{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EING66YPV3L6TC5DOLMJAA5RK6","short_pith_number":"pith:EING66YP","schema_version":"1.0","canonical_sha256":"221a6f7b0faed7e98ba372d89003b157b85d4c933504eff1b03d61ffec6a4b2e","source":{"kind":"arxiv","id":"2311.04207","version":3},"attestation_state":"computed","paper":{"title":"Deep Hashing via Householder Quantization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CV","authors_text":"Lucas Resende, Lucas R. Schwengber, Paulo Orenstein, Roberto I. Oliveira","submitted_at":"2023-11-07T18:47:28Z","abstract_excerpt":"Hashing is at the heart of large-scale image similarity search, and recent methods have been substantially improved through deep learning techniques. Such algorithms typically learn continuous embeddings of the data. To avoid a subsequent costly binarization step, a common solution is to employ loss functions that combine a similarity learning term (to ensure similar images are grouped to nearby embeddings) and a quantization penalty term (to ensure that the embedding entries are close to binarized entries, e.g., -1 or 1). Still, the interaction between these two terms can make learning harder"},"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":"2311.04207","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-07T18:47:28Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"936e88f74dade4b790be1848dae47a0cd04502a57c89425dfef634545eda54e9","abstract_canon_sha256":"5429ddd69e617c107e6a3a98f9dfd0cb295b73747b0ca29272196890687395c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:33:21.892343Z","signature_b64":"0N0+AMsEyCkSNgB0rz5niRS6BKwqoETs/IcGQELX6yGDnEuV5zDJMfsQ+3++EN4fkzRrvUDumh2t1CURnitMAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"221a6f7b0faed7e98ba372d89003b157b85d4c933504eff1b03d61ffec6a4b2e","last_reissued_at":"2026-07-05T07:33:21.891947Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:33:21.891947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Hashing via Householder Quantization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CV","authors_text":"Lucas Resende, Lucas R. Schwengber, Paulo Orenstein, Roberto I. Oliveira","submitted_at":"2023-11-07T18:47:28Z","abstract_excerpt":"Hashing is at the heart of large-scale image similarity search, and recent methods have been substantially improved through deep learning techniques. Such algorithms typically learn continuous embeddings of the data. To avoid a subsequent costly binarization step, a common solution is to employ loss functions that combine a similarity learning term (to ensure similar images are grouped to nearby embeddings) and a quantization penalty term (to ensure that the embedding entries are close to binarized entries, e.g., -1 or 1). Still, the interaction between these two terms can make learning harder"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04207","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/2311.04207/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":"2311.04207","created_at":"2026-07-05T07:33:21.892014+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.04207v3","created_at":"2026-07-05T07:33:21.892014+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04207","created_at":"2026-07-05T07:33:21.892014+00:00"},{"alias_kind":"pith_short_12","alias_value":"EING66YPV3L6","created_at":"2026-07-05T07:33:21.892014+00:00"},{"alias_kind":"pith_short_16","alias_value":"EING66YPV3L6TC5D","created_at":"2026-07-05T07:33:21.892014+00:00"},{"alias_kind":"pith_short_8","alias_value":"EING66YP","created_at":"2026-07-05T07:33:21.892014+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.05925","citing_title":"Sign-Symmetry Learning Rules are Robust Fine-Tuners","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EING66YPV3L6TC5DOLMJAA5RK6","json":"https://pith.science/pith/EING66YPV3L6TC5DOLMJAA5RK6.json","graph_json":"https://pith.science/api/pith-number/EING66YPV3L6TC5DOLMJAA5RK6/graph.json","events_json":"https://pith.science/api/pith-number/EING66YPV3L6TC5DOLMJAA5RK6/events.json","paper":"https://pith.science/paper/EING66YP"},"agent_actions":{"view_html":"https://pith.science/pith/EING66YPV3L6TC5DOLMJAA5RK6","download_json":"https://pith.science/pith/EING66YPV3L6TC5DOLMJAA5RK6.json","view_paper":"https://pith.science/paper/EING66YP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.04207&json=true","fetch_graph":"https://pith.science/api/pith-number/EING66YPV3L6TC5DOLMJAA5RK6/graph.json","fetch_events":"https://pith.science/api/pith-number/EING66YPV3L6TC5DOLMJAA5RK6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EING66YPV3L6TC5DOLMJAA5RK6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EING66YPV3L6TC5DOLMJAA5RK6/action/storage_attestation","attest_author":"https://pith.science/pith/EING66YPV3L6TC5DOLMJAA5RK6/action/author_attestation","sign_citation":"https://pith.science/pith/EING66YPV3L6TC5DOLMJAA5RK6/action/citation_signature","submit_replication":"https://pith.science/pith/EING66YPV3L6TC5DOLMJAA5RK6/action/replication_record"}},"created_at":"2026-07-05T07:33:21.892014+00:00","updated_at":"2026-07-05T07:33:21.892014+00:00"}