{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LIBMPMSVHWZ7S2JEAMK33JBK7W","short_pith_number":"pith:LIBMPMSV","schema_version":"1.0","canonical_sha256":"5a02c7b2553db3f969240315bda42afda356f1757290cf1ed95606f081b2849d","source":{"kind":"arxiv","id":"2605.17704","version":1},"attestation_state":"computed","paper":{"title":"Toy Combinatorial Interpretability Models Reveal Lottery Tickets in Early Feature Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Winning tickets correspond to precursor locations in feature space already near the final codes at initialization.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alon Bebchuk, Nir Shavit","submitted_at":"2026-05-18T00:00:53Z","abstract_excerpt":"The lottery ticket hypothesis posits that dense networks contain sparse subnetworks, ``winning tickets,'' that, when rewound to their initial weights and retrained in isolation, match the performance of the full model. We ask a more mechanistic question: what internal object does a winning ticket preserve? We work in a combinatorial, clause-structured toy setting that admits an interpretable feature-space representation with well-defined combinatorial distances between features. We show that winning tickets in weight space correspond to precursor locations in feature space that are already nea"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.17704","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T00:00:53Z","cross_cats_sorted":[],"title_canon_sha256":"384a9d1492db2241b97e02283d40c69b245f325342cb96960b2289adac4318f4","abstract_canon_sha256":"2c7c7580093599767840203442bafa64edbea7e5b6d34a4aec80260d4624a973"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:53.654879Z","signature_b64":"nnUbWcqGohWs4HbCxQdlmUJs1gzXpFsG7nmyBsdKXbP5dwFyW8PNBxHQZ/89P6uPD34C5tK0r2aeJ7Y14yvsDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a02c7b2553db3f969240315bda42afda356f1757290cf1ed95606f081b2849d","last_reissued_at":"2026-05-20T00:04:53.654081Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:53.654081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toy Combinatorial Interpretability Models Reveal Lottery Tickets in Early Feature Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Winning tickets correspond to precursor locations in feature space already near the final codes at initialization.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alon Bebchuk, Nir Shavit","submitted_at":"2026-05-18T00:00:53Z","abstract_excerpt":"The lottery ticket hypothesis posits that dense networks contain sparse subnetworks, ``winning tickets,'' that, when rewound to their initial weights and retrained in isolation, match the performance of the full model. We ask a more mechanistic question: what internal object does a winning ticket preserve? We work in a combinatorial, clause-structured toy setting that admits an interpretable feature-space representation with well-defined combinatorial distances between features. We show that winning tickets in weight space correspond to precursor locations in feature space that are already nea"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"winning tickets in weight space correspond to precursor locations in feature space that are already near, at initialization, to the final feature-channel codes. A winning ticket is thus a family of compatible code locations that jointly balance proximity to final codes with low inter-feature interference.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The combinatorial, clause-structured toy setting admits an interpretable feature-space representation with well-defined combinatorial distances between features that capture the relevant dynamics of real neural networks under superposition.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"In a combinatorial toy setting, winning lottery tickets preserve families of compatible feature locations in early feature space that balance proximity to final codes with low interference, rather than specific weight subnetworks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Winning tickets correspond to precursor locations in feature space already near the final codes at initialization.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8368c865ca9c63ef62ac228ffba84ec337f60e9ccfe53ba188a3996aaaff97a0"},"source":{"id":"2605.17704","kind":"arxiv","version":1},"verdict":{"id":"ca06049a-8b98-4cf9-91f2-eabf34870def","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T22:06:17.836785Z","strongest_claim":"winning tickets in weight space correspond to precursor locations in feature space that are already near, at initialization, to the final feature-channel codes. A winning ticket is thus a family of compatible code locations that jointly balance proximity to final codes with low inter-feature interference.","one_line_summary":"In a combinatorial toy setting, winning lottery tickets preserve families of compatible feature locations in early feature space that balance proximity to final codes with low interference, rather than specific weight subnetworks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The combinatorial, clause-structured toy setting admits an interpretable feature-space representation with well-defined combinatorial distances between features that capture the relevant dynamics of real neural networks under superposition.","pith_extraction_headline":"Winning tickets correspond to precursor locations in feature space already near the final codes at initialization."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.17704/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T22:31:19.405696Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T22:10:57.458735Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"shingle_duplication","ran_at":"2026-05-19T21:49:43.479897Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T21:49:43.309341Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.512988Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"cited_work_retraction","ran_at":"2026-05-19T21:21:59.173374Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T21:21:57.420154Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"d12a80bad7596fa66e800253bec3b70f84da1d583d68da6f48c4873a1a360fd1"},"references":{"count":91,"sample":[{"doi":"","year":null,"title":"International Conference on Learning Representations , year=","work_id":"61b9ca7f-3fca-4d6c-8df5-e91576c98a1b","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"International Conference on Learning Representations , year=","work_id":"9145ab82-d376-4eef-ab5b-332886510d7b","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"International Conference on Machine Learning , year=","work_id":"4b9f0050-4324-4b4d-95a0-77ec2030a415","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"International Conference on Learning Representations , year=","work_id":"a8140a03-8d67-4bf8-93d3-896dbb7b2dbe","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Advances in Neural Information Processing Systems , year=","work_id":"9ac2d762-b569-4d13-9f39-17080231cf34","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":91,"snapshot_sha256":"049f8f95a42883fe34c333d33c3083246569f043978576b244084ad54264fa8f","internal_anchors":6},"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":"2605.17704","created_at":"2026-05-20T00:04:53.654222+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17704v1","created_at":"2026-05-20T00:04:53.654222+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17704","created_at":"2026-05-20T00:04:53.654222+00:00"},{"alias_kind":"pith_short_12","alias_value":"LIBMPMSVHWZ7","created_at":"2026-05-20T00:04:53.654222+00:00"},{"alias_kind":"pith_short_16","alias_value":"LIBMPMSVHWZ7S2JE","created_at":"2026-05-20T00:04:53.654222+00:00"},{"alias_kind":"pith_short_8","alias_value":"LIBMPMSV","created_at":"2026-05-20T00:04:53.654222+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/LIBMPMSVHWZ7S2JEAMK33JBK7W","json":"https://pith.science/pith/LIBMPMSVHWZ7S2JEAMK33JBK7W.json","graph_json":"https://pith.science/api/pith-number/LIBMPMSVHWZ7S2JEAMK33JBK7W/graph.json","events_json":"https://pith.science/api/pith-number/LIBMPMSVHWZ7S2JEAMK33JBK7W/events.json","paper":"https://pith.science/paper/LIBMPMSV"},"agent_actions":{"view_html":"https://pith.science/pith/LIBMPMSVHWZ7S2JEAMK33JBK7W","download_json":"https://pith.science/pith/LIBMPMSVHWZ7S2JEAMK33JBK7W.json","view_paper":"https://pith.science/paper/LIBMPMSV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17704&json=true","fetch_graph":"https://pith.science/api/pith-number/LIBMPMSVHWZ7S2JEAMK33JBK7W/graph.json","fetch_events":"https://pith.science/api/pith-number/LIBMPMSVHWZ7S2JEAMK33JBK7W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LIBMPMSVHWZ7S2JEAMK33JBK7W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LIBMPMSVHWZ7S2JEAMK33JBK7W/action/storage_attestation","attest_author":"https://pith.science/pith/LIBMPMSVHWZ7S2JEAMK33JBK7W/action/author_attestation","sign_citation":"https://pith.science/pith/LIBMPMSVHWZ7S2JEAMK33JBK7W/action/citation_signature","submit_replication":"https://pith.science/pith/LIBMPMSVHWZ7S2JEAMK33JBK7W/action/replication_record"}},"created_at":"2026-05-20T00:04:53.654222+00:00","updated_at":"2026-05-20T00:04:53.654222+00:00"}