{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DDXMFBPLCUSTSD3OGZ6WPGS3TD","short_pith_number":"pith:DDXMFBPL","schema_version":"1.0","canonical_sha256":"18eec285eb1525390f6e367d679a5b98fb95e31e86d03d978d958f12a77c1dfc","source":{"kind":"arxiv","id":"2401.16024","version":1},"attestation_state":"computed","paper":{"title":"Probabilistic Abduction for Visual Abstract Reasoning via Learning Rules in Vector-symbolic Architectures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abbas Rahimi, Abu Sebastian, Francesco di Stefano, Michael Hersche, Thomas Hofmann","submitted_at":"2024-01-29T10:17:18Z","abstract_excerpt":"Abstract reasoning is a cornerstone of human intelligence, and replicating it with artificial intelligence (AI) presents an ongoing challenge. This study focuses on efficiently solving Raven's progressive matrices (RPM), a visual test for assessing abstract reasoning abilities, by using distributed computation and operators provided by vector-symbolic architectures (VSA). Instead of hard-coding the rule formulations associated with RPMs, our approach can learn the VSA rule formulations (hence the name Learn-VRF) with just one pass through the training data. Yet, our approach, with compact para"},"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":"2401.16024","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-29T10:17:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fd1ec77ce64d7eedae5a8388437ea338af6977944d878e22a6ef48e49ebcfc8b","abstract_canon_sha256":"368d791196a3e0cdbef19f1b53997ec07c6a0d2c0caf80508fe81fd48b19023b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:43.055611Z","signature_b64":"myMuHo7+yDRLe+sxt78R4dGnzaALjYIPeXLzClZrHc7hM6q6C8S2olX4VpjeVFReA0JJvl9Qm31BS1QAP++4Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18eec285eb1525390f6e367d679a5b98fb95e31e86d03d978d958f12a77c1dfc","last_reissued_at":"2026-07-05T07:38:43.055101Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:43.055101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probabilistic Abduction for Visual Abstract Reasoning via Learning Rules in Vector-symbolic Architectures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abbas Rahimi, Abu Sebastian, Francesco di Stefano, Michael Hersche, Thomas Hofmann","submitted_at":"2024-01-29T10:17:18Z","abstract_excerpt":"Abstract reasoning is a cornerstone of human intelligence, and replicating it with artificial intelligence (AI) presents an ongoing challenge. This study focuses on efficiently solving Raven's progressive matrices (RPM), a visual test for assessing abstract reasoning abilities, by using distributed computation and operators provided by vector-symbolic architectures (VSA). Instead of hard-coding the rule formulations associated with RPMs, our approach can learn the VSA rule formulations (hence the name Learn-VRF) with just one pass through the training data. Yet, our approach, with compact para"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.16024","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/2401.16024/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":"2401.16024","created_at":"2026-07-05T07:38:43.055159+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.16024v1","created_at":"2026-07-05T07:38:43.055159+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.16024","created_at":"2026-07-05T07:38:43.055159+00:00"},{"alias_kind":"pith_short_12","alias_value":"DDXMFBPLCUST","created_at":"2026-07-05T07:38:43.055159+00:00"},{"alias_kind":"pith_short_16","alias_value":"DDXMFBPLCUSTSD3O","created_at":"2026-07-05T07:38:43.055159+00:00"},{"alias_kind":"pith_short_8","alias_value":"DDXMFBPL","created_at":"2026-07-05T07:38:43.055159+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.01528","citing_title":"Gram-Space: Structure-Preserving Codebook Compression for Memory-Efficient Neuro-Symbolic AI","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DDXMFBPLCUSTSD3OGZ6WPGS3TD","json":"https://pith.science/pith/DDXMFBPLCUSTSD3OGZ6WPGS3TD.json","graph_json":"https://pith.science/api/pith-number/DDXMFBPLCUSTSD3OGZ6WPGS3TD/graph.json","events_json":"https://pith.science/api/pith-number/DDXMFBPLCUSTSD3OGZ6WPGS3TD/events.json","paper":"https://pith.science/paper/DDXMFBPL"},"agent_actions":{"view_html":"https://pith.science/pith/DDXMFBPLCUSTSD3OGZ6WPGS3TD","download_json":"https://pith.science/pith/DDXMFBPLCUSTSD3OGZ6WPGS3TD.json","view_paper":"https://pith.science/paper/DDXMFBPL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.16024&json=true","fetch_graph":"https://pith.science/api/pith-number/DDXMFBPLCUSTSD3OGZ6WPGS3TD/graph.json","fetch_events":"https://pith.science/api/pith-number/DDXMFBPLCUSTSD3OGZ6WPGS3TD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DDXMFBPLCUSTSD3OGZ6WPGS3TD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DDXMFBPLCUSTSD3OGZ6WPGS3TD/action/storage_attestation","attest_author":"https://pith.science/pith/DDXMFBPLCUSTSD3OGZ6WPGS3TD/action/author_attestation","sign_citation":"https://pith.science/pith/DDXMFBPLCUSTSD3OGZ6WPGS3TD/action/citation_signature","submit_replication":"https://pith.science/pith/DDXMFBPLCUSTSD3OGZ6WPGS3TD/action/replication_record"}},"created_at":"2026-07-05T07:38:43.055159+00:00","updated_at":"2026-07-05T07:38:43.055159+00:00"}