{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:67CHVBC7PUOU76WRUX7PX7ASZU","short_pith_number":"pith:67CHVBC7","canonical_record":{"source":{"id":"2408.11367","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-21T06:38:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cbd027d1b0878ed6fc65354918a831e33dfc3edef88fbed4a61237f128cd2953","abstract_canon_sha256":"71d47be1fe1400c4473eccbbc62e1c8d89c946eeeae76d9658e6f31d0191de63"},"schema_version":"1.0"},"canonical_sha256":"f7c47a845f7d1d4ffad1a5fefbfc12cd39fc59ef8e69ab75171904c469daabb5","source":{"kind":"arxiv","id":"2408.11367","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11367","created_at":"2026-07-05T09:09:25Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11367v2","created_at":"2026-07-05T09:09:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11367","created_at":"2026-07-05T09:09:25Z"},{"alias_kind":"pith_short_12","alias_value":"67CHVBC7PUOU","created_at":"2026-07-05T09:09:25Z"},{"alias_kind":"pith_short_16","alias_value":"67CHVBC7PUOU76WR","created_at":"2026-07-05T09:09:25Z"},{"alias_kind":"pith_short_8","alias_value":"67CHVBC7","created_at":"2026-07-05T09:09:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:67CHVBC7PUOU76WRUX7PX7ASZU","target":"record","payload":{"canonical_record":{"source":{"id":"2408.11367","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-21T06:38:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cbd027d1b0878ed6fc65354918a831e33dfc3edef88fbed4a61237f128cd2953","abstract_canon_sha256":"71d47be1fe1400c4473eccbbc62e1c8d89c946eeeae76d9658e6f31d0191de63"},"schema_version":"1.0"},"canonical_sha256":"f7c47a845f7d1d4ffad1a5fefbfc12cd39fc59ef8e69ab75171904c469daabb5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:25.148980Z","signature_b64":"jZT4tvymtqV0AFxZ/hdYfMgJ12JcqRlTW5YnBJGsNe8jkAFdk8CC3gcQI99VCvod9pqUUmPAQmlc+IczYymmAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7c47a845f7d1d4ffad1a5fefbfc12cd39fc59ef8e69ab75171904c469daabb5","last_reissued_at":"2026-07-05T09:09:25.148522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:25.148522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.11367","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":"2026-07-05T09:09:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"COQLk2tVVroqCLu5lWMyeGGN535BOShUaFq94lNauXMoE+c25kd80HVcXhkLvQamONgqOQz9yT0bJ0ENq95SBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:06:42.845823Z"},"content_sha256":"0fda4c8017a2a91f447f54d2c392b337465b6281dc25cae92cf96799c86c002b","schema_version":"1.0","event_id":"sha256:0fda4c8017a2a91f447f54d2c392b337465b6281dc25cae92cf96799c86c002b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:67CHVBC7PUOU76WRUX7PX7ASZU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Probabilistic Inductive Logic Programming with Neurosymbolic Inference and Relaxation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Fieke Hillerstrom, Gertjan Burghouts","submitted_at":"2024-08-21T06:38:49Z","abstract_excerpt":"Many inductive logic programming (ILP) methods are incapable of learning programs from probabilistic background knowledge, e.g. coming from sensory data or neural networks with probabilities. We propose Propper, which handles flawed and probabilistic background knowledge by extending ILP with a combination of neurosymbolic inference, a continuous criterion for hypothesis selection (BCE) and a relaxation of the hypothesis constrainer (NoisyCombo). For relational patterns in noisy images, Propper can learn programs from as few as 8 examples. It outperforms binary ILP and statistical models such "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11367","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/2408.11367/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:09:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SdvxFEFKsusweZBiVp0uT0sfN+VdebUVGRCxD4EHhTc2FV8wgEHwYhvURLY/bh0ida9vFtx7QkPEbuiq7/rBAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:06:42.846208Z"},"content_sha256":"85b11512a62ddaa8b0d79136f30b2df7a48c1565ab87460c2727973b9209fb6e","schema_version":"1.0","event_id":"sha256:85b11512a62ddaa8b0d79136f30b2df7a48c1565ab87460c2727973b9209fb6e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/67CHVBC7PUOU76WRUX7PX7ASZU/bundle.json","state_url":"https://pith.science/pith/67CHVBC7PUOU76WRUX7PX7ASZU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/67CHVBC7PUOU76WRUX7PX7ASZU/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":"2026-07-07T07:06:42Z","links":{"resolver":"https://pith.science/pith/67CHVBC7PUOU76WRUX7PX7ASZU","bundle":"https://pith.science/pith/67CHVBC7PUOU76WRUX7PX7ASZU/bundle.json","state":"https://pith.science/pith/67CHVBC7PUOU76WRUX7PX7ASZU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/67CHVBC7PUOU76WRUX7PX7ASZU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:67CHVBC7PUOU76WRUX7PX7ASZU","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":"71d47be1fe1400c4473eccbbc62e1c8d89c946eeeae76d9658e6f31d0191de63","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-21T06:38:49Z","title_canon_sha256":"cbd027d1b0878ed6fc65354918a831e33dfc3edef88fbed4a61237f128cd2953"},"schema_version":"1.0","source":{"id":"2408.11367","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11367","created_at":"2026-07-05T09:09:25Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11367v2","created_at":"2026-07-05T09:09:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11367","created_at":"2026-07-05T09:09:25Z"},{"alias_kind":"pith_short_12","alias_value":"67CHVBC7PUOU","created_at":"2026-07-05T09:09:25Z"},{"alias_kind":"pith_short_16","alias_value":"67CHVBC7PUOU76WR","created_at":"2026-07-05T09:09:25Z"},{"alias_kind":"pith_short_8","alias_value":"67CHVBC7","created_at":"2026-07-05T09:09:25Z"}],"graph_snapshots":[{"event_id":"sha256:85b11512a62ddaa8b0d79136f30b2df7a48c1565ab87460c2727973b9209fb6e","target":"graph","created_at":"2026-07-05T09:09:25Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2408.11367/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many inductive logic programming (ILP) methods are incapable of learning programs from probabilistic background knowledge, e.g. coming from sensory data or neural networks with probabilities. We propose Propper, which handles flawed and probabilistic background knowledge by extending ILP with a combination of neurosymbolic inference, a continuous criterion for hypothesis selection (BCE) and a relaxation of the hypothesis constrainer (NoisyCombo). For relational patterns in noisy images, Propper can learn programs from as few as 8 examples. It outperforms binary ILP and statistical models such ","authors_text":"Fieke Hillerstrom, Gertjan Burghouts","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-21T06:38:49Z","title":"Towards Probabilistic Inductive Logic Programming with Neurosymbolic Inference and Relaxation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11367","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0fda4c8017a2a91f447f54d2c392b337465b6281dc25cae92cf96799c86c002b","target":"record","created_at":"2026-07-05T09:09:25Z","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":"71d47be1fe1400c4473eccbbc62e1c8d89c946eeeae76d9658e6f31d0191de63","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-21T06:38:49Z","title_canon_sha256":"cbd027d1b0878ed6fc65354918a831e33dfc3edef88fbed4a61237f128cd2953"},"schema_version":"1.0","source":{"id":"2408.11367","kind":"arxiv","version":2}},"canonical_sha256":"f7c47a845f7d1d4ffad1a5fefbfc12cd39fc59ef8e69ab75171904c469daabb5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7c47a845f7d1d4ffad1a5fefbfc12cd39fc59ef8e69ab75171904c469daabb5","first_computed_at":"2026-07-05T09:09:25.148522Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:09:25.148522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jZT4tvymtqV0AFxZ/hdYfMgJ12JcqRlTW5YnBJGsNe8jkAFdk8CC3gcQI99VCvod9pqUUmPAQmlc+IczYymmAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:09:25.148980Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.11367","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0fda4c8017a2a91f447f54d2c392b337465b6281dc25cae92cf96799c86c002b","sha256:85b11512a62ddaa8b0d79136f30b2df7a48c1565ab87460c2727973b9209fb6e"],"state_sha256":"fcd11006a4e44f68579e7ac92a8fe56adf41f576774a2ea0c20f585962c50676"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1iLxrRG29e5Iq1S4ViA1QSOqyHX6UI+4hZlDHUWbde5nX450ubPaxxoBMDnpk7HIOhdfiaJYMaFeqF7ApDfhAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:06:42.848280Z","bundle_sha256":"43cd167727b5c19c034f081801c149d5642f933dad97aa92c2933954a3a1c741"}}