{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4KNIANX7FIQV6HO3NI4MYEE2XY","short_pith_number":"pith:4KNIANX7","schema_version":"1.0","canonical_sha256":"e29a8036ff2a215f1ddb6a38cc109abe0674d15b1a830a823fcadb42f80b8e57","source":{"kind":"arxiv","id":"2411.13786","version":1},"attestation_state":"computed","paper":{"title":"Adaptable Embeddings Network (AEN)","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Alexander Titus, Stan Loosmore","submitted_at":"2024-11-21T02:15:52Z","abstract_excerpt":"Modern day Language Models see extensive use in text classification, yet this comes at significant computational cost. Compute-effective classification models are needed for low-resource environments, most notably on edge devices. We introduce Adaptable Embeddings Networks (AEN), a novel dual-encoder architecture using Kernel Density Estimation (KDE). This architecture allows for runtime adaptation of classification criteria without retraining and is non-autoregressive. Through thorough synthetic data experimentation, we demonstrate our model outputs comparable and in certain cases superior re"},"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":"2411.13786","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-21T02:15:52Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d3bd1c8770035d4e331bf50e70fa2ddeea30d845e82fe14647c946b55b969c50","abstract_canon_sha256":"07292b2e9f90974893bce579b26a7b50f2f52a9a261c6a0cad19a98898239d53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:37.085423Z","signature_b64":"CEZKXvREN6fkMNzJqGNi1OL+cuSQT0GS1LBQK3YRmUW74aqU4asGzqTMOvEFB7748WEFFHLRAXDTqomQ9GjVAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e29a8036ff2a215f1ddb6a38cc109abe0674d15b1a830a823fcadb42f80b8e57","last_reissued_at":"2026-07-05T09:38:37.084868Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:37.084868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptable Embeddings Network (AEN)","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Alexander Titus, Stan Loosmore","submitted_at":"2024-11-21T02:15:52Z","abstract_excerpt":"Modern day Language Models see extensive use in text classification, yet this comes at significant computational cost. Compute-effective classification models are needed for low-resource environments, most notably on edge devices. We introduce Adaptable Embeddings Networks (AEN), a novel dual-encoder architecture using Kernel Density Estimation (KDE). This architecture allows for runtime adaptation of classification criteria without retraining and is non-autoregressive. Through thorough synthetic data experimentation, we demonstrate our model outputs comparable and in certain cases superior re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13786","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/2411.13786/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":"2411.13786","created_at":"2026-07-05T09:38:37.084946+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.13786v1","created_at":"2026-07-05T09:38:37.084946+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13786","created_at":"2026-07-05T09:38:37.084946+00:00"},{"alias_kind":"pith_short_12","alias_value":"4KNIANX7FIQV","created_at":"2026-07-05T09:38:37.084946+00:00"},{"alias_kind":"pith_short_16","alias_value":"4KNIANX7FIQV6HO3","created_at":"2026-07-05T09:38:37.084946+00:00"},{"alias_kind":"pith_short_8","alias_value":"4KNIANX7","created_at":"2026-07-05T09:38:37.084946+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/4KNIANX7FIQV6HO3NI4MYEE2XY","json":"https://pith.science/pith/4KNIANX7FIQV6HO3NI4MYEE2XY.json","graph_json":"https://pith.science/api/pith-number/4KNIANX7FIQV6HO3NI4MYEE2XY/graph.json","events_json":"https://pith.science/api/pith-number/4KNIANX7FIQV6HO3NI4MYEE2XY/events.json","paper":"https://pith.science/paper/4KNIANX7"},"agent_actions":{"view_html":"https://pith.science/pith/4KNIANX7FIQV6HO3NI4MYEE2XY","download_json":"https://pith.science/pith/4KNIANX7FIQV6HO3NI4MYEE2XY.json","view_paper":"https://pith.science/paper/4KNIANX7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.13786&json=true","fetch_graph":"https://pith.science/api/pith-number/4KNIANX7FIQV6HO3NI4MYEE2XY/graph.json","fetch_events":"https://pith.science/api/pith-number/4KNIANX7FIQV6HO3NI4MYEE2XY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4KNIANX7FIQV6HO3NI4MYEE2XY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4KNIANX7FIQV6HO3NI4MYEE2XY/action/storage_attestation","attest_author":"https://pith.science/pith/4KNIANX7FIQV6HO3NI4MYEE2XY/action/author_attestation","sign_citation":"https://pith.science/pith/4KNIANX7FIQV6HO3NI4MYEE2XY/action/citation_signature","submit_replication":"https://pith.science/pith/4KNIANX7FIQV6HO3NI4MYEE2XY/action/replication_record"}},"created_at":"2026-07-05T09:38:37.084946+00:00","updated_at":"2026-07-05T09:38:37.084946+00:00"}