{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:USEEI4GLQIYKDPAXLV7Q4G73WD","short_pith_number":"pith:USEEI4GL","canonical_record":{"source":{"id":"2605.04193","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-05T18:35:06Z","cross_cats_sorted":["cs.LG","cs.LO"],"title_canon_sha256":"b9728e4103424a7ff14399736b539bea1d104da6bfbc200454c8a87c312f0883","abstract_canon_sha256":"3bdcaa77ad05f78d7749b8ccf6ccef89a59e9b25f88540938063569e0af12d2a"},"schema_version":"1.0"},"canonical_sha256":"a4884470cb8230a1bc175d7f0e1bfbb0e8c3aae9abcb4a87a1a8403e81740e90","source":{"kind":"arxiv","id":"2605.04193","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.04193","created_at":"2026-06-02T02:04:18Z"},{"alias_kind":"arxiv_version","alias_value":"2605.04193v2","created_at":"2026-06-02T02:04:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.04193","created_at":"2026-06-02T02:04:18Z"},{"alias_kind":"pith_short_12","alias_value":"USEEI4GLQIYK","created_at":"2026-06-02T02:04:18Z"},{"alias_kind":"pith_short_16","alias_value":"USEEI4GLQIYKDPAX","created_at":"2026-06-02T02:04:18Z"},{"alias_kind":"pith_short_8","alias_value":"USEEI4GL","created_at":"2026-06-02T02:04:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:USEEI4GLQIYKDPAXLV7Q4G73WD","target":"record","payload":{"canonical_record":{"source":{"id":"2605.04193","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-05T18:35:06Z","cross_cats_sorted":["cs.LG","cs.LO"],"title_canon_sha256":"b9728e4103424a7ff14399736b539bea1d104da6bfbc200454c8a87c312f0883","abstract_canon_sha256":"3bdcaa77ad05f78d7749b8ccf6ccef89a59e9b25f88540938063569e0af12d2a"},"schema_version":"1.0"},"canonical_sha256":"a4884470cb8230a1bc175d7f0e1bfbb0e8c3aae9abcb4a87a1a8403e81740e90","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:18.575646Z","signature_b64":"5qCtb8R6Clm3eF04EqE7hKPQimOtnQu2nuUFIcu7MBdMd0ltzNlddwG1UAj9sLcDmobWpOf59cx0oetW4KxwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4884470cb8230a1bc175d7f0e1bfbb0e8c3aae9abcb4a87a1a8403e81740e90","last_reissued_at":"2026-06-02T02:04:18.575135Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:18.575135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.04193","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T02:04:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VUqid+1T2FB7BN+hxNvXZF3OP39yyRSIs7R5b7EgoWmKFH4UFIKssb+/MyfAY5Sdn4J3EUyXN7TE+aPqnkf1Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:55:47.982233Z"},"content_sha256":"35f244bc8ecd36adcb5e0e16703e71020b9389216137aeed3c789723797a5cd8","schema_version":"1.0","event_id":"sha256:35f244bc8ecd36adcb5e0e16703e71020b9389216137aeed3c789723797a5cd8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:USEEI4GLQIYKDPAXLV7Q4G73WD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ANDRE: An Attention-based Neuro-symbolic Differentiable Rule Extractor for Inductive Logic Programming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"ANDRE learns first-order logic rules from noisy probabilistic data by optimizing a continuous space with attention-driven conjunction and disjunction operators.","cross_cats":["cs.LG","cs.LO"],"primary_cat":"cs.AI","authors_text":"Iman Sharifi, Peng Wei, Saber Fallah","submitted_at":"2026-05-05T18:35:06Z","abstract_excerpt":"Inductive Logic Programming (ILP) aims to learn interpretable first-order rules from data, but existing symbolic and neuro-symbolic approaches struggle to scale to noisy and probabilistic settings. Classical ILP relies on discrete combinatorial rule search and is brittle under uncertainty, while differentiable ILP methods typically depend on predefined rule templates or inaccurate fuzzy operators that suffer from vanishing gradients or poor approximation of logical structure when reasoning over probabilistic predicate valuations. This paper proposes an Attention-based Neuro-symbolic Differenti"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"ANDRE achieves competitive or superior predictive performance while reliably recovering correct symbolic rules under uncertainty. In particular, ANDRE remains robust to moderate label noise, substantially outperforming existing differentiable ILP methods in both rule extraction quality and stability.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That attention-based operators can accurately and stably approximate min-max logical semantics over probabilistic predicate valuations without vanishing gradients or loss of interpretability when optimizing the continuous rule space.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ANDRE learns first-order logic programs via attention-driven differentiable operators that approximate logical semantics, achieving competitive performance and robust rule recovery on noisy and probabilistic ILP benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"ANDRE learns first-order logic rules from noisy probabilistic data by optimizing a continuous space with attention-driven conjunction and disjunction operators.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"47f7b47853c3392ede697abe19c5e4be0c3a79b78a6907a4acc6ff3665e0850c"},"source":{"id":"2605.04193","kind":"arxiv","version":2},"verdict":{"id":"d00327e7-15f0-43d2-ad0a-9eb977930707","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T17:33:11.416702Z","strongest_claim":"ANDRE achieves competitive or superior predictive performance while reliably recovering correct symbolic rules under uncertainty. In particular, ANDRE remains robust to moderate label noise, substantially outperforming existing differentiable ILP methods in both rule extraction quality and stability.","one_line_summary":"ANDRE learns first-order logic programs via attention-driven differentiable operators that approximate logical semantics, achieving competitive performance and robust rule recovery on noisy and probabilistic ILP benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That attention-based operators can accurately and stably approximate min-max logical semantics over probabilistic predicate valuations without vanishing gradients or loss of interpretability when optimizing the continuous rule space.","pith_extraction_headline":"ANDRE learns first-order logic rules from noisy probabilistic data by optimizing a continuous space with attention-driven conjunction and disjunction operators."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.04193/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T12:36:58.724228Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T23:31:21.183747Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T14:42:43.829418Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"8cf56ef4f33e2f4254af139b669121ca40b81d62a08fef3f232aa6ad3bbf615e"},"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"},"verdict_id":"d00327e7-15f0-43d2-ad0a-9eb977930707"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T02:04:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xr2gFJDcIqL3WiHemU9qIkp6exuxuUP0mpZGZrKibQkGaq4CkJ1u79Vn7ByQroGQXeDuicJetWw43rjmVAk/Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:55:47.983492Z"},"content_sha256":"77700792386a81bd783ca885e794b3caec110d331f6b00f652908cfa5731cb0f","schema_version":"1.0","event_id":"sha256:77700792386a81bd783ca885e794b3caec110d331f6b00f652908cfa5731cb0f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/USEEI4GLQIYKDPAXLV7Q4G73WD/bundle.json","state_url":"https://pith.science/pith/USEEI4GLQIYKDPAXLV7Q4G73WD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/USEEI4GLQIYKDPAXLV7Q4G73WD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T15:55:47Z","links":{"resolver":"https://pith.science/pith/USEEI4GLQIYKDPAXLV7Q4G73WD","bundle":"https://pith.science/pith/USEEI4GLQIYKDPAXLV7Q4G73WD/bundle.json","state":"https://pith.science/pith/USEEI4GLQIYKDPAXLV7Q4G73WD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/USEEI4GLQIYKDPAXLV7Q4G73WD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:USEEI4GLQIYKDPAXLV7Q4G73WD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3bdcaa77ad05f78d7749b8ccf6ccef89a59e9b25f88540938063569e0af12d2a","cross_cats_sorted":["cs.LG","cs.LO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-05T18:35:06Z","title_canon_sha256":"b9728e4103424a7ff14399736b539bea1d104da6bfbc200454c8a87c312f0883"},"schema_version":"1.0","source":{"id":"2605.04193","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.04193","created_at":"2026-06-02T02:04:18Z"},{"alias_kind":"arxiv_version","alias_value":"2605.04193v2","created_at":"2026-06-02T02:04:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.04193","created_at":"2026-06-02T02:04:18Z"},{"alias_kind":"pith_short_12","alias_value":"USEEI4GLQIYK","created_at":"2026-06-02T02:04:18Z"},{"alias_kind":"pith_short_16","alias_value":"USEEI4GLQIYKDPAX","created_at":"2026-06-02T02:04:18Z"},{"alias_kind":"pith_short_8","alias_value":"USEEI4GL","created_at":"2026-06-02T02:04:18Z"}],"graph_snapshots":[{"event_id":"sha256:77700792386a81bd783ca885e794b3caec110d331f6b00f652908cfa5731cb0f","target":"graph","created_at":"2026-06-02T02:04:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"ANDRE achieves competitive or superior predictive performance while reliably recovering correct symbolic rules under uncertainty. In particular, ANDRE remains robust to moderate label noise, substantially outperforming existing differentiable ILP methods in both rule extraction quality and stability."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That attention-based operators can accurately and stably approximate min-max logical semantics over probabilistic predicate valuations without vanishing gradients or loss of interpretability when optimizing the continuous rule space."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"ANDRE learns first-order logic programs via attention-driven differentiable operators that approximate logical semantics, achieving competitive performance and robust rule recovery on noisy and probabilistic ILP benchmarks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"ANDRE learns first-order logic rules from noisy probabilistic data by optimizing a continuous space with attention-driven conjunction and disjunction operators."}],"snapshot_sha256":"47f7b47853c3392ede697abe19c5e4be0c3a79b78a6907a4acc6ff3665e0850c"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T12:36:58.724228Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T23:31:21.183747Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T14:42:43.829418Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.04193/integrity.json","findings":[],"snapshot_sha256":"8cf56ef4f33e2f4254af139b669121ca40b81d62a08fef3f232aa6ad3bbf615e","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inductive Logic Programming (ILP) aims to learn interpretable first-order rules from data, but existing symbolic and neuro-symbolic approaches struggle to scale to noisy and probabilistic settings. Classical ILP relies on discrete combinatorial rule search and is brittle under uncertainty, while differentiable ILP methods typically depend on predefined rule templates or inaccurate fuzzy operators that suffer from vanishing gradients or poor approximation of logical structure when reasoning over probabilistic predicate valuations. This paper proposes an Attention-based Neuro-symbolic Differenti","authors_text":"Iman Sharifi, Peng Wei, Saber Fallah","cross_cats":["cs.LG","cs.LO"],"headline":"ANDRE learns first-order logic rules from noisy probabilistic data by optimizing a continuous space with attention-driven conjunction and disjunction operators.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-05T18:35:06Z","title":"ANDRE: An Attention-based Neuro-symbolic Differentiable Rule Extractor for Inductive Logic Programming"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.04193","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-08T17:33:11.416702Z","id":"d00327e7-15f0-43d2-ad0a-9eb977930707","model_set":{"reader":"grok-4.3"},"one_line_summary":"ANDRE learns first-order logic programs via attention-driven differentiable operators that approximate logical semantics, achieving competitive performance and robust rule recovery on noisy and probabilistic ILP benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"ANDRE learns first-order logic rules from noisy probabilistic data by optimizing a continuous space with attention-driven conjunction and disjunction operators.","strongest_claim":"ANDRE achieves competitive or superior predictive performance while reliably recovering correct symbolic rules under uncertainty. In particular, ANDRE remains robust to moderate label noise, substantially outperforming existing differentiable ILP methods in both rule extraction quality and stability.","weakest_assumption":"That attention-based operators can accurately and stably approximate min-max logical semantics over probabilistic predicate valuations without vanishing gradients or loss of interpretability when optimizing the continuous rule space."}},"verdict_id":"d00327e7-15f0-43d2-ad0a-9eb977930707"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:35f244bc8ecd36adcb5e0e16703e71020b9389216137aeed3c789723797a5cd8","target":"record","created_at":"2026-06-02T02:04:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3bdcaa77ad05f78d7749b8ccf6ccef89a59e9b25f88540938063569e0af12d2a","cross_cats_sorted":["cs.LG","cs.LO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-05T18:35:06Z","title_canon_sha256":"b9728e4103424a7ff14399736b539bea1d104da6bfbc200454c8a87c312f0883"},"schema_version":"1.0","source":{"id":"2605.04193","kind":"arxiv","version":2}},"canonical_sha256":"a4884470cb8230a1bc175d7f0e1bfbb0e8c3aae9abcb4a87a1a8403e81740e90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4884470cb8230a1bc175d7f0e1bfbb0e8c3aae9abcb4a87a1a8403e81740e90","first_computed_at":"2026-06-02T02:04:18.575135Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:18.575135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5qCtb8R6Clm3eF04EqE7hKPQimOtnQu2nuUFIcu7MBdMd0ltzNlddwG1UAj9sLcDmobWpOf59cx0oetW4KxwCA==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:18.575646Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.04193","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35f244bc8ecd36adcb5e0e16703e71020b9389216137aeed3c789723797a5cd8","sha256:77700792386a81bd783ca885e794b3caec110d331f6b00f652908cfa5731cb0f"],"state_sha256":"f15c00827d1a8713463a5809d55374224a3cbd766553d4680bfbdf23036cc029"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FkGSbp+48F20wuwR1c4M4txyfC04HeBjEzvhGKMSi7M4DJ4yx8fGsov1qNqzTKxJbbYeBt/R9dJHe0u+WsHHDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:55:47.989382Z","bundle_sha256":"1878b80353ddea2fa73f00441867c79dbaec075590b15c1488bf2e5ac316039c"}}