{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D76WS2AS46U3NU2YBR4H4MWCBZ","short_pith_number":"pith:D76WS2AS","schema_version":"1.0","canonical_sha256":"1ffd696812e7a9b6d3580c787e32c20e44184a77f82a4ca31640db9a18bedc0b","source":{"kind":"arxiv","id":"2402.00854","version":4},"attestation_state":"computed","paper":{"title":"SymbolicAI: A framework for logic-based approaches combining generative models and solvers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SC","cs.SE"],"primary_cat":"cs.LG","authors_text":"Claudiu Leoveanu-Condrei, Marius-Constantin Dinu, Markus Holzleitner, Sepp Hochreiter, Werner Zellinger","submitted_at":"2024-02-01T18:50:50Z","abstract_excerpt":"We introduce SymbolicAI, a versatile and modular framework employing a logic-based approach to concept learning and flow management in generative processes. SymbolicAI enables the seamless integration of generative models with a diverse range of solvers by treating large language models (LLMs) as semantic parsers that execute tasks based on both natural and formal language instructions, thus bridging the gap between symbolic reasoning and generative AI. We leverage probabilistic programming principles to tackle complex tasks, and utilize differentiable and classical programming paradigms with "},"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":"2402.00854","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-01T18:50:50Z","cross_cats_sorted":["cs.AI","cs.SC","cs.SE"],"title_canon_sha256":"24281cd1cf85b91f78792659a8c4cc873383ae1c0d38ccaf4508a4b0ef4e6790","abstract_canon_sha256":"a2c77dd25d99818cfc4c09516b46879d97c3d5fe960ecce738da0feae26929c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:54.419360Z","signature_b64":"xTMRdd0cVeIyaQX5EdjutX2Lp7m46L8JPUkFeiHq+NDLOWaILMCviPf6r/5K2Upo3gS8T2ffZ5pZVQCHf7bpAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ffd696812e7a9b6d3580c787e32c20e44184a77f82a4ca31640db9a18bedc0b","last_reissued_at":"2026-07-05T08:57:54.418839Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:54.418839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SymbolicAI: A framework for logic-based approaches combining generative models and solvers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SC","cs.SE"],"primary_cat":"cs.LG","authors_text":"Claudiu Leoveanu-Condrei, Marius-Constantin Dinu, Markus Holzleitner, Sepp Hochreiter, Werner Zellinger","submitted_at":"2024-02-01T18:50:50Z","abstract_excerpt":"We introduce SymbolicAI, a versatile and modular framework employing a logic-based approach to concept learning and flow management in generative processes. SymbolicAI enables the seamless integration of generative models with a diverse range of solvers by treating large language models (LLMs) as semantic parsers that execute tasks based on both natural and formal language instructions, thus bridging the gap between symbolic reasoning and generative AI. We leverage probabilistic programming principles to tackle complex tasks, and utilize differentiable and classical programming paradigms with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00854","kind":"arxiv","version":4},"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/2402.00854/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":"2402.00854","created_at":"2026-07-05T08:57:54.418904+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.00854v4","created_at":"2026-07-05T08:57:54.418904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00854","created_at":"2026-07-05T08:57:54.418904+00:00"},{"alias_kind":"pith_short_12","alias_value":"D76WS2AS46U3","created_at":"2026-07-05T08:57:54.418904+00:00"},{"alias_kind":"pith_short_16","alias_value":"D76WS2AS46U3NU2Y","created_at":"2026-07-05T08:57:54.418904+00:00"},{"alias_kind":"pith_short_8","alias_value":"D76WS2AS","created_at":"2026-07-05T08:57:54.418904+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07663","citing_title":"Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2408.06292","citing_title":"The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07935","citing_title":"TraceFix: Repairing Agent Coordination Protocols with TLA+ Counterexamples","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D76WS2AS46U3NU2YBR4H4MWCBZ","json":"https://pith.science/pith/D76WS2AS46U3NU2YBR4H4MWCBZ.json","graph_json":"https://pith.science/api/pith-number/D76WS2AS46U3NU2YBR4H4MWCBZ/graph.json","events_json":"https://pith.science/api/pith-number/D76WS2AS46U3NU2YBR4H4MWCBZ/events.json","paper":"https://pith.science/paper/D76WS2AS"},"agent_actions":{"view_html":"https://pith.science/pith/D76WS2AS46U3NU2YBR4H4MWCBZ","download_json":"https://pith.science/pith/D76WS2AS46U3NU2YBR4H4MWCBZ.json","view_paper":"https://pith.science/paper/D76WS2AS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.00854&json=true","fetch_graph":"https://pith.science/api/pith-number/D76WS2AS46U3NU2YBR4H4MWCBZ/graph.json","fetch_events":"https://pith.science/api/pith-number/D76WS2AS46U3NU2YBR4H4MWCBZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D76WS2AS46U3NU2YBR4H4MWCBZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D76WS2AS46U3NU2YBR4H4MWCBZ/action/storage_attestation","attest_author":"https://pith.science/pith/D76WS2AS46U3NU2YBR4H4MWCBZ/action/author_attestation","sign_citation":"https://pith.science/pith/D76WS2AS46U3NU2YBR4H4MWCBZ/action/citation_signature","submit_replication":"https://pith.science/pith/D76WS2AS46U3NU2YBR4H4MWCBZ/action/replication_record"}},"created_at":"2026-07-05T08:57:54.418904+00:00","updated_at":"2026-07-05T08:57:54.418904+00:00"}