{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LMERSWYLJ26R4NYQR6PN5T5JSW","short_pith_number":"pith:LMERSWYL","schema_version":"1.0","canonical_sha256":"5b09195b0b4ebd1e37108f9edecfa995a5125cb4c8a34ab411c323e4fda3099b","source":{"kind":"arxiv","id":"2407.00478","version":3},"attestation_state":"computed","paper":{"title":"Beyond Scaleup: Knowledge-aware Parsimony Learning from Deep Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"James Kwok, Nan Yin, Qiang Yang, Quanming Yao, Yaqing Wang, Yongqi Zhang","submitted_at":"2024-06-29T15:52:37Z","abstract_excerpt":"The brute-force scaleup of training datasets, learnable parameters and computation power, has become a prevalent strategy for developing more robust learning models. However, due to bottlenecks in data, computation, and trust, the sustainability of this strategy is a serious concern. In this paper, we attempt to address this issue in a parsimonious manner (i.e., achieving greater potential with simpler models). The key is to drive models using domain-specific knowledge, such as symbols, logic, and formulas, instead of purely relying on scaleup. This approach allows us to build a framework that"},"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":"2407.00478","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-29T15:52:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"452c23d25acf5ac65dd496f2ecd17073231f8f651f39e108fce0c3dd60d7a3cd","abstract_canon_sha256":"5bb992f8bcdc104421ee4bf774dd654eb391567c7b67ab202d74354b6a81874b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:03.604560Z","signature_b64":"eLD2O16Kw/qbCqwDJqb9L6PrVhR7h4ODyJF0JlD1fuTMiYvPvHjPNN6cdWYdhM4fTGdKyLWZR0PxiLgHKocRCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b09195b0b4ebd1e37108f9edecfa995a5125cb4c8a34ab411c323e4fda3099b","last_reissued_at":"2026-07-05T09:50:03.604061Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:03.604061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Scaleup: Knowledge-aware Parsimony Learning from Deep Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"James Kwok, Nan Yin, Qiang Yang, Quanming Yao, Yaqing Wang, Yongqi Zhang","submitted_at":"2024-06-29T15:52:37Z","abstract_excerpt":"The brute-force scaleup of training datasets, learnable parameters and computation power, has become a prevalent strategy for developing more robust learning models. However, due to bottlenecks in data, computation, and trust, the sustainability of this strategy is a serious concern. In this paper, we attempt to address this issue in a parsimonious manner (i.e., achieving greater potential with simpler models). The key is to drive models using domain-specific knowledge, such as symbols, logic, and formulas, instead of purely relying on scaleup. This approach allows us to build a framework that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00478","kind":"arxiv","version":3},"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/2407.00478/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":"2407.00478","created_at":"2026-07-05T09:50:03.604119+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.00478v3","created_at":"2026-07-05T09:50:03.604119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00478","created_at":"2026-07-05T09:50:03.604119+00:00"},{"alias_kind":"pith_short_12","alias_value":"LMERSWYLJ26R","created_at":"2026-07-05T09:50:03.604119+00:00"},{"alias_kind":"pith_short_16","alias_value":"LMERSWYLJ26R4NYQ","created_at":"2026-07-05T09:50:03.604119+00:00"},{"alias_kind":"pith_short_8","alias_value":"LMERSWYL","created_at":"2026-07-05T09:50:03.604119+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.00933","citing_title":"OKG-LLM: Aligning Ocean Knowledge Graph with Observation Data via LLMs for Global Sea Surface Temperature Prediction","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LMERSWYLJ26R4NYQR6PN5T5JSW","json":"https://pith.science/pith/LMERSWYLJ26R4NYQR6PN5T5JSW.json","graph_json":"https://pith.science/api/pith-number/LMERSWYLJ26R4NYQR6PN5T5JSW/graph.json","events_json":"https://pith.science/api/pith-number/LMERSWYLJ26R4NYQR6PN5T5JSW/events.json","paper":"https://pith.science/paper/LMERSWYL"},"agent_actions":{"view_html":"https://pith.science/pith/LMERSWYLJ26R4NYQR6PN5T5JSW","download_json":"https://pith.science/pith/LMERSWYLJ26R4NYQR6PN5T5JSW.json","view_paper":"https://pith.science/paper/LMERSWYL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.00478&json=true","fetch_graph":"https://pith.science/api/pith-number/LMERSWYLJ26R4NYQR6PN5T5JSW/graph.json","fetch_events":"https://pith.science/api/pith-number/LMERSWYLJ26R4NYQR6PN5T5JSW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LMERSWYLJ26R4NYQR6PN5T5JSW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LMERSWYLJ26R4NYQR6PN5T5JSW/action/storage_attestation","attest_author":"https://pith.science/pith/LMERSWYLJ26R4NYQR6PN5T5JSW/action/author_attestation","sign_citation":"https://pith.science/pith/LMERSWYLJ26R4NYQR6PN5T5JSW/action/citation_signature","submit_replication":"https://pith.science/pith/LMERSWYLJ26R4NYQR6PN5T5JSW/action/replication_record"}},"created_at":"2026-07-05T09:50:03.604119+00:00","updated_at":"2026-07-05T09:50:03.604119+00:00"}