{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OJKJSJMD7U6D76FNNHWXH4G2QR","short_pith_number":"pith:OJKJSJMD","schema_version":"1.0","canonical_sha256":"7254992583fd3c3ff8ad69ed73f0da847fcd0d2c75b81cf61be6fe76ac8f62e6","source":{"kind":"arxiv","id":"2504.07055","version":1},"attestation_state":"computed","paper":{"title":"$\\Pi$-NeSy: A Possibilistic Neuro-Symbolic Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.LO"],"primary_cat":"cs.AI","authors_text":"Isma\\\"il Baaj, Pierre Marquis","submitted_at":"2025-04-09T17:16:23Z","abstract_excerpt":"In this article, we introduce a neuro-symbolic approach that combines a low-level perception task performed by a neural network with a high-level reasoning task performed by a possibilistic rule-based system. The goal is to be able to derive for each input instance the degree of possibility that it belongs to a target (meta-)concept. This (meta-)concept is connected to intermediate concepts by a possibilistic rule-based system. The probability of each intermediate concept for the input instance is inferred using a neural network. The connection between the low-level perception task and the hig"},"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":"2504.07055","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-09T17:16:23Z","cross_cats_sorted":["cs.LG","cs.LO"],"title_canon_sha256":"d9e5047ca77f91eb778588f4d7f2c7ca51010f1c3ef1c1cbec5333bfcf728bc4","abstract_canon_sha256":"62a2dee2285f67af2beb53bd11380b99d5e8867fccc5115f4c05343176bd4ed2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:50.404813Z","signature_b64":"W+CnuCrvc5lNvdhkQ54bZl1Ke8rKGW9VokCW5s6hBq+kXEFzsE1d9o/1H5Tj+EQtp/Cjry3kjKl9DGnQxADeAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7254992583fd3c3ff8ad69ed73f0da847fcd0d2c75b81cf61be6fe76ac8f62e6","last_reissued_at":"2026-07-05T10:46:50.404280Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:50.404280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"$\\Pi$-NeSy: A Possibilistic Neuro-Symbolic Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.LO"],"primary_cat":"cs.AI","authors_text":"Isma\\\"il Baaj, Pierre Marquis","submitted_at":"2025-04-09T17:16:23Z","abstract_excerpt":"In this article, we introduce a neuro-symbolic approach that combines a low-level perception task performed by a neural network with a high-level reasoning task performed by a possibilistic rule-based system. The goal is to be able to derive for each input instance the degree of possibility that it belongs to a target (meta-)concept. This (meta-)concept is connected to intermediate concepts by a possibilistic rule-based system. The probability of each intermediate concept for the input instance is inferred using a neural network. The connection between the low-level perception task and the hig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07055","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/2504.07055/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":"2504.07055","created_at":"2026-07-05T10:46:50.404354+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.07055v1","created_at":"2026-07-05T10:46:50.404354+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07055","created_at":"2026-07-05T10:46:50.404354+00:00"},{"alias_kind":"pith_short_12","alias_value":"OJKJSJMD7U6D","created_at":"2026-07-05T10:46:50.404354+00:00"},{"alias_kind":"pith_short_16","alias_value":"OJKJSJMD7U6D76FN","created_at":"2026-07-05T10:46:50.404354+00:00"},{"alias_kind":"pith_short_8","alias_value":"OJKJSJMD","created_at":"2026-07-05T10:46:50.404354+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17967","citing_title":"A Sugeno Integral View of Binarized Neural Network Inference","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OJKJSJMD7U6D76FNNHWXH4G2QR","json":"https://pith.science/pith/OJKJSJMD7U6D76FNNHWXH4G2QR.json","graph_json":"https://pith.science/api/pith-number/OJKJSJMD7U6D76FNNHWXH4G2QR/graph.json","events_json":"https://pith.science/api/pith-number/OJKJSJMD7U6D76FNNHWXH4G2QR/events.json","paper":"https://pith.science/paper/OJKJSJMD"},"agent_actions":{"view_html":"https://pith.science/pith/OJKJSJMD7U6D76FNNHWXH4G2QR","download_json":"https://pith.science/pith/OJKJSJMD7U6D76FNNHWXH4G2QR.json","view_paper":"https://pith.science/paper/OJKJSJMD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.07055&json=true","fetch_graph":"https://pith.science/api/pith-number/OJKJSJMD7U6D76FNNHWXH4G2QR/graph.json","fetch_events":"https://pith.science/api/pith-number/OJKJSJMD7U6D76FNNHWXH4G2QR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OJKJSJMD7U6D76FNNHWXH4G2QR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OJKJSJMD7U6D76FNNHWXH4G2QR/action/storage_attestation","attest_author":"https://pith.science/pith/OJKJSJMD7U6D76FNNHWXH4G2QR/action/author_attestation","sign_citation":"https://pith.science/pith/OJKJSJMD7U6D76FNNHWXH4G2QR/action/citation_signature","submit_replication":"https://pith.science/pith/OJKJSJMD7U6D76FNNHWXH4G2QR/action/replication_record"}},"created_at":"2026-07-05T10:46:50.404354+00:00","updated_at":"2026-07-05T10:46:50.404354+00:00"}