{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7MAU6ZMBCM4WOOSETBYLTOG73M","short_pith_number":"pith:7MAU6ZMB","schema_version":"1.0","canonical_sha256":"fb014f65811339673a449870b9b8dfdb154c39fc9c5943cd682c37c1e621b983","source":{"kind":"arxiv","id":"2508.19873","version":1},"attestation_state":"computed","paper":{"title":"Beyond Shallow Heuristics: Leveraging Human Intuition for Curriculum Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christian Bauckhage, Sebastian M\\\"uller, Tam\\'as Horv\\'ath, Tim Selbach, Vanessa Toborek","submitted_at":"2025-08-27T13:35:13Z","abstract_excerpt":"Curriculum learning (CL) aims to improve training by presenting data from \"easy\" to \"hard\", yet defining and measuring linguistic difficulty remains an open challenge. We investigate whether human-curated simple language can serve as an effective signal for CL. Using the article-level labels from the Simple Wikipedia corpus, we compare label-based curricula to competence-based strategies relying on shallow heuristics. Our experiments with a BERT-tiny model show that adding simple data alone yields no clear benefit. However, structuring it via a curriculum -- especially when introduced first --"},"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":"2508.19873","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-27T13:35:13Z","cross_cats_sorted":[],"title_canon_sha256":"cf5dc4a03a2192e7cd2a5d0536020a89455c760039b745a9390134d0f9b8787e","abstract_canon_sha256":"887dfdb6b9d9d188ba0de1a4c9495ad438850fdde394371d88c8bea52e994096"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:19.170753Z","signature_b64":"Pzc0q04vOgTTDYJZVH5TGWJsAaZ5EpM0D2ly7hnvvuHO5AwSyBOckg++YX7HiacNVUTI9epZZeR08qhfkzO6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb014f65811339673a449870b9b8dfdb154c39fc9c5943cd682c37c1e621b983","last_reissued_at":"2026-07-05T12:00:19.170293Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:19.170293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Shallow Heuristics: Leveraging Human Intuition for Curriculum Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christian Bauckhage, Sebastian M\\\"uller, Tam\\'as Horv\\'ath, Tim Selbach, Vanessa Toborek","submitted_at":"2025-08-27T13:35:13Z","abstract_excerpt":"Curriculum learning (CL) aims to improve training by presenting data from \"easy\" to \"hard\", yet defining and measuring linguistic difficulty remains an open challenge. We investigate whether human-curated simple language can serve as an effective signal for CL. Using the article-level labels from the Simple Wikipedia corpus, we compare label-based curricula to competence-based strategies relying on shallow heuristics. Our experiments with a BERT-tiny model show that adding simple data alone yields no clear benefit. However, structuring it via a curriculum -- especially when introduced first --"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19873","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/2508.19873/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":"2508.19873","created_at":"2026-07-05T12:00:19.170359+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.19873v1","created_at":"2026-07-05T12:00:19.170359+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19873","created_at":"2026-07-05T12:00:19.170359+00:00"},{"alias_kind":"pith_short_12","alias_value":"7MAU6ZMBCM4W","created_at":"2026-07-05T12:00:19.170359+00:00"},{"alias_kind":"pith_short_16","alias_value":"7MAU6ZMBCM4WOOSE","created_at":"2026-07-05T12:00:19.170359+00:00"},{"alias_kind":"pith_short_8","alias_value":"7MAU6ZMB","created_at":"2026-07-05T12:00:19.170359+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/7MAU6ZMBCM4WOOSETBYLTOG73M","json":"https://pith.science/pith/7MAU6ZMBCM4WOOSETBYLTOG73M.json","graph_json":"https://pith.science/api/pith-number/7MAU6ZMBCM4WOOSETBYLTOG73M/graph.json","events_json":"https://pith.science/api/pith-number/7MAU6ZMBCM4WOOSETBYLTOG73M/events.json","paper":"https://pith.science/paper/7MAU6ZMB"},"agent_actions":{"view_html":"https://pith.science/pith/7MAU6ZMBCM4WOOSETBYLTOG73M","download_json":"https://pith.science/pith/7MAU6ZMBCM4WOOSETBYLTOG73M.json","view_paper":"https://pith.science/paper/7MAU6ZMB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.19873&json=true","fetch_graph":"https://pith.science/api/pith-number/7MAU6ZMBCM4WOOSETBYLTOG73M/graph.json","fetch_events":"https://pith.science/api/pith-number/7MAU6ZMBCM4WOOSETBYLTOG73M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7MAU6ZMBCM4WOOSETBYLTOG73M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7MAU6ZMBCM4WOOSETBYLTOG73M/action/storage_attestation","attest_author":"https://pith.science/pith/7MAU6ZMBCM4WOOSETBYLTOG73M/action/author_attestation","sign_citation":"https://pith.science/pith/7MAU6ZMBCM4WOOSETBYLTOG73M/action/citation_signature","submit_replication":"https://pith.science/pith/7MAU6ZMBCM4WOOSETBYLTOG73M/action/replication_record"}},"created_at":"2026-07-05T12:00:19.170359+00:00","updated_at":"2026-07-05T12:00:19.170359+00:00"}