{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:42IXXRV5LQL7GY64AMFXRHDAHJ","short_pith_number":"pith:42IXXRV5","schema_version":"1.0","canonical_sha256":"e6917bc6bd5c17f363dc030b789c603a61df85fbb932d0541744bac567abfc55","source":{"kind":"arxiv","id":"2606.25087","version":1},"attestation_state":"computed","paper":{"title":"Neural Network Quantization by Learning Low-Loss Subspaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Vashchilko, Mikhalina Kharkevich, Vladimir Kryzhanovskiy, Vladimir Protsenko","submitted_at":"2026-06-23T18:48:45Z","abstract_excerpt":"Neural network quantization aims to find a discrete representation of parameters that preserves the performance of a full-precision (FP) model as faithfully as possible. Enforcing discrete constraints perturbs parameters away from a well-optimized minimum, generally resulting in performance degradation. Recent studies indicate that low-loss FP solutions are not isolated, but instead belong to connected low-loss subspaces of the loss landscape, where the loss maintains nearly the same minimum value. Models sampled from these subspaces are diverse and retain high accuracy. This raises the questi"},"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":"2606.25087","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-23T18:48:45Z","cross_cats_sorted":[],"title_canon_sha256":"6cfd0ff112b897fdb28eec5f097d428a199923c7cfa73ddca149144384fba17e","abstract_canon_sha256":"da75d6849183e364f1a6284c8a792be11e0f2548c88ac9a23fb2ca46eb0db831"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T00:18:17.380915Z","signature_b64":"SEMEPaoC1wqJ2r+GdtrUnoN5bMe2MEkTPy4Mq98PHw23BQ4DD2srDj2hKxyxGe0jRsHyntYVihIzwgshwO7VBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6917bc6bd5c17f363dc030b789c603a61df85fbb932d0541744bac567abfc55","last_reissued_at":"2026-06-25T00:18:17.380575Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T00:18:17.380575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Network Quantization by Learning Low-Loss Subspaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Vashchilko, Mikhalina Kharkevich, Vladimir Kryzhanovskiy, Vladimir Protsenko","submitted_at":"2026-06-23T18:48:45Z","abstract_excerpt":"Neural network quantization aims to find a discrete representation of parameters that preserves the performance of a full-precision (FP) model as faithfully as possible. Enforcing discrete constraints perturbs parameters away from a well-optimized minimum, generally resulting in performance degradation. Recent studies indicate that low-loss FP solutions are not isolated, but instead belong to connected low-loss subspaces of the loss landscape, where the loss maintains nearly the same minimum value. Models sampled from these subspaces are diverse and retain high accuracy. This raises the questi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25087","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/2606.25087/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":"2606.25087","created_at":"2026-06-25T00:18:17.380637+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.25087v1","created_at":"2026-06-25T00:18:17.380637+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25087","created_at":"2026-06-25T00:18:17.380637+00:00"},{"alias_kind":"pith_short_12","alias_value":"42IXXRV5LQL7","created_at":"2026-06-25T00:18:17.380637+00:00"},{"alias_kind":"pith_short_16","alias_value":"42IXXRV5LQL7GY64","created_at":"2026-06-25T00:18:17.380637+00:00"},{"alias_kind":"pith_short_8","alias_value":"42IXXRV5","created_at":"2026-06-25T00:18:17.380637+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/42IXXRV5LQL7GY64AMFXRHDAHJ","json":"https://pith.science/pith/42IXXRV5LQL7GY64AMFXRHDAHJ.json","graph_json":"https://pith.science/api/pith-number/42IXXRV5LQL7GY64AMFXRHDAHJ/graph.json","events_json":"https://pith.science/api/pith-number/42IXXRV5LQL7GY64AMFXRHDAHJ/events.json","paper":"https://pith.science/paper/42IXXRV5"},"agent_actions":{"view_html":"https://pith.science/pith/42IXXRV5LQL7GY64AMFXRHDAHJ","download_json":"https://pith.science/pith/42IXXRV5LQL7GY64AMFXRHDAHJ.json","view_paper":"https://pith.science/paper/42IXXRV5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.25087&json=true","fetch_graph":"https://pith.science/api/pith-number/42IXXRV5LQL7GY64AMFXRHDAHJ/graph.json","fetch_events":"https://pith.science/api/pith-number/42IXXRV5LQL7GY64AMFXRHDAHJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/42IXXRV5LQL7GY64AMFXRHDAHJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/42IXXRV5LQL7GY64AMFXRHDAHJ/action/storage_attestation","attest_author":"https://pith.science/pith/42IXXRV5LQL7GY64AMFXRHDAHJ/action/author_attestation","sign_citation":"https://pith.science/pith/42IXXRV5LQL7GY64AMFXRHDAHJ/action/citation_signature","submit_replication":"https://pith.science/pith/42IXXRV5LQL7GY64AMFXRHDAHJ/action/replication_record"}},"created_at":"2026-06-25T00:18:17.380637+00:00","updated_at":"2026-06-25T00:18:17.380637+00:00"}