{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6BBS66UD3DZI5CF4WA65NVZWE4","short_pith_number":"pith:6BBS66UD","schema_version":"1.0","canonical_sha256":"f0432f7a83d8f28e88bcb03dd6d7362734c46e92d7d6586b40d722a272b84b32","source":{"kind":"arxiv","id":"2402.05696","version":1},"attestation_state":"computed","paper":{"title":"Fixed width treelike neural networks capacity analysis -- generic activations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.IT","cs.LG","math.IT","math.PR"],"primary_cat":"stat.ML","authors_text":"Mihailo Stojnic","submitted_at":"2024-02-08T14:19:29Z","abstract_excerpt":"We consider the capacity of \\emph{treelike committee machines} (TCM) neural networks. Relying on Random Duality Theory (RDT), \\cite{Stojnictcmspnncaprdt23} recently introduced a generic framework for their capacity analysis. An upgrade based on the so-called \\emph{partially lifted} RDT (pl RDT) was then presented in \\cite{Stojnictcmspnncapliftedrdt23}. Both lines of work focused on the networks with the most typical, \\emph{sign}, activations. Here, on the other hand, we focus on networks with other, more general, types of activations and show that the frameworks of \\cite{Stojnictcmspnncaprdt23"},"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":"2402.05696","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-02-08T14:19:29Z","cross_cats_sorted":["cond-mat.dis-nn","cs.IT","cs.LG","math.IT","math.PR"],"title_canon_sha256":"96aaee6096eeb7eb3b27a3a132427c5709425c64076e1f1f97e324abe6b4b8ae","abstract_canon_sha256":"240cc70a2c13ac0c74bcf9308ad3584bd581bbdbeaa68ef3b58437fae81e16de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:54.511119Z","signature_b64":"P0floYJZovmvsSjPi3uu/prZMhEjsshxUEmf7k71+5fCmRK1c6nHHgvFZLKbGjLmW2U9fcjna2bFRfcpRfyNBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0432f7a83d8f28e88bcb03dd6d7362734c46e92d7d6586b40d722a272b84b32","last_reissued_at":"2026-07-05T07:42:54.510694Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:54.510694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fixed width treelike neural networks capacity analysis -- generic activations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.IT","cs.LG","math.IT","math.PR"],"primary_cat":"stat.ML","authors_text":"Mihailo Stojnic","submitted_at":"2024-02-08T14:19:29Z","abstract_excerpt":"We consider the capacity of \\emph{treelike committee machines} (TCM) neural networks. Relying on Random Duality Theory (RDT), \\cite{Stojnictcmspnncaprdt23} recently introduced a generic framework for their capacity analysis. An upgrade based on the so-called \\emph{partially lifted} RDT (pl RDT) was then presented in \\cite{Stojnictcmspnncapliftedrdt23}. Both lines of work focused on the networks with the most typical, \\emph{sign}, activations. Here, on the other hand, we focus on networks with other, more general, types of activations and show that the frameworks of \\cite{Stojnictcmspnncaprdt23"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05696","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/2402.05696/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":"2402.05696","created_at":"2026-07-05T07:42:54.510753+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.05696v1","created_at":"2026-07-05T07:42:54.510753+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05696","created_at":"2026-07-05T07:42:54.510753+00:00"},{"alias_kind":"pith_short_12","alias_value":"6BBS66UD3DZI","created_at":"2026-07-05T07:42:54.510753+00:00"},{"alias_kind":"pith_short_16","alias_value":"6BBS66UD3DZI5CF4","created_at":"2026-07-05T07:42:54.510753+00:00"},{"alias_kind":"pith_short_8","alias_value":"6BBS66UD","created_at":"2026-07-05T07:42:54.510753+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.19677","citing_title":"Deep ReLU networks -- injectivity capacity upper bounds","ref_index":81,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6BBS66UD3DZI5CF4WA65NVZWE4","json":"https://pith.science/pith/6BBS66UD3DZI5CF4WA65NVZWE4.json","graph_json":"https://pith.science/api/pith-number/6BBS66UD3DZI5CF4WA65NVZWE4/graph.json","events_json":"https://pith.science/api/pith-number/6BBS66UD3DZI5CF4WA65NVZWE4/events.json","paper":"https://pith.science/paper/6BBS66UD"},"agent_actions":{"view_html":"https://pith.science/pith/6BBS66UD3DZI5CF4WA65NVZWE4","download_json":"https://pith.science/pith/6BBS66UD3DZI5CF4WA65NVZWE4.json","view_paper":"https://pith.science/paper/6BBS66UD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.05696&json=true","fetch_graph":"https://pith.science/api/pith-number/6BBS66UD3DZI5CF4WA65NVZWE4/graph.json","fetch_events":"https://pith.science/api/pith-number/6BBS66UD3DZI5CF4WA65NVZWE4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6BBS66UD3DZI5CF4WA65NVZWE4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6BBS66UD3DZI5CF4WA65NVZWE4/action/storage_attestation","attest_author":"https://pith.science/pith/6BBS66UD3DZI5CF4WA65NVZWE4/action/author_attestation","sign_citation":"https://pith.science/pith/6BBS66UD3DZI5CF4WA65NVZWE4/action/citation_signature","submit_replication":"https://pith.science/pith/6BBS66UD3DZI5CF4WA65NVZWE4/action/replication_record"}},"created_at":"2026-07-05T07:42:54.510753+00:00","updated_at":"2026-07-05T07:42:54.510753+00:00"}