{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LBWH2NZQKVLPFNCSLVMQPEROCZ","short_pith_number":"pith:LBWH2NZQ","schema_version":"1.0","canonical_sha256":"586c7d37305556f2b4525d5907922e166431579fb59d629d4862cfd2a0f89c60","source":{"kind":"arxiv","id":"1911.07518","version":1},"attestation_state":"computed","paper":{"title":"Constructing Multiple Tasks for Augmentation: Improving Neural Image Classification With K-means Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Yan, Jiacheng Ye, Lizhi Qing, Qi Zhang, Tao Gui, Xuanjing Huang, Zichu Fei","submitted_at":"2019-11-18T10:04:08Z","abstract_excerpt":"Multi-task learning (MTL) has received considerable attention, and numerous deep learning applications benefit from MTL with multiple objectives. However, constructing multiple related tasks is difficult, and sometimes only a single task is available for training in a dataset. To tackle this problem, we explored the idea of using unsupervised clustering to construct a variety of auxiliary tasks from unlabeled data or existing labeled data. We found that some of these newly constructed tasks could exhibit semantic meanings corresponding to certain human-specific attributes, but some were non-id"},"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":"1911.07518","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-18T10:04:08Z","cross_cats_sorted":[],"title_canon_sha256":"3b97255235cf5bf621b0ae7636efa2b7a46d008ce6a7feee825621d4563903bf","abstract_canon_sha256":"3fd36140896c80d625c6d2b3470661988e0646108b13a0d0b755cf21ef78a0fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:21:16.628339Z","signature_b64":"7P3k63CftuUvjkNS1hHCbhltaiHd3ovGLSU0pdbMH1FjcPzND9xSuoCwmXAKiSl6q/k0PdZr8Xz9oH7R1tQoBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"586c7d37305556f2b4525d5907922e166431579fb59d629d4862cfd2a0f89c60","last_reissued_at":"2026-07-05T00:21:16.627875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:21:16.627875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constructing Multiple Tasks for Augmentation: Improving Neural Image Classification With K-means Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Yan, Jiacheng Ye, Lizhi Qing, Qi Zhang, Tao Gui, Xuanjing Huang, Zichu Fei","submitted_at":"2019-11-18T10:04:08Z","abstract_excerpt":"Multi-task learning (MTL) has received considerable attention, and numerous deep learning applications benefit from MTL with multiple objectives. However, constructing multiple related tasks is difficult, and sometimes only a single task is available for training in a dataset. To tackle this problem, we explored the idea of using unsupervised clustering to construct a variety of auxiliary tasks from unlabeled data or existing labeled data. We found that some of these newly constructed tasks could exhibit semantic meanings corresponding to certain human-specific attributes, but some were non-id"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.07518","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/1911.07518/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":"1911.07518","created_at":"2026-07-05T00:21:16.627935+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.07518v1","created_at":"2026-07-05T00:21:16.627935+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.07518","created_at":"2026-07-05T00:21:16.627935+00:00"},{"alias_kind":"pith_short_12","alias_value":"LBWH2NZQKVLP","created_at":"2026-07-05T00:21:16.627935+00:00"},{"alias_kind":"pith_short_16","alias_value":"LBWH2NZQKVLPFNCS","created_at":"2026-07-05T00:21:16.627935+00:00"},{"alias_kind":"pith_short_8","alias_value":"LBWH2NZQ","created_at":"2026-07-05T00:21:16.627935+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/LBWH2NZQKVLPFNCSLVMQPEROCZ","json":"https://pith.science/pith/LBWH2NZQKVLPFNCSLVMQPEROCZ.json","graph_json":"https://pith.science/api/pith-number/LBWH2NZQKVLPFNCSLVMQPEROCZ/graph.json","events_json":"https://pith.science/api/pith-number/LBWH2NZQKVLPFNCSLVMQPEROCZ/events.json","paper":"https://pith.science/paper/LBWH2NZQ"},"agent_actions":{"view_html":"https://pith.science/pith/LBWH2NZQKVLPFNCSLVMQPEROCZ","download_json":"https://pith.science/pith/LBWH2NZQKVLPFNCSLVMQPEROCZ.json","view_paper":"https://pith.science/paper/LBWH2NZQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.07518&json=true","fetch_graph":"https://pith.science/api/pith-number/LBWH2NZQKVLPFNCSLVMQPEROCZ/graph.json","fetch_events":"https://pith.science/api/pith-number/LBWH2NZQKVLPFNCSLVMQPEROCZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LBWH2NZQKVLPFNCSLVMQPEROCZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LBWH2NZQKVLPFNCSLVMQPEROCZ/action/storage_attestation","attest_author":"https://pith.science/pith/LBWH2NZQKVLPFNCSLVMQPEROCZ/action/author_attestation","sign_citation":"https://pith.science/pith/LBWH2NZQKVLPFNCSLVMQPEROCZ/action/citation_signature","submit_replication":"https://pith.science/pith/LBWH2NZQKVLPFNCSLVMQPEROCZ/action/replication_record"}},"created_at":"2026-07-05T00:21:16.627935+00:00","updated_at":"2026-07-05T00:21:16.627935+00:00"}