{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:AW6HF2JFJCKVBM3CUOV33HKSK2","short_pith_number":"pith:AW6HF2JF","schema_version":"1.0","canonical_sha256":"05bc72e925489550b362a3abbd9d5256b561262ec828dc5abda2e6a618213e24","source":{"kind":"arxiv","id":"1804.08838","version":1},"attestation_state":"computed","paper":{"title":"Measuring the Intrinsic Dimension of Objective Landscapes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chunyuan Li, Heerad Farkhoor, Jason Yosinski, Rosanne Liu","submitted_at":"2018-04-24T04:29:10Z","abstract_excerpt":"Many recently trained neural networks employ large numbers of parameters to achieve good performance. One may intuitively use the number of parameters required as a rough gauge of the difficulty of a problem. But how accurate are such notions? How many parameters are really needed? In this paper we attempt to answer this question by training networks not in their native parameter space, but instead in a smaller, randomly oriented subspace. We slowly increase the dimension of this subspace, note at which dimension solutions first appear, and define this to be the intrinsic dimension of the obje"},"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":"1804.08838","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-24T04:29:10Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"920182f69016997d2d9ada665feb1e0a5e5d82ea5f7b9760172506587cba0e2c","abstract_canon_sha256":"ededf294315ae664c5c405a1a4203a7ee62a251f2c4e5b82609b39be259d3728"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:37.149953Z","signature_b64":"kSuUtkdyEANpaQ/Z17xW8yZVKmGf+Wg9Hc1mI+35D8e1lYYM3Q5Lxb/aEnimAiVK1n9nJ/rbEJwCNY6N5/NHDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05bc72e925489550b362a3abbd9d5256b561262ec828dc5abda2e6a618213e24","last_reissued_at":"2026-05-18T00:17:37.149222Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:37.149222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Measuring the Intrinsic Dimension of Objective Landscapes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chunyuan Li, Heerad Farkhoor, Jason Yosinski, Rosanne Liu","submitted_at":"2018-04-24T04:29:10Z","abstract_excerpt":"Many recently trained neural networks employ large numbers of parameters to achieve good performance. One may intuitively use the number of parameters required as a rough gauge of the difficulty of a problem. But how accurate are such notions? How many parameters are really needed? In this paper we attempt to answer this question by training networks not in their native parameter space, but instead in a smaller, randomly oriented subspace. We slowly increase the dimension of this subspace, note at which dimension solutions first appear, and define this to be the intrinsic dimension of the obje"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.08838","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":""},"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":"1804.08838","created_at":"2026-05-18T00:17:37.149334+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.08838v1","created_at":"2026-05-18T00:17:37.149334+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.08838","created_at":"2026-05-18T00:17:37.149334+00:00"},{"alias_kind":"pith_short_12","alias_value":"AW6HF2JFJCKV","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"AW6HF2JFJCKVBM3C","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"AW6HF2JF","created_at":"2026-05-18T12:32:13.499390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":8,"sample":[{"citing_arxiv_id":"1907.06374","citing_title":"What does it mean to understand a neural network?","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"1907.11879","citing_title":"Multi-task Self-Supervised Learning for Human Activity Detection","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2506.21035","citing_title":"Little by Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2509.18629","citing_title":"HyperAdapt: Simple High-Rank Adaptation","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2510.01105","citing_title":"Geometric Analysis of Neural Regression Collapse via Intrinsic Dimension","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2102.01293","citing_title":"Scaling Laws for Transfer","ref_index":132,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06179","citing_title":"ARIA: Adaptive Retrieval Intelligence Assistant -- A Multimodal RAG Framework for Domain-Specific Engineering Education","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2305.14233","citing_title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations","ref_index":182,"is_internal_anchor":true},{"citing_arxiv_id":"2604.00779","citing_title":"Using predefined vector systems to speed up neural network multimillion class classification","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11142","citing_title":"Rank Is Not Capacity: Spectral Occupancy for Latent Graph Models","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2112.00861","citing_title":"A General Language Assistant as a Laboratory for Alignment","ref_index":174,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07302","citing_title":"Pretraining Induces a Reusable Spectral Basis for Downstream Task Adaptation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2207.05221","citing_title":"Language Models (Mostly) Know What They Know","ref_index":251,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18124","citing_title":"TLoRA: Task-aware Low Rank Adaptation of Large Language Models","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2106.09685","citing_title":"LoRA: Low-Rank Adaptation of Large Language Models","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AW6HF2JFJCKVBM3CUOV33HKSK2","json":"https://pith.science/pith/AW6HF2JFJCKVBM3CUOV33HKSK2.json","graph_json":"https://pith.science/api/pith-number/AW6HF2JFJCKVBM3CUOV33HKSK2/graph.json","events_json":"https://pith.science/api/pith-number/AW6HF2JFJCKVBM3CUOV33HKSK2/events.json","paper":"https://pith.science/paper/AW6HF2JF"},"agent_actions":{"view_html":"https://pith.science/pith/AW6HF2JFJCKVBM3CUOV33HKSK2","download_json":"https://pith.science/pith/AW6HF2JFJCKVBM3CUOV33HKSK2.json","view_paper":"https://pith.science/paper/AW6HF2JF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.08838&json=true","fetch_graph":"https://pith.science/api/pith-number/AW6HF2JFJCKVBM3CUOV33HKSK2/graph.json","fetch_events":"https://pith.science/api/pith-number/AW6HF2JFJCKVBM3CUOV33HKSK2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AW6HF2JFJCKVBM3CUOV33HKSK2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AW6HF2JFJCKVBM3CUOV33HKSK2/action/storage_attestation","attest_author":"https://pith.science/pith/AW6HF2JFJCKVBM3CUOV33HKSK2/action/author_attestation","sign_citation":"https://pith.science/pith/AW6HF2JFJCKVBM3CUOV33HKSK2/action/citation_signature","submit_replication":"https://pith.science/pith/AW6HF2JFJCKVBM3CUOV33HKSK2/action/replication_record"}},"created_at":"2026-05-18T00:17:37.149334+00:00","updated_at":"2026-05-18T00:17:37.149334+00:00"}