{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:B4B2MAQSL3HSL4TU3RIKZXFJVU","short_pith_number":"pith:B4B2MAQS","schema_version":"1.0","canonical_sha256":"0f03a602125ecf25f274dc50acdca9ad29d56d9a81a32ad131e74a96aeb82e7a","source":{"kind":"arxiv","id":"1803.03635","version":5},"attestation_state":"computed","paper":{"title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Jonathan Frankle, Michael Carbin","submitted_at":"2018-03-09T18:51:28Z","abstract_excerpt":"Neural network pruning techniques can reduce the parameter counts of trained networks by over 90%, decreasing storage requirements and improving computational performance of inference without compromising accuracy. However, contemporary experience is that the sparse architectures produced by pruning are difficult to train from the start, which would similarly improve training performance.\n  We find that a standard pruning technique naturally uncovers subnetworks whose initializations made them capable of training effectively. Based on these results, we articulate the \"lottery ticket hypothesis"},"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":"1803.03635","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-09T18:51:28Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"65d80b721f7d732c280419b550c66348cf0a701c4abf0eb47baa20d23474233a","abstract_canon_sha256":"92dbc5abefc9a86cf8394c7472403193af79f82d5204262ef308757cd3a3f945"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:09.471897Z","signature_b64":"ToBFYe2t8/u85Fe86tzhxd82OG14Ew2KWjyANeU7l1dciIm5vASPxMEQQzsTgAFZ4+8LUnofmKEnxFU+PVdgAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f03a602125ecf25f274dc50acdca9ad29d56d9a81a32ad131e74a96aeb82e7a","last_reissued_at":"2026-05-17T23:52:09.471390Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:09.471390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Jonathan Frankle, Michael Carbin","submitted_at":"2018-03-09T18:51:28Z","abstract_excerpt":"Neural network pruning techniques can reduce the parameter counts of trained networks by over 90%, decreasing storage requirements and improving computational performance of inference without compromising accuracy. However, contemporary experience is that the sparse architectures produced by pruning are difficult to train from the start, which would similarly improve training performance.\n  We find that a standard pruning technique naturally uncovers subnetworks whose initializations made them capable of training effectively. Based on these results, we articulate the \"lottery ticket hypothesis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.03635","kind":"arxiv","version":5},"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":"1803.03635","created_at":"2026-05-17T23:52:09.471475+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.03635v5","created_at":"2026-05-17T23:52:09.471475+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.03635","created_at":"2026-05-17T23:52:09.471475+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4B2MAQSL3HS","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4B2MAQSL3HSL4TU","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4B2MAQS","created_at":"2026-05-18T12:32:13.499390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":40,"internal_anchor_count":22,"sample":[{"citing_arxiv_id":"1906.10771","citing_title":"Importance Estimation for Neural Network Pruning","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2305.07759","citing_title":"TinyStories: How Small Can Language Models Be and Still Speak Coherent English?","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06572","citing_title":"Deep network as memory space: complexity, generalization, disentangled representation and interpretability","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"1907.09881","citing_title":"Convolutional Dictionary Learning in Hierarchical Networks","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2306.00978","citing_title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2309.08600","citing_title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2407.15389","citing_title":"Poisoning with A Pill: Circumventing Detection in Federated Learning","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2409.18169","citing_title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2411.02813","citing_title":"Sparse Orthogonal Parameters Tuning for Continual Learning","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2502.06809","citing_title":"Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18789","citing_title":"Features have life history. And we should care","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16470","citing_title":"Strategic Over-Parameterization for Generalizable Low-Rank Adaptation","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16138","citing_title":"Surrogate Neural Architecture Codesign Package (SNAC-Pack)","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18933","citing_title":"A Geometric Analysis of Sign-Magnitude Asymmetry in a ReLU + RMSNorm Block under Ternary Quantization","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15435","citing_title":"On the Stability of Growth in Structural Plasticity","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2506.12876","citing_title":"MaskPro: Linear-Space Probabilistic Learning for Strict (N:M)-Sparsity on LLMs","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2001.04385","citing_title":"Universal Differential Equations for Scientific Machine Learning","ref_index":123,"is_internal_anchor":true},{"citing_arxiv_id":"2511.09290","citing_title":"Prediction horizon shapes representations in predictive learning","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2310.12508","citing_title":"SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation","ref_index":190,"is_internal_anchor":true},{"citing_arxiv_id":"2603.15757","citing_title":"You've Got a Golden Ticket: Improving Generative Robot Policies With A Single Noise Vector","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2603.24654","citing_title":"Spectral methods: crucial for machine learning, natural for quantum computers?","ref_index":72,"is_internal_anchor":true},{"citing_arxiv_id":"2301.05217","citing_title":"Progress measures for grokking via mechanistic interpretability","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03132","citing_title":"Minimal Information Control Invariance via Vector Quantization","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04988","citing_title":"Prune-Quantize-Distill: An Ordered Pipeline for Efficient Neural Network Compression","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2403.14608","citing_title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","ref_index":107,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B4B2MAQSL3HSL4TU3RIKZXFJVU","json":"https://pith.science/pith/B4B2MAQSL3HSL4TU3RIKZXFJVU.json","graph_json":"https://pith.science/api/pith-number/B4B2MAQSL3HSL4TU3RIKZXFJVU/graph.json","events_json":"https://pith.science/api/pith-number/B4B2MAQSL3HSL4TU3RIKZXFJVU/events.json","paper":"https://pith.science/paper/B4B2MAQS"},"agent_actions":{"view_html":"https://pith.science/pith/B4B2MAQSL3HSL4TU3RIKZXFJVU","download_json":"https://pith.science/pith/B4B2MAQSL3HSL4TU3RIKZXFJVU.json","view_paper":"https://pith.science/paper/B4B2MAQS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.03635&json=true","fetch_graph":"https://pith.science/api/pith-number/B4B2MAQSL3HSL4TU3RIKZXFJVU/graph.json","fetch_events":"https://pith.science/api/pith-number/B4B2MAQSL3HSL4TU3RIKZXFJVU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4B2MAQSL3HSL4TU3RIKZXFJVU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4B2MAQSL3HSL4TU3RIKZXFJVU/action/storage_attestation","attest_author":"https://pith.science/pith/B4B2MAQSL3HSL4TU3RIKZXFJVU/action/author_attestation","sign_citation":"https://pith.science/pith/B4B2MAQSL3HSL4TU3RIKZXFJVU/action/citation_signature","submit_replication":"https://pith.science/pith/B4B2MAQSL3HSL4TU3RIKZXFJVU/action/replication_record"}},"created_at":"2026-05-17T23:52:09.471475+00:00","updated_at":"2026-05-17T23:52:09.471475+00:00"}