{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QKU4GOOGQJD2DQALBQK5MWPIGB","short_pith_number":"pith:QKU4GOOG","schema_version":"1.0","canonical_sha256":"82a9c339c68247a1c00b0c15d659e83076f18ceb946705b3fd273f5ecd1a2430","source":{"kind":"arxiv","id":"2606.26452","version":1},"attestation_state":"computed","paper":{"title":"AnySimLite: A Lightweight Few-Shot Similarity Encoder for On-Device Speech-Adjacent Classification","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.CL","authors_text":"Keshav Goyal, Mohamed Akram Ulla Shariff, Sahil Singh Bagri, Saravana Balaji Shanmugam, Sourav Ghosh, Yash Bhatia","submitted_at":"2026-06-24T23:25:28Z","abstract_excerpt":"To minimize privacy concerns and inference latency on edge devices like smartphones, lightweight on-device models remain important for end-user applications. Many of these applications involve natural language classification, but deploying multiple specialized models creates a memory footprint challenge. We investigate: Can a single lightweight architecture solve multiple Speech-Adjacent (SA) classification tasks through reduction to a nuanced text similarity formulation? We propose AnySimLite, a lightweight similarity encoder that combines word-level and character-level channels. Together wit"},"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":"2606.26452","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-24T23:25:28Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"946cb3dd48cace48f217cfd6417f3240ff7c917718370f59e7306862a4bc337c","abstract_canon_sha256":"700c55ebf8d2d11d3ad34d5889cfe4d60d52bb3d27ee5e53360e4839da662846"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T00:15:41.650736Z","signature_b64":"/Z4DTRgM5HYvWfPo1WvTND+oNDtudzcQVk471XwXQoXGLkEws4azrDYNqDD9tB5misGJgaKXpRfmAUwnemUbBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82a9c339c68247a1c00b0c15d659e83076f18ceb946705b3fd273f5ecd1a2430","last_reissued_at":"2026-06-26T00:15:41.650346Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T00:15:41.650346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AnySimLite: A Lightweight Few-Shot Similarity Encoder for On-Device Speech-Adjacent Classification","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.CL","authors_text":"Keshav Goyal, Mohamed Akram Ulla Shariff, Sahil Singh Bagri, Saravana Balaji Shanmugam, Sourav Ghosh, Yash Bhatia","submitted_at":"2026-06-24T23:25:28Z","abstract_excerpt":"To minimize privacy concerns and inference latency on edge devices like smartphones, lightweight on-device models remain important for end-user applications. Many of these applications involve natural language classification, but deploying multiple specialized models creates a memory footprint challenge. We investigate: Can a single lightweight architecture solve multiple Speech-Adjacent (SA) classification tasks through reduction to a nuanced text similarity formulation? We propose AnySimLite, a lightweight similarity encoder that combines word-level and character-level channels. Together wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26452","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/2606.26452/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":"2606.26452","created_at":"2026-06-26T00:15:41.650405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.26452v1","created_at":"2026-06-26T00:15:41.650405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26452","created_at":"2026-06-26T00:15:41.650405+00:00"},{"alias_kind":"pith_short_12","alias_value":"QKU4GOOGQJD2","created_at":"2026-06-26T00:15:41.650405+00:00"},{"alias_kind":"pith_short_16","alias_value":"QKU4GOOGQJD2DQAL","created_at":"2026-06-26T00:15:41.650405+00:00"},{"alias_kind":"pith_short_8","alias_value":"QKU4GOOG","created_at":"2026-06-26T00:15:41.650405+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/QKU4GOOGQJD2DQALBQK5MWPIGB","json":"https://pith.science/pith/QKU4GOOGQJD2DQALBQK5MWPIGB.json","graph_json":"https://pith.science/api/pith-number/QKU4GOOGQJD2DQALBQK5MWPIGB/graph.json","events_json":"https://pith.science/api/pith-number/QKU4GOOGQJD2DQALBQK5MWPIGB/events.json","paper":"https://pith.science/paper/QKU4GOOG"},"agent_actions":{"view_html":"https://pith.science/pith/QKU4GOOGQJD2DQALBQK5MWPIGB","download_json":"https://pith.science/pith/QKU4GOOGQJD2DQALBQK5MWPIGB.json","view_paper":"https://pith.science/paper/QKU4GOOG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.26452&json=true","fetch_graph":"https://pith.science/api/pith-number/QKU4GOOGQJD2DQALBQK5MWPIGB/graph.json","fetch_events":"https://pith.science/api/pith-number/QKU4GOOGQJD2DQALBQK5MWPIGB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QKU4GOOGQJD2DQALBQK5MWPIGB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QKU4GOOGQJD2DQALBQK5MWPIGB/action/storage_attestation","attest_author":"https://pith.science/pith/QKU4GOOGQJD2DQALBQK5MWPIGB/action/author_attestation","sign_citation":"https://pith.science/pith/QKU4GOOGQJD2DQALBQK5MWPIGB/action/citation_signature","submit_replication":"https://pith.science/pith/QKU4GOOGQJD2DQALBQK5MWPIGB/action/replication_record"}},"created_at":"2026-06-26T00:15:41.650405+00:00","updated_at":"2026-06-26T00:15:41.650405+00:00"}