{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:I2YEYY74LR57TX6IJ6WP2GGVOB","short_pith_number":"pith:I2YEYY74","schema_version":"1.0","canonical_sha256":"46b04c63fc5c7bf9dfc84facfd18d57050e542d66ec34ec495678863c8dcc26f","source":{"kind":"arxiv","id":"1412.2863","version":2},"attestation_state":"computed","paper":{"title":"Score Function Features for Discriminative Learning: Matrix and Tensor Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anima Anandkumar, Hanie Sedghi, Majid Janzamin","submitted_at":"2014-12-09T06:22:19Z","abstract_excerpt":"Feature learning forms the cornerstone for tackling challenging learning problems in domains such as speech, computer vision and natural language processing. In this paper, we consider a novel class of matrix and tensor-valued features, which can be pre-trained using unlabeled samples. We present efficient algorithms for extracting discriminative information, given these pre-trained features and labeled samples for any related task. Our class of features are based on higher-order score functions, which capture local variations in the probability density function of the input. We establish a th"},"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":"1412.2863","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-12-09T06:22:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"201b9d92c70a1d066c313bc348a36326e8d65eebb7d0e516d927826602a0ae86","abstract_canon_sha256":"cbf808392c436e39a04818d8d663440107edebc9315c9864b0d01a0e63bd4043"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:31:30.942630Z","signature_b64":"JmtDc7C5JuX9Ha6SWNfDlT1J8aftNSopMo2Ujgblm4hQTzL6kzznvaQ0uxUryionSEJSmLBLwT8bUk5fPTFBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46b04c63fc5c7bf9dfc84facfd18d57050e542d66ec34ec495678863c8dcc26f","last_reissued_at":"2026-05-18T02:31:30.942251Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:31:30.942251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Score Function Features for Discriminative Learning: Matrix and Tensor Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anima Anandkumar, Hanie Sedghi, Majid Janzamin","submitted_at":"2014-12-09T06:22:19Z","abstract_excerpt":"Feature learning forms the cornerstone for tackling challenging learning problems in domains such as speech, computer vision and natural language processing. In this paper, we consider a novel class of matrix and tensor-valued features, which can be pre-trained using unlabeled samples. We present efficient algorithms for extracting discriminative information, given these pre-trained features and labeled samples for any related task. Our class of features are based on higher-order score functions, which capture local variations in the probability density function of the input. We establish a th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.2863","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1412.2863","created_at":"2026-05-18T02:31:30.942306+00:00"},{"alias_kind":"arxiv_version","alias_value":"1412.2863v2","created_at":"2026-05-18T02:31:30.942306+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.2863","created_at":"2026-05-18T02:31:30.942306+00:00"},{"alias_kind":"pith_short_12","alias_value":"I2YEYY74LR57","created_at":"2026-05-18T12:28:33.132498+00:00"},{"alias_kind":"pith_short_16","alias_value":"I2YEYY74LR57TX6I","created_at":"2026-05-18T12:28:33.132498+00:00"},{"alias_kind":"pith_short_8","alias_value":"I2YEYY74","created_at":"2026-05-18T12:28:33.132498+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/I2YEYY74LR57TX6IJ6WP2GGVOB","json":"https://pith.science/pith/I2YEYY74LR57TX6IJ6WP2GGVOB.json","graph_json":"https://pith.science/api/pith-number/I2YEYY74LR57TX6IJ6WP2GGVOB/graph.json","events_json":"https://pith.science/api/pith-number/I2YEYY74LR57TX6IJ6WP2GGVOB/events.json","paper":"https://pith.science/paper/I2YEYY74"},"agent_actions":{"view_html":"https://pith.science/pith/I2YEYY74LR57TX6IJ6WP2GGVOB","download_json":"https://pith.science/pith/I2YEYY74LR57TX6IJ6WP2GGVOB.json","view_paper":"https://pith.science/paper/I2YEYY74","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1412.2863&json=true","fetch_graph":"https://pith.science/api/pith-number/I2YEYY74LR57TX6IJ6WP2GGVOB/graph.json","fetch_events":"https://pith.science/api/pith-number/I2YEYY74LR57TX6IJ6WP2GGVOB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I2YEYY74LR57TX6IJ6WP2GGVOB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I2YEYY74LR57TX6IJ6WP2GGVOB/action/storage_attestation","attest_author":"https://pith.science/pith/I2YEYY74LR57TX6IJ6WP2GGVOB/action/author_attestation","sign_citation":"https://pith.science/pith/I2YEYY74LR57TX6IJ6WP2GGVOB/action/citation_signature","submit_replication":"https://pith.science/pith/I2YEYY74LR57TX6IJ6WP2GGVOB/action/replication_record"}},"created_at":"2026-05-18T02:31:30.942306+00:00","updated_at":"2026-05-18T02:31:30.942306+00:00"}