{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:X2642MPK3BQST7H3E7BX2HBTK5","short_pith_number":"pith:X2642MPK","schema_version":"1.0","canonical_sha256":"bebdcd31ead86129fcfb27c37d1c335749e7b5e7cff524dfbadeb9182238d02b","source":{"kind":"arxiv","id":"2204.02965","version":1},"attestation_state":"computed","paper":{"title":"LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Kamal Gupta, Saurabh Singh, Sharath Girish","submitted_at":"2022-04-06T17:59:10Z","abstract_excerpt":"We introduce LilNetX, an end-to-end trainable technique for neural networks that enables learning models with specified accuracy-rate-computation trade-off. Prior works approach these problems one at a time and often require post-processing or multistage training which become less practical and do not scale very well for large datasets or architectures. Our method constructs a joint training objective that penalizes the self-information of network parameters in a reparameterized latent space to encourage small model size while also introducing priors to increase structured sparsity in the para"},"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":"2204.02965","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-06T17:59:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"99f072d1b26f52cf0ed03e06c4c22c0874e6b222dd3148b737a943615c87fe2e","abstract_canon_sha256":"a63bce634ef336a3ab0adb26dae1be1efca035988ddc37d91fc4234a982a69d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:12:14.074585Z","signature_b64":"5KWL0O6kBurSMpFX8O9181n1QxO7CktK9ABuBN3G3Q0Ya5DdwLKUM2NX+6e4rXlNRsS71ybi9GAgAp6ioL+ADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bebdcd31ead86129fcfb27c37d1c335749e7b5e7cff524dfbadeb9182238d02b","last_reissued_at":"2026-07-05T04:12:14.074236Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:12:14.074236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Kamal Gupta, Saurabh Singh, Sharath Girish","submitted_at":"2022-04-06T17:59:10Z","abstract_excerpt":"We introduce LilNetX, an end-to-end trainable technique for neural networks that enables learning models with specified accuracy-rate-computation trade-off. Prior works approach these problems one at a time and often require post-processing or multistage training which become less practical and do not scale very well for large datasets or architectures. Our method constructs a joint training objective that penalizes the self-information of network parameters in a reparameterized latent space to encourage small model size while also introducing priors to increase structured sparsity in the para"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.02965","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/2204.02965/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":"2204.02965","created_at":"2026-07-05T04:12:14.074295+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.02965v1","created_at":"2026-07-05T04:12:14.074295+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.02965","created_at":"2026-07-05T04:12:14.074295+00:00"},{"alias_kind":"pith_short_12","alias_value":"X2642MPK3BQS","created_at":"2026-07-05T04:12:14.074295+00:00"},{"alias_kind":"pith_short_16","alias_value":"X2642MPK3BQST7H3","created_at":"2026-07-05T04:12:14.074295+00:00"},{"alias_kind":"pith_short_8","alias_value":"X2642MPK","created_at":"2026-07-05T04:12:14.074295+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/X2642MPK3BQST7H3E7BX2HBTK5","json":"https://pith.science/pith/X2642MPK3BQST7H3E7BX2HBTK5.json","graph_json":"https://pith.science/api/pith-number/X2642MPK3BQST7H3E7BX2HBTK5/graph.json","events_json":"https://pith.science/api/pith-number/X2642MPK3BQST7H3E7BX2HBTK5/events.json","paper":"https://pith.science/paper/X2642MPK"},"agent_actions":{"view_html":"https://pith.science/pith/X2642MPK3BQST7H3E7BX2HBTK5","download_json":"https://pith.science/pith/X2642MPK3BQST7H3E7BX2HBTK5.json","view_paper":"https://pith.science/paper/X2642MPK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.02965&json=true","fetch_graph":"https://pith.science/api/pith-number/X2642MPK3BQST7H3E7BX2HBTK5/graph.json","fetch_events":"https://pith.science/api/pith-number/X2642MPK3BQST7H3E7BX2HBTK5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X2642MPK3BQST7H3E7BX2HBTK5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X2642MPK3BQST7H3E7BX2HBTK5/action/storage_attestation","attest_author":"https://pith.science/pith/X2642MPK3BQST7H3E7BX2HBTK5/action/author_attestation","sign_citation":"https://pith.science/pith/X2642MPK3BQST7H3E7BX2HBTK5/action/citation_signature","submit_replication":"https://pith.science/pith/X2642MPK3BQST7H3E7BX2HBTK5/action/replication_record"}},"created_at":"2026-07-05T04:12:14.074295+00:00","updated_at":"2026-07-05T04:12:14.074295+00:00"}