{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QGWBQYRALH3FBPVIJR5T2I5JYS","short_pith_number":"pith:QGWBQYRA","schema_version":"1.0","canonical_sha256":"81ac18622059f650bea84c7b3d23a9c49bf3e14cff4aa22f22344de526e99623","source":{"kind":"arxiv","id":"2608.01528","version":1},"attestation_state":"computed","paper":{"title":"Gram-Space: Structure-Preserving Codebook Compression for Memory-Efficient Neuro-Symbolic AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Wantong Li, Weilun Wang","submitted_at":"2026-08-02T22:37:34Z","abstract_excerpt":"Vector symbolic architectures (VSA) are widely used for reasoning in neuro-symbolic (NeSy) AI, yet high-dimensional codebooks often create severe memory bottlenecks that limit scalability and deployment. In this paper, we propose Gram-Space, a compression framework that applies Gram-Schmidt orthogonalization to represent codebook vectors in a compact orthonormal coordinate system. Gram-Space preserves the dot-product structure required by matrix-based VSA operators, which supports numerically equivalent execution of matrix similarity, probability vectorization, and attention score computations"},"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":"2608.01528","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-02T22:37:34Z","cross_cats_sorted":[],"title_canon_sha256":"835679917247fc688a5d358d69950a07ad9f63b0e0de787989b4bf0bdfccb6e9","abstract_canon_sha256":"3b046ebe5961c20eb08074d3c25aca3eb6a40cb5dbf36ed2f6f5556ac7a9a17e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:05:48.615740Z","signature_b64":"6xZcVHU7J+4njQPj0vQdWtLKHGQEBvxDV7McSe3XvYFc566SPckb0rN+UndW3YgUHRggN0PQBrHWsIypBwlyCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81ac18622059f650bea84c7b3d23a9c49bf3e14cff4aa22f22344de526e99623","last_reissued_at":"2026-08-04T02:05:48.613869Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:05:48.613869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gram-Space: Structure-Preserving Codebook Compression for Memory-Efficient Neuro-Symbolic AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Wantong Li, Weilun Wang","submitted_at":"2026-08-02T22:37:34Z","abstract_excerpt":"Vector symbolic architectures (VSA) are widely used for reasoning in neuro-symbolic (NeSy) AI, yet high-dimensional codebooks often create severe memory bottlenecks that limit scalability and deployment. In this paper, we propose Gram-Space, a compression framework that applies Gram-Schmidt orthogonalization to represent codebook vectors in a compact orthonormal coordinate system. Gram-Space preserves the dot-product structure required by matrix-based VSA operators, which supports numerically equivalent execution of matrix similarity, probability vectorization, and attention score computations"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01528","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/2608.01528/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":"2608.01528","created_at":"2026-08-04T02:05:48.615555+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01528v1","created_at":"2026-08-04T02:05:48.615555+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01528","created_at":"2026-08-04T02:05:48.615555+00:00"},{"alias_kind":"pith_short_12","alias_value":"QGWBQYRALH3F","created_at":"2026-08-04T02:05:48.615555+00:00"},{"alias_kind":"pith_short_16","alias_value":"QGWBQYRALH3FBPVI","created_at":"2026-08-04T02:05:48.615555+00:00"},{"alias_kind":"pith_short_8","alias_value":"QGWBQYRA","created_at":"2026-08-04T02:05:48.615555+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/QGWBQYRALH3FBPVIJR5T2I5JYS","json":"https://pith.science/pith/QGWBQYRALH3FBPVIJR5T2I5JYS.json","graph_json":"https://pith.science/api/pith-number/QGWBQYRALH3FBPVIJR5T2I5JYS/graph.json","events_json":"https://pith.science/api/pith-number/QGWBQYRALH3FBPVIJR5T2I5JYS/events.json","paper":"https://pith.science/paper/QGWBQYRA"},"agent_actions":{"view_html":"https://pith.science/pith/QGWBQYRALH3FBPVIJR5T2I5JYS","download_json":"https://pith.science/pith/QGWBQYRALH3FBPVIJR5T2I5JYS.json","view_paper":"https://pith.science/paper/QGWBQYRA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01528&json=true","fetch_graph":"https://pith.science/api/pith-number/QGWBQYRALH3FBPVIJR5T2I5JYS/graph.json","fetch_events":"https://pith.science/api/pith-number/QGWBQYRALH3FBPVIJR5T2I5JYS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QGWBQYRALH3FBPVIJR5T2I5JYS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QGWBQYRALH3FBPVIJR5T2I5JYS/action/storage_attestation","attest_author":"https://pith.science/pith/QGWBQYRALH3FBPVIJR5T2I5JYS/action/author_attestation","sign_citation":"https://pith.science/pith/QGWBQYRALH3FBPVIJR5T2I5JYS/action/citation_signature","submit_replication":"https://pith.science/pith/QGWBQYRALH3FBPVIJR5T2I5JYS/action/replication_record"}},"created_at":"2026-08-04T02:05:48.615555+00:00","updated_at":"2026-08-04T02:05:48.615555+00:00"}