{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:D22TNB3MJLLWOG35OP2QY7KIZE","short_pith_number":"pith:D22TNB3M","schema_version":"1.0","canonical_sha256":"1eb536876c4ad7671b7d73f50c7d48c93289366a8ba6f2160a702afec119b4d6","source":{"kind":"arxiv","id":"2606.05134","version":1},"attestation_state":"computed","paper":{"title":"Activation-Based Active Learning for In-Context Learning: Challenges and Insights","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Geoff V. Merrett, Stuart E. Middleton, Yaseen M. Osman","submitted_at":"2026-06-03T17:39:29Z","abstract_excerpt":"Deep active learning has previously been explored for LLM in-context sample selection, but not with methods that utilise recent advances in understanding of transformer activations. In this paper, we test the hypothesis that model activations could provide a fine-grained signal to optimise the selection of in-context examples. We present the most comprehensive analysis to date of MLP activation-based deep active learning methods applied to in-context learning, including how different attention masking strategies impact active learning across diverse classification and generative datasets, usin"},"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":"2606.05134","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T17:39:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a95378ff52452e8114f78bdf20c0624c7cb6d52899f38fef54df1c09b3d02e87","abstract_canon_sha256":"c2bcf8ad1ed5a0c83619f0eb2d8c14c5c146ee728e37f9988acb6d2517b7791a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:10:07.906033Z","signature_b64":"xJREVPZjSwH12b6XbnAuv8zN123dFGXRhoQc57Ccvg6SwYovuIz/hSGDuBMq5o+Tbc37r7OsYuM5/Sd9KvkuCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1eb536876c4ad7671b7d73f50c7d48c93289366a8ba6f2160a702afec119b4d6","last_reissued_at":"2026-06-04T01:10:07.905471Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:10:07.905471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Activation-Based Active Learning for In-Context Learning: Challenges and Insights","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Geoff V. Merrett, Stuart E. Middleton, Yaseen M. Osman","submitted_at":"2026-06-03T17:39:29Z","abstract_excerpt":"Deep active learning has previously been explored for LLM in-context sample selection, but not with methods that utilise recent advances in understanding of transformer activations. In this paper, we test the hypothesis that model activations could provide a fine-grained signal to optimise the selection of in-context examples. We present the most comprehensive analysis to date of MLP activation-based deep active learning methods applied to in-context learning, including how different attention masking strategies impact active learning across diverse classification and generative datasets, usin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05134","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/2606.05134/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":"2606.05134","created_at":"2026-06-04T01:10:07.905560+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05134v1","created_at":"2026-06-04T01:10:07.905560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05134","created_at":"2026-06-04T01:10:07.905560+00:00"},{"alias_kind":"pith_short_12","alias_value":"D22TNB3MJLLW","created_at":"2026-06-04T01:10:07.905560+00:00"},{"alias_kind":"pith_short_16","alias_value":"D22TNB3MJLLWOG35","created_at":"2026-06-04T01:10:07.905560+00:00"},{"alias_kind":"pith_short_8","alias_value":"D22TNB3M","created_at":"2026-06-04T01:10:07.905560+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/D22TNB3MJLLWOG35OP2QY7KIZE","json":"https://pith.science/pith/D22TNB3MJLLWOG35OP2QY7KIZE.json","graph_json":"https://pith.science/api/pith-number/D22TNB3MJLLWOG35OP2QY7KIZE/graph.json","events_json":"https://pith.science/api/pith-number/D22TNB3MJLLWOG35OP2QY7KIZE/events.json","paper":"https://pith.science/paper/D22TNB3M"},"agent_actions":{"view_html":"https://pith.science/pith/D22TNB3MJLLWOG35OP2QY7KIZE","download_json":"https://pith.science/pith/D22TNB3MJLLWOG35OP2QY7KIZE.json","view_paper":"https://pith.science/paper/D22TNB3M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05134&json=true","fetch_graph":"https://pith.science/api/pith-number/D22TNB3MJLLWOG35OP2QY7KIZE/graph.json","fetch_events":"https://pith.science/api/pith-number/D22TNB3MJLLWOG35OP2QY7KIZE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D22TNB3MJLLWOG35OP2QY7KIZE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D22TNB3MJLLWOG35OP2QY7KIZE/action/storage_attestation","attest_author":"https://pith.science/pith/D22TNB3MJLLWOG35OP2QY7KIZE/action/author_attestation","sign_citation":"https://pith.science/pith/D22TNB3MJLLWOG35OP2QY7KIZE/action/citation_signature","submit_replication":"https://pith.science/pith/D22TNB3MJLLWOG35OP2QY7KIZE/action/replication_record"}},"created_at":"2026-06-04T01:10:07.905560+00:00","updated_at":"2026-06-04T01:10:07.905560+00:00"}