{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MHD2MRLP5FU3LXJBC2G4NAPALC","short_pith_number":"pith:MHD2MRLP","schema_version":"1.0","canonical_sha256":"61c7a6456fe969b5dd21168dc681e058975886324e90ee51a9db72446ca624c4","source":{"kind":"arxiv","id":"1911.11756","version":1},"attestation_state":"computed","paper":{"title":"Semi-Supervised Learning for Text Classification by Layer Partitioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhinav Sethy, Alexander Hanbo Li","submitted_at":"2019-11-26T18:47:48Z","abstract_excerpt":"Most recent neural semi-supervised learning algorithms rely on adding small perturbation to either the input vectors or their representations. These methods have been successful on computer vision tasks as the images form a continuous manifold, but are not appropriate for discrete input such as sentence. To adapt these methods to text input, we propose to decompose a neural network $M$ into two components $F$ and $U$ so that $M = U\\circ F$. The layers in $F$ are then frozen and only the layers in $U$ will be updated during most time of the training. In this way, $F$ serves as a feature extract"},"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":"1911.11756","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-26T18:47:48Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"4db8b97e5f4653e577264960499f02660d28ec66d02f57cf677b532de2703481","abstract_canon_sha256":"a6910fc5fa1a26defde2d3751367afcf228cb38db152ca05f76544d2d664e783"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:22:12.849632Z","signature_b64":"OG5K6fQ0t9MO2rmL3aMp8TUdhL/xAeNmbEUGo/SgxrmPo6cf0tLCoh/bmhSBFiOv4fc7tNVAbz6SBG4J4rJNCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61c7a6456fe969b5dd21168dc681e058975886324e90ee51a9db72446ca624c4","last_reissued_at":"2026-07-05T00:22:12.849235Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:22:12.849235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-Supervised Learning for Text Classification by Layer Partitioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhinav Sethy, Alexander Hanbo Li","submitted_at":"2019-11-26T18:47:48Z","abstract_excerpt":"Most recent neural semi-supervised learning algorithms rely on adding small perturbation to either the input vectors or their representations. These methods have been successful on computer vision tasks as the images form a continuous manifold, but are not appropriate for discrete input such as sentence. To adapt these methods to text input, we propose to decompose a neural network $M$ into two components $F$ and $U$ so that $M = U\\circ F$. The layers in $F$ are then frozen and only the layers in $U$ will be updated during most time of the training. In this way, $F$ serves as a feature extract"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.11756","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/1911.11756/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":"1911.11756","created_at":"2026-07-05T00:22:12.849291+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.11756v1","created_at":"2026-07-05T00:22:12.849291+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.11756","created_at":"2026-07-05T00:22:12.849291+00:00"},{"alias_kind":"pith_short_12","alias_value":"MHD2MRLP5FU3","created_at":"2026-07-05T00:22:12.849291+00:00"},{"alias_kind":"pith_short_16","alias_value":"MHD2MRLP5FU3LXJB","created_at":"2026-07-05T00:22:12.849291+00:00"},{"alias_kind":"pith_short_8","alias_value":"MHD2MRLP","created_at":"2026-07-05T00:22:12.849291+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/MHD2MRLP5FU3LXJBC2G4NAPALC","json":"https://pith.science/pith/MHD2MRLP5FU3LXJBC2G4NAPALC.json","graph_json":"https://pith.science/api/pith-number/MHD2MRLP5FU3LXJBC2G4NAPALC/graph.json","events_json":"https://pith.science/api/pith-number/MHD2MRLP5FU3LXJBC2G4NAPALC/events.json","paper":"https://pith.science/paper/MHD2MRLP"},"agent_actions":{"view_html":"https://pith.science/pith/MHD2MRLP5FU3LXJBC2G4NAPALC","download_json":"https://pith.science/pith/MHD2MRLP5FU3LXJBC2G4NAPALC.json","view_paper":"https://pith.science/paper/MHD2MRLP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.11756&json=true","fetch_graph":"https://pith.science/api/pith-number/MHD2MRLP5FU3LXJBC2G4NAPALC/graph.json","fetch_events":"https://pith.science/api/pith-number/MHD2MRLP5FU3LXJBC2G4NAPALC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MHD2MRLP5FU3LXJBC2G4NAPALC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MHD2MRLP5FU3LXJBC2G4NAPALC/action/storage_attestation","attest_author":"https://pith.science/pith/MHD2MRLP5FU3LXJBC2G4NAPALC/action/author_attestation","sign_citation":"https://pith.science/pith/MHD2MRLP5FU3LXJBC2G4NAPALC/action/citation_signature","submit_replication":"https://pith.science/pith/MHD2MRLP5FU3LXJBC2G4NAPALC/action/replication_record"}},"created_at":"2026-07-05T00:22:12.849291+00:00","updated_at":"2026-07-05T00:22:12.849291+00:00"}