{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XJ3UXBE4ZE5EPWW45U5DLZCXWF","short_pith_number":"pith:XJ3UXBE4","schema_version":"1.0","canonical_sha256":"ba774b849cc93a47dadced3a35e457b1551288f05c3c7071db503152426a43a5","source":{"kind":"arxiv","id":"2601.16366","version":2},"attestation_state":"computed","paper":{"title":"Post-Training Neural Network Pruning using Graph Curvature","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SC"],"primary_cat":"cs.LG","authors_text":"Jayson Sia, Paul Bogdan, Radoslav Ivanov, Shuhang Tan","submitted_at":"2026-01-22T23:35:10Z","abstract_excerpt":"This paper provides a fresh view of the neural network (NN) pruning problem through the lens of graph theory. To achieve effective pruning, we aim to identify the main NN data flows and the corresponding NN connections that are most and least important for the performance of the full model. Unlike the standard approach to NN data flow analysis, which is based on information theory, we employ the notion of graph curvature, specifically Ollivier-Ricci curvature (ORC). ORC has been successfully used to identify important graph edges in various domains such as road traffic analysis, biological net"},"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":"2601.16366","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-22T23:35:10Z","cross_cats_sorted":["cs.SC"],"title_canon_sha256":"6288b75c1799c198ffcc57cd8708f5c26a4061fd06eb9e4dd9542f151789e83c","abstract_canon_sha256":"3cf11ed0e00e2f1a5d03d4d3c86944ca0ea16e430d97ac8608044f465c81cf04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:02:30.050797Z","signature_b64":"F6mtrV9bL1CQ2X4B1azloXaODcuTC+LtaNjZGAuY0Wfdnkdp8a+dC5kFOEZFj44YkqfFINGn3vICt+L8H6vtBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba774b849cc93a47dadced3a35e457b1551288f05c3c7071db503152426a43a5","last_reissued_at":"2026-06-01T01:02:30.049930Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:02:30.049930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Post-Training Neural Network Pruning using Graph Curvature","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SC"],"primary_cat":"cs.LG","authors_text":"Jayson Sia, Paul Bogdan, Radoslav Ivanov, Shuhang Tan","submitted_at":"2026-01-22T23:35:10Z","abstract_excerpt":"This paper provides a fresh view of the neural network (NN) pruning problem through the lens of graph theory. To achieve effective pruning, we aim to identify the main NN data flows and the corresponding NN connections that are most and least important for the performance of the full model. Unlike the standard approach to NN data flow analysis, which is based on information theory, we employ the notion of graph curvature, specifically Ollivier-Ricci curvature (ORC). ORC has been successfully used to identify important graph edges in various domains such as road traffic analysis, biological net"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.16366","kind":"arxiv","version":2},"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/2601.16366/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":"2601.16366","created_at":"2026-06-01T01:02:30.050038+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.16366v2","created_at":"2026-06-01T01:02:30.050038+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.16366","created_at":"2026-06-01T01:02:30.050038+00:00"},{"alias_kind":"pith_short_12","alias_value":"XJ3UXBE4ZE5E","created_at":"2026-06-01T01:02:30.050038+00:00"},{"alias_kind":"pith_short_16","alias_value":"XJ3UXBE4ZE5EPWW4","created_at":"2026-06-01T01:02:30.050038+00:00"},{"alias_kind":"pith_short_8","alias_value":"XJ3UXBE4","created_at":"2026-06-01T01:02:30.050038+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/XJ3UXBE4ZE5EPWW45U5DLZCXWF","json":"https://pith.science/pith/XJ3UXBE4ZE5EPWW45U5DLZCXWF.json","graph_json":"https://pith.science/api/pith-number/XJ3UXBE4ZE5EPWW45U5DLZCXWF/graph.json","events_json":"https://pith.science/api/pith-number/XJ3UXBE4ZE5EPWW45U5DLZCXWF/events.json","paper":"https://pith.science/paper/XJ3UXBE4"},"agent_actions":{"view_html":"https://pith.science/pith/XJ3UXBE4ZE5EPWW45U5DLZCXWF","download_json":"https://pith.science/pith/XJ3UXBE4ZE5EPWW45U5DLZCXWF.json","view_paper":"https://pith.science/paper/XJ3UXBE4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.16366&json=true","fetch_graph":"https://pith.science/api/pith-number/XJ3UXBE4ZE5EPWW45U5DLZCXWF/graph.json","fetch_events":"https://pith.science/api/pith-number/XJ3UXBE4ZE5EPWW45U5DLZCXWF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XJ3UXBE4ZE5EPWW45U5DLZCXWF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XJ3UXBE4ZE5EPWW45U5DLZCXWF/action/storage_attestation","attest_author":"https://pith.science/pith/XJ3UXBE4ZE5EPWW45U5DLZCXWF/action/author_attestation","sign_citation":"https://pith.science/pith/XJ3UXBE4ZE5EPWW45U5DLZCXWF/action/citation_signature","submit_replication":"https://pith.science/pith/XJ3UXBE4ZE5EPWW45U5DLZCXWF/action/replication_record"}},"created_at":"2026-06-01T01:02:30.050038+00:00","updated_at":"2026-06-01T01:02:30.050038+00:00"}