{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WSQZFSHPHXFYHBI67RCKFNNN5E","short_pith_number":"pith:WSQZFSHP","schema_version":"1.0","canonical_sha256":"b4a192c8ef3dcb83851efc44a2b5ade93af09f71059aec805623750ba88e13d2","source":{"kind":"arxiv","id":"2507.17025","version":1},"attestation_state":"computed","paper":{"title":"Evolutionary Feature-wise Thresholding for Binary Representation of NLP Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Azam Asilian Bidgoli, Shahryar Rahnamayan, Soumen Sinha","submitted_at":"2025-07-22T21:29:34Z","abstract_excerpt":"Efficient text embedding is crucial for large-scale natural language processing (NLP) applications, where storage and computational efficiency are key concerns. In this paper, we explore how using binary representations (barcodes) instead of real-valued features can be used for NLP embeddings derived from machine learning models such as BERT. Thresholding is a common method for converting continuous embeddings into binary representations, often using a fixed threshold across all features. We propose a Coordinate Search-based optimization framework that instead identifies the optimal threshold "},"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":"2507.17025","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-22T21:29:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b206c70e927d60a34437c2e13fcf0cd652ff2aad1931edb1f0c00c649f945292","abstract_canon_sha256":"7b961090d029ede118588aa0f762fd9c1fd1cbcc91231f6f3c39ed21638f6582"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:00.360370Z","signature_b64":"omgKqXC8FvcqnWLzOdfLEzUZxvcCd4DkHcCbho4DuW7MfmP2006SrrKTQMc+gQOFFCtn9HUcDCBrerudLY6zCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4a192c8ef3dcb83851efc44a2b5ade93af09f71059aec805623750ba88e13d2","last_reissued_at":"2026-07-05T11:42:00.359837Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:00.359837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evolutionary Feature-wise Thresholding for Binary Representation of NLP Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Azam Asilian Bidgoli, Shahryar Rahnamayan, Soumen Sinha","submitted_at":"2025-07-22T21:29:34Z","abstract_excerpt":"Efficient text embedding is crucial for large-scale natural language processing (NLP) applications, where storage and computational efficiency are key concerns. In this paper, we explore how using binary representations (barcodes) instead of real-valued features can be used for NLP embeddings derived from machine learning models such as BERT. Thresholding is a common method for converting continuous embeddings into binary representations, often using a fixed threshold across all features. We propose a Coordinate Search-based optimization framework that instead identifies the optimal threshold "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17025","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/2507.17025/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":"2507.17025","created_at":"2026-07-05T11:42:00.359897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.17025v1","created_at":"2026-07-05T11:42:00.359897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17025","created_at":"2026-07-05T11:42:00.359897+00:00"},{"alias_kind":"pith_short_12","alias_value":"WSQZFSHPHXFY","created_at":"2026-07-05T11:42:00.359897+00:00"},{"alias_kind":"pith_short_16","alias_value":"WSQZFSHPHXFYHBI6","created_at":"2026-07-05T11:42:00.359897+00:00"},{"alias_kind":"pith_short_8","alias_value":"WSQZFSHP","created_at":"2026-07-05T11:42:00.359897+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/WSQZFSHPHXFYHBI67RCKFNNN5E","json":"https://pith.science/pith/WSQZFSHPHXFYHBI67RCKFNNN5E.json","graph_json":"https://pith.science/api/pith-number/WSQZFSHPHXFYHBI67RCKFNNN5E/graph.json","events_json":"https://pith.science/api/pith-number/WSQZFSHPHXFYHBI67RCKFNNN5E/events.json","paper":"https://pith.science/paper/WSQZFSHP"},"agent_actions":{"view_html":"https://pith.science/pith/WSQZFSHPHXFYHBI67RCKFNNN5E","download_json":"https://pith.science/pith/WSQZFSHPHXFYHBI67RCKFNNN5E.json","view_paper":"https://pith.science/paper/WSQZFSHP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.17025&json=true","fetch_graph":"https://pith.science/api/pith-number/WSQZFSHPHXFYHBI67RCKFNNN5E/graph.json","fetch_events":"https://pith.science/api/pith-number/WSQZFSHPHXFYHBI67RCKFNNN5E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WSQZFSHPHXFYHBI67RCKFNNN5E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WSQZFSHPHXFYHBI67RCKFNNN5E/action/storage_attestation","attest_author":"https://pith.science/pith/WSQZFSHPHXFYHBI67RCKFNNN5E/action/author_attestation","sign_citation":"https://pith.science/pith/WSQZFSHPHXFYHBI67RCKFNNN5E/action/citation_signature","submit_replication":"https://pith.science/pith/WSQZFSHPHXFYHBI67RCKFNNN5E/action/replication_record"}},"created_at":"2026-07-05T11:42:00.359897+00:00","updated_at":"2026-07-05T11:42:00.359897+00:00"}