{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GBYJ3OUVUXE5OLKQ3HWK3CECMA","short_pith_number":"pith:GBYJ3OUV","schema_version":"1.0","canonical_sha256":"30709dba95a5c9d72d50d9ecad88826022e383ff7b5b1c231d527977313cfdd5","source":{"kind":"arxiv","id":"2503.12917","version":2},"attestation_state":"computed","paper":{"title":"Verification Learning: Make Unsupervised Neuro-Symbolic System Feasible","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jie-Jing Shao, Lan-Zhe Guo, Lin-Han Jia, Wen-Chao Hu, Yu-Feng Li","submitted_at":"2025-03-17T08:28:58Z","abstract_excerpt":"The current Neuro-Symbolic (NeSy) Learning paradigm suffers from an over-reliance on labeled data, so if we completely disregard labels, it leads to less symbol information, a larger solution space, and more shortcuts-issues that current Nesy systems cannot resolve. This paper introduces a novel learning paradigm, Verification Learning (VL), which addresses this challenge by transforming the label-based reasoning process in Nesy into a label-free verification process. VL achieves excellent learning results solely by relying on unlabeled data and a function that verifies whether the current pre"},"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":"2503.12917","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-17T08:28:58Z","cross_cats_sorted":[],"title_canon_sha256":"0383b8c84dfb340e1923d25f8a7d95181c7e57b2a4e3a35b6d7bcb153b9decd3","abstract_canon_sha256":"65e59226402aaea6b3916b9270f882270945ee7b269b5ad11055aa9c0d17de49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:37.892390Z","signature_b64":"RR7+Ht2AkGw4oRTmD8vEKeqrk7k8O85I7d699gGntfNF2/vX0yOZ0/rf2ZIwo1upPVP93Tq5jiuqCHm+PfH+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30709dba95a5c9d72d50d9ecad88826022e383ff7b5b1c231d527977313cfdd5","last_reissued_at":"2026-07-05T11:22:37.891853Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:37.891853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Verification Learning: Make Unsupervised Neuro-Symbolic System Feasible","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jie-Jing Shao, Lan-Zhe Guo, Lin-Han Jia, Wen-Chao Hu, Yu-Feng Li","submitted_at":"2025-03-17T08:28:58Z","abstract_excerpt":"The current Neuro-Symbolic (NeSy) Learning paradigm suffers from an over-reliance on labeled data, so if we completely disregard labels, it leads to less symbol information, a larger solution space, and more shortcuts-issues that current Nesy systems cannot resolve. This paper introduces a novel learning paradigm, Verification Learning (VL), which addresses this challenge by transforming the label-based reasoning process in Nesy into a label-free verification process. VL achieves excellent learning results solely by relying on unlabeled data and a function that verifies whether the current pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12917","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/2503.12917/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":"2503.12917","created_at":"2026-07-05T11:22:37.891905+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.12917v2","created_at":"2026-07-05T11:22:37.891905+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12917","created_at":"2026-07-05T11:22:37.891905+00:00"},{"alias_kind":"pith_short_12","alias_value":"GBYJ3OUVUXE5","created_at":"2026-07-05T11:22:37.891905+00:00"},{"alias_kind":"pith_short_16","alias_value":"GBYJ3OUVUXE5OLKQ","created_at":"2026-07-05T11:22:37.891905+00:00"},{"alias_kind":"pith_short_8","alias_value":"GBYJ3OUV","created_at":"2026-07-05T11:22:37.891905+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10528","citing_title":"BareBones: Benchmarking Zero-Shot Geometric Comprehension in VLMs","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GBYJ3OUVUXE5OLKQ3HWK3CECMA","json":"https://pith.science/pith/GBYJ3OUVUXE5OLKQ3HWK3CECMA.json","graph_json":"https://pith.science/api/pith-number/GBYJ3OUVUXE5OLKQ3HWK3CECMA/graph.json","events_json":"https://pith.science/api/pith-number/GBYJ3OUVUXE5OLKQ3HWK3CECMA/events.json","paper":"https://pith.science/paper/GBYJ3OUV"},"agent_actions":{"view_html":"https://pith.science/pith/GBYJ3OUVUXE5OLKQ3HWK3CECMA","download_json":"https://pith.science/pith/GBYJ3OUVUXE5OLKQ3HWK3CECMA.json","view_paper":"https://pith.science/paper/GBYJ3OUV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.12917&json=true","fetch_graph":"https://pith.science/api/pith-number/GBYJ3OUVUXE5OLKQ3HWK3CECMA/graph.json","fetch_events":"https://pith.science/api/pith-number/GBYJ3OUVUXE5OLKQ3HWK3CECMA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GBYJ3OUVUXE5OLKQ3HWK3CECMA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GBYJ3OUVUXE5OLKQ3HWK3CECMA/action/storage_attestation","attest_author":"https://pith.science/pith/GBYJ3OUVUXE5OLKQ3HWK3CECMA/action/author_attestation","sign_citation":"https://pith.science/pith/GBYJ3OUVUXE5OLKQ3HWK3CECMA/action/citation_signature","submit_replication":"https://pith.science/pith/GBYJ3OUVUXE5OLKQ3HWK3CECMA/action/replication_record"}},"created_at":"2026-07-05T11:22:37.891905+00:00","updated_at":"2026-07-05T11:22:37.891905+00:00"}