{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:D72JKIQIRV436GZUPZSGLJHHM4","short_pith_number":"pith:D72JKIQI","canonical_record":{"source":{"id":"2606.10787","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-09T12:37:43Z","cross_cats_sorted":["cs.LO"],"title_canon_sha256":"ad32e808e755428c713337952bee3a802bc1c65e329fbaf5b6f96fa0a1ce1808","abstract_canon_sha256":"f6bece9eed48dcec3ed9a448ef7a6fc3c5ff9e29aa6ef47dea59f9542a0e5f61"},"schema_version":"1.0"},"canonical_sha256":"1ff49522088d79bf1b347e6465a4e76702ef0233d40fff5240077e78a62bd3c0","source":{"kind":"arxiv","id":"2606.10787","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10787","created_at":"2026-06-10T01:10:40Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10787v1","created_at":"2026-06-10T01:10:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10787","created_at":"2026-06-10T01:10:40Z"},{"alias_kind":"pith_short_12","alias_value":"D72JKIQIRV43","created_at":"2026-06-10T01:10:40Z"},{"alias_kind":"pith_short_16","alias_value":"D72JKIQIRV436GZU","created_at":"2026-06-10T01:10:40Z"},{"alias_kind":"pith_short_8","alias_value":"D72JKIQI","created_at":"2026-06-10T01:10:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:D72JKIQIRV436GZUPZSGLJHHM4","target":"record","payload":{"canonical_record":{"source":{"id":"2606.10787","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-09T12:37:43Z","cross_cats_sorted":["cs.LO"],"title_canon_sha256":"ad32e808e755428c713337952bee3a802bc1c65e329fbaf5b6f96fa0a1ce1808","abstract_canon_sha256":"f6bece9eed48dcec3ed9a448ef7a6fc3c5ff9e29aa6ef47dea59f9542a0e5f61"},"schema_version":"1.0"},"canonical_sha256":"1ff49522088d79bf1b347e6465a4e76702ef0233d40fff5240077e78a62bd3c0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:40.562122Z","signature_b64":"WuM6cBgi3mqlNKdWnVOtLfNaUcCqOANKSRFoYlgJCt8rXnl7bWuAkJCQtZHWetlcMQWliJUeODwSxLFCetMNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ff49522088d79bf1b347e6465a4e76702ef0233d40fff5240077e78a62bd3c0","last_reissued_at":"2026-06-10T01:10:40.561594Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:40.561594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.10787","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-10T01:10:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Oa8nAbnd+oakDe+O2iwLRZ9MmLmpVMgcBTVfV04+7u9WKkVpmxT39L6q7ekThLzxhnc/wqu6E5gj8OJq3nxIBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T07:05:41.866701Z"},"content_sha256":"6a9877a0f53f7171260de9eac1f4b204d227bedd5ccca24c2b08f9d8bcdc70a9","schema_version":"1.0","event_id":"sha256:6a9877a0f53f7171260de9eac1f4b204d227bedd5ccca24c2b08f9d8bcdc70a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:D72JKIQIRV436GZUPZSGLJHHM4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Accelerating NeurASP with vectorization and caching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LO"],"primary_cat":"cs.AI","authors_text":"Alessandra Russo, Alexander Philipp Rader","submitted_at":"2026-06-09T12:37:43Z","abstract_excerpt":"Neurosymbolic AI combines neural networks with symbolic programs to create robust and explainable predictions. One such framework is NeurASP, which trains a neural network to predict concepts and reasons over them using rules written in answer set programming (ASP) to solve downstream tasks. Crucially, labels are only provided for the downstream prediction produced by the symbolic rules, not for the latent concepts themselves.Backpropagation through the non-differentiable ASP component requires expensive probability and gradient calculations, which has hindered scalability to more sophisticate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10787","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/2606.10787/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":"2026-06-10T01:10:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OLk35QQ7sOUB9CqhEvM6zTOwD63csW1X44wNJ4t4+j2ZgcjlajgRMIxqAJ1UVP87scmKSOo7tTZ9DKfNkJ/qDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T07:05:41.867074Z"},"content_sha256":"1063ad4785b69d0789ae42de84dc9f1cc046cb0a3cb83a6dc4083ec5f07b0731","schema_version":"1.0","event_id":"sha256:1063ad4785b69d0789ae42de84dc9f1cc046cb0a3cb83a6dc4083ec5f07b0731"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D72JKIQIRV436GZUPZSGLJHHM4/bundle.json","state_url":"https://pith.science/pith/D72JKIQIRV436GZUPZSGLJHHM4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D72JKIQIRV436GZUPZSGLJHHM4/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":"2026-07-22T07:05:41Z","links":{"resolver":"https://pith.science/pith/D72JKIQIRV436GZUPZSGLJHHM4","bundle":"https://pith.science/pith/D72JKIQIRV436GZUPZSGLJHHM4/bundle.json","state":"https://pith.science/pith/D72JKIQIRV436GZUPZSGLJHHM4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D72JKIQIRV436GZUPZSGLJHHM4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:D72JKIQIRV436GZUPZSGLJHHM4","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":"f6bece9eed48dcec3ed9a448ef7a6fc3c5ff9e29aa6ef47dea59f9542a0e5f61","cross_cats_sorted":["cs.LO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-09T12:37:43Z","title_canon_sha256":"ad32e808e755428c713337952bee3a802bc1c65e329fbaf5b6f96fa0a1ce1808"},"schema_version":"1.0","source":{"id":"2606.10787","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10787","created_at":"2026-06-10T01:10:40Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10787v1","created_at":"2026-06-10T01:10:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10787","created_at":"2026-06-10T01:10:40Z"},{"alias_kind":"pith_short_12","alias_value":"D72JKIQIRV43","created_at":"2026-06-10T01:10:40Z"},{"alias_kind":"pith_short_16","alias_value":"D72JKIQIRV436GZU","created_at":"2026-06-10T01:10:40Z"},{"alias_kind":"pith_short_8","alias_value":"D72JKIQI","created_at":"2026-06-10T01:10:40Z"}],"graph_snapshots":[{"event_id":"sha256:1063ad4785b69d0789ae42de84dc9f1cc046cb0a3cb83a6dc4083ec5f07b0731","target":"graph","created_at":"2026-06-10T01:10:40Z","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/2606.10787/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neurosymbolic AI combines neural networks with symbolic programs to create robust and explainable predictions. One such framework is NeurASP, which trains a neural network to predict concepts and reasons over them using rules written in answer set programming (ASP) to solve downstream tasks. Crucially, labels are only provided for the downstream prediction produced by the symbolic rules, not for the latent concepts themselves.Backpropagation through the non-differentiable ASP component requires expensive probability and gradient calculations, which has hindered scalability to more sophisticate","authors_text":"Alessandra Russo, Alexander Philipp Rader","cross_cats":["cs.LO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-09T12:37:43Z","title":"Accelerating NeurASP with vectorization and caching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10787","kind":"arxiv","version":1},"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":"sha256:6a9877a0f53f7171260de9eac1f4b204d227bedd5ccca24c2b08f9d8bcdc70a9","target":"record","created_at":"2026-06-10T01:10:40Z","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":"f6bece9eed48dcec3ed9a448ef7a6fc3c5ff9e29aa6ef47dea59f9542a0e5f61","cross_cats_sorted":["cs.LO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-09T12:37:43Z","title_canon_sha256":"ad32e808e755428c713337952bee3a802bc1c65e329fbaf5b6f96fa0a1ce1808"},"schema_version":"1.0","source":{"id":"2606.10787","kind":"arxiv","version":1}},"canonical_sha256":"1ff49522088d79bf1b347e6465a4e76702ef0233d40fff5240077e78a62bd3c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ff49522088d79bf1b347e6465a4e76702ef0233d40fff5240077e78a62bd3c0","first_computed_at":"2026-06-10T01:10:40.561594Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:10:40.561594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WuM6cBgi3mqlNKdWnVOtLfNaUcCqOANKSRFoYlgJCt8rXnl7bWuAkJCQtZHWetlcMQWliJUeODwSxLFCetMNAg==","signature_status":"signed_v1","signed_at":"2026-06-10T01:10:40.562122Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10787","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a9877a0f53f7171260de9eac1f4b204d227bedd5ccca24c2b08f9d8bcdc70a9","sha256:1063ad4785b69d0789ae42de84dc9f1cc046cb0a3cb83a6dc4083ec5f07b0731"],"state_sha256":"c062722406071ce323cb455471c40be7f5224cd2eb7d8ec2ff74fbb4bbc62294"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"djMSG3Nm/zUe4mAyCiAewzO8h7zJb1RHgpriSmbZe1xIBpxrAkFwnX+0MiXTsJm1610+zNPJU8Gqa3vYggxUAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-22T07:05:41.869632Z","bundle_sha256":"e77916d93d9ba4675571cf460b2bd7a2995acca294b17674be142c1de17b6c75"}}