{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CZBIAOS5O3LXRW2KG2IYD56ESL","short_pith_number":"pith:CZBIAOS5","schema_version":"1.0","canonical_sha256":"1642803a5d76d778db4a369181f7c492eace535d751acab2de3278666b5ba6b2","source":{"kind":"arxiv","id":"2211.13976","version":6},"attestation_state":"computed","paper":{"title":"Expanding Small-Scale Datasets with Guided Imagination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bryan Hooi, Daquan Zhou, Jiashi Feng, Kai Wang, Yifan Zhang","submitted_at":"2022-11-25T09:38:22Z","abstract_excerpt":"The power of DNNs relies heavily on the quantity and quality of training data. However, collecting and annotating data on a large scale is often expensive and time-consuming. To address this issue, we explore a new task, termed dataset expansion, aimed at expanding a ready-to-use small dataset by automatically creating new labeled samples. To this end, we present a Guided Imagination Framework (GIF) that leverages cutting-edge generative models like DALL-E2 and Stable Diffusion (SD) to \"imagine\" and create informative new data from the input seed data. Specifically, GIF conducts data imaginati"},"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":"2211.13976","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-25T09:38:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"15cbdcec9d881a9d556fe5d65a57c4e25bcfb8e55134be3544e8f3bc89820170","abstract_canon_sha256":"82a0b46b099c7235168347b21975aa417bda495ab2a1c376989ab7aee959429e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:58:54.171834Z","signature_b64":"5Ht4roWnR50jgDFz2XSzYL39GMyZQTaU2AlNmtiooMDPh5UZJJyIO6pV+NZfnPI3U+/t+JbbdO6eyuAJdVR4BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1642803a5d76d778db4a369181f7c492eace535d751acab2de3278666b5ba6b2","last_reissued_at":"2026-07-05T06:58:54.171339Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:58:54.171339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Expanding Small-Scale Datasets with Guided Imagination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bryan Hooi, Daquan Zhou, Jiashi Feng, Kai Wang, Yifan Zhang","submitted_at":"2022-11-25T09:38:22Z","abstract_excerpt":"The power of DNNs relies heavily on the quantity and quality of training data. However, collecting and annotating data on a large scale is often expensive and time-consuming. To address this issue, we explore a new task, termed dataset expansion, aimed at expanding a ready-to-use small dataset by automatically creating new labeled samples. To this end, we present a Guided Imagination Framework (GIF) that leverages cutting-edge generative models like DALL-E2 and Stable Diffusion (SD) to \"imagine\" and create informative new data from the input seed data. Specifically, GIF conducts data imaginati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.13976","kind":"arxiv","version":6},"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/2211.13976/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":"2211.13976","created_at":"2026-07-05T06:58:54.171395+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.13976v6","created_at":"2026-07-05T06:58:54.171395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.13976","created_at":"2026-07-05T06:58:54.171395+00:00"},{"alias_kind":"pith_short_12","alias_value":"CZBIAOS5O3LX","created_at":"2026-07-05T06:58:54.171395+00:00"},{"alias_kind":"pith_short_16","alias_value":"CZBIAOS5O3LXRW2K","created_at":"2026-07-05T06:58:54.171395+00:00"},{"alias_kind":"pith_short_8","alias_value":"CZBIAOS5","created_at":"2026-07-05T06:58:54.171395+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.18926","citing_title":"Data Augmentation with Diffusion Models for Colon Polyp Localization on the Low Data Regime: How much real data is enough?","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CZBIAOS5O3LXRW2KG2IYD56ESL","json":"https://pith.science/pith/CZBIAOS5O3LXRW2KG2IYD56ESL.json","graph_json":"https://pith.science/api/pith-number/CZBIAOS5O3LXRW2KG2IYD56ESL/graph.json","events_json":"https://pith.science/api/pith-number/CZBIAOS5O3LXRW2KG2IYD56ESL/events.json","paper":"https://pith.science/paper/CZBIAOS5"},"agent_actions":{"view_html":"https://pith.science/pith/CZBIAOS5O3LXRW2KG2IYD56ESL","download_json":"https://pith.science/pith/CZBIAOS5O3LXRW2KG2IYD56ESL.json","view_paper":"https://pith.science/paper/CZBIAOS5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.13976&json=true","fetch_graph":"https://pith.science/api/pith-number/CZBIAOS5O3LXRW2KG2IYD56ESL/graph.json","fetch_events":"https://pith.science/api/pith-number/CZBIAOS5O3LXRW2KG2IYD56ESL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CZBIAOS5O3LXRW2KG2IYD56ESL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CZBIAOS5O3LXRW2KG2IYD56ESL/action/storage_attestation","attest_author":"https://pith.science/pith/CZBIAOS5O3LXRW2KG2IYD56ESL/action/author_attestation","sign_citation":"https://pith.science/pith/CZBIAOS5O3LXRW2KG2IYD56ESL/action/citation_signature","submit_replication":"https://pith.science/pith/CZBIAOS5O3LXRW2KG2IYD56ESL/action/replication_record"}},"created_at":"2026-07-05T06:58:54.171395+00:00","updated_at":"2026-07-05T06:58:54.171395+00:00"}