{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VBIDD5EQSWH3YHLWKZBHW23ABQ","short_pith_number":"pith:VBIDD5EQ","schema_version":"1.0","canonical_sha256":"a85031f490958fbc1d7656427b6b600c2dfb69dd25fa80d8a6d00234b855bf05","source":{"kind":"arxiv","id":"2606.09924","version":1},"attestation_state":"computed","paper":{"title":"Sigma-Branch: Hierarchical Single-Path Network Reconstruction for Dynamic Inference with Reduced Active Parameters","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hiroaki Nishi, Kohga Tanaka","submitted_at":"2026-06-07T09:19:44Z","abstract_excerpt":"Deploying deep neural networks on memory-constrained edge accelerators is bottlenecked by per-inference off-chip weight transfer rather than computation: the dense network cannot be retained on-chip, and every parameter must be loaded for every input. Existing model compression reduces this transfer only at the cost of permanent capacity loss. We propose Sigma-Branch (SigmaB), a framework that restructures a pretrained dense network into a hierarchical binary tree composed of a shared backbone, hierarchical routers, and specialized leaves. Pretrained weights are distributed across the tree via"},"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":"2606.09924","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-07T09:19:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a352e0d410861bd3362b1f9603d09d7d81a4fe8239aa5e82df3bea0413759bb8","abstract_canon_sha256":"c044ad00c3d3ac249219294296f723931237db9cb078867604349e5600c3d0da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T00:08:33.258640Z","signature_b64":"0hKHvwl/uksUPoqlMzLUMppYuPrGTPYUbhhtZYohKyFLOGZjdH4nZcezu2+uixihz8WR5PwkEGbMQty+DPIyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a85031f490958fbc1d7656427b6b600c2dfb69dd25fa80d8a6d00234b855bf05","last_reissued_at":"2026-06-10T00:08:33.257688Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T00:08:33.257688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sigma-Branch: Hierarchical Single-Path Network Reconstruction for Dynamic Inference with Reduced Active Parameters","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hiroaki Nishi, Kohga Tanaka","submitted_at":"2026-06-07T09:19:44Z","abstract_excerpt":"Deploying deep neural networks on memory-constrained edge accelerators is bottlenecked by per-inference off-chip weight transfer rather than computation: the dense network cannot be retained on-chip, and every parameter must be loaded for every input. Existing model compression reduces this transfer only at the cost of permanent capacity loss. We propose Sigma-Branch (SigmaB), a framework that restructures a pretrained dense network into a hierarchical binary tree composed of a shared backbone, hierarchical routers, and specialized leaves. Pretrained weights are distributed across the tree via"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09924","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/2606.09924/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":"2606.09924","created_at":"2026-06-10T00:08:33.257866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09924v1","created_at":"2026-06-10T00:08:33.257866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09924","created_at":"2026-06-10T00:08:33.257866+00:00"},{"alias_kind":"pith_short_12","alias_value":"VBIDD5EQSWH3","created_at":"2026-06-10T00:08:33.257866+00:00"},{"alias_kind":"pith_short_16","alias_value":"VBIDD5EQSWH3YHLW","created_at":"2026-06-10T00:08:33.257866+00:00"},{"alias_kind":"pith_short_8","alias_value":"VBIDD5EQ","created_at":"2026-06-10T00:08:33.257866+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/VBIDD5EQSWH3YHLWKZBHW23ABQ","json":"https://pith.science/pith/VBIDD5EQSWH3YHLWKZBHW23ABQ.json","graph_json":"https://pith.science/api/pith-number/VBIDD5EQSWH3YHLWKZBHW23ABQ/graph.json","events_json":"https://pith.science/api/pith-number/VBIDD5EQSWH3YHLWKZBHW23ABQ/events.json","paper":"https://pith.science/paper/VBIDD5EQ"},"agent_actions":{"view_html":"https://pith.science/pith/VBIDD5EQSWH3YHLWKZBHW23ABQ","download_json":"https://pith.science/pith/VBIDD5EQSWH3YHLWKZBHW23ABQ.json","view_paper":"https://pith.science/paper/VBIDD5EQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09924&json=true","fetch_graph":"https://pith.science/api/pith-number/VBIDD5EQSWH3YHLWKZBHW23ABQ/graph.json","fetch_events":"https://pith.science/api/pith-number/VBIDD5EQSWH3YHLWKZBHW23ABQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VBIDD5EQSWH3YHLWKZBHW23ABQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VBIDD5EQSWH3YHLWKZBHW23ABQ/action/storage_attestation","attest_author":"https://pith.science/pith/VBIDD5EQSWH3YHLWKZBHW23ABQ/action/author_attestation","sign_citation":"https://pith.science/pith/VBIDD5EQSWH3YHLWKZBHW23ABQ/action/citation_signature","submit_replication":"https://pith.science/pith/VBIDD5EQSWH3YHLWKZBHW23ABQ/action/replication_record"}},"created_at":"2026-06-10T00:08:33.257866+00:00","updated_at":"2026-06-10T00:08:33.257866+00:00"}