV7LOG3H7WF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZMX36POZJRDUWTNPV7LOG3H7WF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZMX36POZJRDUWTNPV7LOG3H7WF/action/storage_attestation","attest_author":"https://pith.science/pith/ZMX36POZJRDUWTNPV7LOG3H7WF/action/author_attestation","sign_citation":"https://pith.science/pith/ZMX36POZJRDUWTNPV7LOG3H7WF/action/citation_signature","submit_replication":"https://pith.science/pith/ZMX36POZJRDUWTNPV7LOG3H7WF/action/replication_record"}},"created_at":"2026-07-05T07:27:04.707810+00:00","updated_at":"2026-07-05T07:27:04.707810+00:00"}