{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:DFOPX46XEWVHIWL2ZD6K63PMSS","short_pith_number":"pith:DFOPX46X","schema_version":"1.0","canonical_sha256":"195cfbf3d725aa74597ac8fcaf6dec94ac7234a2cb389e3a5a5e19e20784a0fb","source":{"kind":"arxiv","id":"2005.10477","version":1},"attestation_state":"computed","paper":{"title":"Pairwise Supervised Hashing with Bernoulli Variational Auto-Encoder and Self-Control Gradient Estimator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mingyuan Zhou, Mingzhang Yin, Shahin Boluki, Siamak Zamani Dadaneh, Xiaoning Qian","submitted_at":"2020-05-21T06:11:33Z","abstract_excerpt":"Semantic hashing has become a crucial component of fast similarity search in many large-scale information retrieval systems, in particular, for text data. Variational auto-encoders (VAEs) with binary latent variables as hashing codes provide state-of-the-art performance in terms of precision for document retrieval. We propose a pairwise loss function with discrete latent VAE to reward within-class similarity and between-class dissimilarity for supervised hashing. Instead of solving the optimization relying on existing biased gradient estimators, an unbiased low-variance gradient estimator is a"},"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":"2005.10477","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-21T06:11:33Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"92c9b2e35983a6e8c4e6f23d2d1b56f80494e29cc4c01e2404c571dc9cd9a4cb","abstract_canon_sha256":"6bfce18dc407814faf3999031a56ffe833f0faf8175a64fde50101442fceb3a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:04:54.475194Z","signature_b64":"rZeT+m9KJKIxw+uLWexRnapI+F+s9oZVFf5HlhwQvRjqPE750JrANoJzh2YCcNu+25yseb4b3n6Qwjh1KbkpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"195cfbf3d725aa74597ac8fcaf6dec94ac7234a2cb389e3a5a5e19e20784a0fb","last_reissued_at":"2026-07-05T01:04:54.474787Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:04:54.474787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pairwise Supervised Hashing with Bernoulli Variational Auto-Encoder and Self-Control Gradient Estimator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mingyuan Zhou, Mingzhang Yin, Shahin Boluki, Siamak Zamani Dadaneh, Xiaoning Qian","submitted_at":"2020-05-21T06:11:33Z","abstract_excerpt":"Semantic hashing has become a crucial component of fast similarity search in many large-scale information retrieval systems, in particular, for text data. Variational auto-encoders (VAEs) with binary latent variables as hashing codes provide state-of-the-art performance in terms of precision for document retrieval. We propose a pairwise loss function with discrete latent VAE to reward within-class similarity and between-class dissimilarity for supervised hashing. Instead of solving the optimization relying on existing biased gradient estimators, an unbiased low-variance gradient estimator is a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.10477","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/2005.10477/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":"2005.10477","created_at":"2026-07-05T01:04:54.474848+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.10477v1","created_at":"2026-07-05T01:04:54.474848+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.10477","created_at":"2026-07-05T01:04:54.474848+00:00"},{"alias_kind":"pith_short_12","alias_value":"DFOPX46XEWVH","created_at":"2026-07-05T01:04:54.474848+00:00"},{"alias_kind":"pith_short_16","alias_value":"DFOPX46XEWVHIWL2","created_at":"2026-07-05T01:04:54.474848+00:00"},{"alias_kind":"pith_short_8","alias_value":"DFOPX46X","created_at":"2026-07-05T01:04:54.474848+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.18703","citing_title":"Probabilistic Modeling of Disparity Uncertainty for Robust and Efficient Stereo Matching","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DFOPX46XEWVHIWL2ZD6K63PMSS","json":"https://pith.science/pith/DFOPX46XEWVHIWL2ZD6K63PMSS.json","graph_json":"https://pith.science/api/pith-number/DFOPX46XEWVHIWL2ZD6K63PMSS/graph.json","events_json":"https://pith.science/api/pith-number/DFOPX46XEWVHIWL2ZD6K63PMSS/events.json","paper":"https://pith.science/paper/DFOPX46X"},"agent_actions":{"view_html":"https://pith.science/pith/DFOPX46XEWVHIWL2ZD6K63PMSS","download_json":"https://pith.science/pith/DFOPX46XEWVHIWL2ZD6K63PMSS.json","view_paper":"https://pith.science/paper/DFOPX46X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.10477&json=true","fetch_graph":"https://pith.science/api/pith-number/DFOPX46XEWVHIWL2ZD6K63PMSS/graph.json","fetch_events":"https://pith.science/api/pith-number/DFOPX46XEWVHIWL2ZD6K63PMSS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DFOPX46XEWVHIWL2ZD6K63PMSS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DFOPX46XEWVHIWL2ZD6K63PMSS/action/storage_attestation","attest_author":"https://pith.science/pith/DFOPX46XEWVHIWL2ZD6K63PMSS/action/author_attestation","sign_citation":"https://pith.science/pith/DFOPX46XEWVHIWL2ZD6K63PMSS/action/citation_signature","submit_replication":"https://pith.science/pith/DFOPX46XEWVHIWL2ZD6K63PMSS/action/replication_record"}},"created_at":"2026-07-05T01:04:54.474848+00:00","updated_at":"2026-07-05T01:04:54.474848+00:00"}