{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XGQ6223FAS3BCPCNT7RJSSAQAL","short_pith_number":"pith:XGQ6223F","schema_version":"1.0","canonical_sha256":"b9a1ed6b6504b6113c4d9fe299481002d5c590323ba1967e9c0ccf745feae8ba","source":{"kind":"arxiv","id":"2408.14381","version":1},"attestation_state":"computed","paper":{"title":"Learning Tree-Structured Composition of Data Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.DS"],"primary_cat":"cs.LG","authors_text":"Dongyue Li, Hongyang R. Zhang, Kailai Chen, Predrag Radivojac","submitted_at":"2024-08-26T16:04:13Z","abstract_excerpt":"Data augmentation is widely used for training a neural network given little labeled data. A common practice of augmentation training is applying a composition of multiple transformations sequentially to the data. Existing augmentation methods such as RandAugment randomly sample from a list of pre-selected transformations, while methods such as AutoAugment apply advanced search to optimize over an augmentation set of size $k^d$, which is the number of transformation sequences of length $d$, given a list of $k$ transformations.\n  In this paper, we design efficient algorithms whose running time c"},"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":"2408.14381","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-26T16:04:13Z","cross_cats_sorted":["cs.CV","cs.DS"],"title_canon_sha256":"a76394682b16977bc39e25e3bbfa7711abc8f2f5acd2960e9385729985f2af63","abstract_canon_sha256":"51977502ab22f2e1438105fccef4fb224b8554c4c51d66c8e1c373c7a366ecd5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:20.051788Z","signature_b64":"NBrEM4xoY19uFEoHragCIUvjwVbk74npUygrS+QKWOzuWvGSZvQkFUU+hQco0ts6/I9x2Cj+wYhShnruBjifDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9a1ed6b6504b6113c4d9fe299481002d5c590323ba1967e9c0ccf745feae8ba","last_reissued_at":"2026-07-05T08:59:20.051363Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:20.051363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Tree-Structured Composition of Data Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.DS"],"primary_cat":"cs.LG","authors_text":"Dongyue Li, Hongyang R. Zhang, Kailai Chen, Predrag Radivojac","submitted_at":"2024-08-26T16:04:13Z","abstract_excerpt":"Data augmentation is widely used for training a neural network given little labeled data. A common practice of augmentation training is applying a composition of multiple transformations sequentially to the data. Existing augmentation methods such as RandAugment randomly sample from a list of pre-selected transformations, while methods such as AutoAugment apply advanced search to optimize over an augmentation set of size $k^d$, which is the number of transformation sequences of length $d$, given a list of $k$ transformations.\n  In this paper, we design efficient algorithms whose running time c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14381","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/2408.14381/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":"2408.14381","created_at":"2026-07-05T08:59:20.051419+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.14381v1","created_at":"2026-07-05T08:59:20.051419+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14381","created_at":"2026-07-05T08:59:20.051419+00:00"},{"alias_kind":"pith_short_12","alias_value":"XGQ6223FAS3B","created_at":"2026-07-05T08:59:20.051419+00:00"},{"alias_kind":"pith_short_16","alias_value":"XGQ6223FAS3BCPCN","created_at":"2026-07-05T08:59:20.051419+00:00"},{"alias_kind":"pith_short_8","alias_value":"XGQ6223F","created_at":"2026-07-05T08:59:20.051419+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/XGQ6223FAS3BCPCNT7RJSSAQAL","json":"https://pith.science/pith/XGQ6223FAS3BCPCNT7RJSSAQAL.json","graph_json":"https://pith.science/api/pith-number/XGQ6223FAS3BCPCNT7RJSSAQAL/graph.json","events_json":"https://pith.science/api/pith-number/XGQ6223FAS3BCPCNT7RJSSAQAL/events.json","paper":"https://pith.science/paper/XGQ6223F"},"agent_actions":{"view_html":"https://pith.science/pith/XGQ6223FAS3BCPCNT7RJSSAQAL","download_json":"https://pith.science/pith/XGQ6223FAS3BCPCNT7RJSSAQAL.json","view_paper":"https://pith.science/paper/XGQ6223F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.14381&json=true","fetch_graph":"https://pith.science/api/pith-number/XGQ6223FAS3BCPCNT7RJSSAQAL/graph.json","fetch_events":"https://pith.science/api/pith-number/XGQ6223FAS3BCPCNT7RJSSAQAL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XGQ6223FAS3BCPCNT7RJSSAQAL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XGQ6223FAS3BCPCNT7RJSSAQAL/action/storage_attestation","attest_author":"https://pith.science/pith/XGQ6223FAS3BCPCNT7RJSSAQAL/action/author_attestation","sign_citation":"https://pith.science/pith/XGQ6223FAS3BCPCNT7RJSSAQAL/action/citation_signature","submit_replication":"https://pith.science/pith/XGQ6223FAS3BCPCNT7RJSSAQAL/action/replication_record"}},"created_at":"2026-07-05T08:59:20.051419+00:00","updated_at":"2026-07-05T08:59:20.051419+00:00"}