{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NLJNVV44GBFN7Q24ECSQWBDXRK","short_pith_number":"pith:NLJNVV44","canonical_record":{"source":{"id":"2606.03269","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T07:35:31Z","cross_cats_sorted":[],"title_canon_sha256":"40f7662295b292e5f1594db64c03cbfbf4ce2230e66706c6782a89c4cfe266fc","abstract_canon_sha256":"abb15fab29df9fa03cd234f6b113fd16caf0838368ea91a3d0929aa5601ef666"},"schema_version":"1.0"},"canonical_sha256":"6ad2dad79c304adfc35c20a50b04778ab6e3cdff0832efed06257624fd7c35d5","source":{"kind":"arxiv","id":"2606.03269","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03269","created_at":"2026-06-03T01:05:37Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03269v1","created_at":"2026-06-03T01:05:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03269","created_at":"2026-06-03T01:05:37Z"},{"alias_kind":"pith_short_12","alias_value":"NLJNVV44GBFN","created_at":"2026-06-03T01:05:37Z"},{"alias_kind":"pith_short_16","alias_value":"NLJNVV44GBFN7Q24","created_at":"2026-06-03T01:05:37Z"},{"alias_kind":"pith_short_8","alias_value":"NLJNVV44","created_at":"2026-06-03T01:05:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NLJNVV44GBFN7Q24ECSQWBDXRK","target":"record","payload":{"canonical_record":{"source":{"id":"2606.03269","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T07:35:31Z","cross_cats_sorted":[],"title_canon_sha256":"40f7662295b292e5f1594db64c03cbfbf4ce2230e66706c6782a89c4cfe266fc","abstract_canon_sha256":"abb15fab29df9fa03cd234f6b113fd16caf0838368ea91a3d0929aa5601ef666"},"schema_version":"1.0"},"canonical_sha256":"6ad2dad79c304adfc35c20a50b04778ab6e3cdff0832efed06257624fd7c35d5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:37.487407Z","signature_b64":"MVSBiXeRbs8nZ21ZtX283ho+sbfDMqYgm2Ot6AVf3WqInUAmjmaIBNgqZ0awZzLq9g6M/B+Jm7Iked7V5CC9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ad2dad79c304adfc35c20a50b04778ab6e3cdff0832efed06257624fd7c35d5","last_reissued_at":"2026-06-03T01:05:37.486984Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:37.486984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.03269","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":"2026-06-03T01:05:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TWbqh40X9I19P7K9lyMNGP1WtWfm0QuTry9vO56Au6AB5QsY00E0Xyu6YRMcvisBkyaQGqubbxLjPLSIXUHQCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T15:29:06.908834Z"},"content_sha256":"547811a0d4eec10e4eb796fda610d7f32c0a8f023d6aa74fb3e158166911a915","schema_version":"1.0","event_id":"sha256:547811a0d4eec10e4eb796fda610d7f32c0a8f023d6aa74fb3e158166911a915"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NLJNVV44GBFN7Q24ECSQWBDXRK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distilling Answer-Set Programming Rules from LLMs for Neurosymbolic Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Johannes Oetsch, Nelson Higuera Ruiz, Thomas Eiter","submitted_at":"2026-06-02T07:35:31Z","abstract_excerpt":"Visual Question Answering (VQA) is the task of answering questions about images, requiring the integration of multimodal input and reasoning. Modular approaches that incorporate logic-based representations into the reasoning component offer clear advantages over end-to-end trained systems, particularly in terms of interpretability. However, adapting or extending these representations when task requirements change can place a significant burden on developers. To address this challenge, we present an approach for distilling rules from Large Language Models (LLMs). Our method prompts an LLM to ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03269","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/2606.03269/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":"2026-06-03T01:05:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qIOrrA6H1yN68wLI6yD1+d3IxOu7/uWaiR+UvttjfgxllbLDX1lYctT2QrWZOvaVXpfVFjow2T3AwNZJxigbBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T15:29:06.909208Z"},"content_sha256":"3c97419f31eb88b5f3ab8628df7711e58d7e268b3cbd73c8bbcf7f663e68bd2c","schema_version":"1.0","event_id":"sha256:3c97419f31eb88b5f3ab8628df7711e58d7e268b3cbd73c8bbcf7f663e68bd2c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NLJNVV44GBFN7Q24ECSQWBDXRK/bundle.json","state_url":"https://pith.science/pith/NLJNVV44GBFN7Q24ECSQWBDXRK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NLJNVV44GBFN7Q24ECSQWBDXRK/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":"2026-06-06T15:29:06Z","links":{"resolver":"https://pith.science/pith/NLJNVV44GBFN7Q24ECSQWBDXRK","bundle":"https://pith.science/pith/NLJNVV44GBFN7Q24ECSQWBDXRK/bundle.json","state":"https://pith.science/pith/NLJNVV44GBFN7Q24ECSQWBDXRK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NLJNVV44GBFN7Q24ECSQWBDXRK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NLJNVV44GBFN7Q24ECSQWBDXRK","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":"abb15fab29df9fa03cd234f6b113fd16caf0838368ea91a3d0929aa5601ef666","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T07:35:31Z","title_canon_sha256":"40f7662295b292e5f1594db64c03cbfbf4ce2230e66706c6782a89c4cfe266fc"},"schema_version":"1.0","source":{"id":"2606.03269","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03269","created_at":"2026-06-03T01:05:37Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03269v1","created_at":"2026-06-03T01:05:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03269","created_at":"2026-06-03T01:05:37Z"},{"alias_kind":"pith_short_12","alias_value":"NLJNVV44GBFN","created_at":"2026-06-03T01:05:37Z"},{"alias_kind":"pith_short_16","alias_value":"NLJNVV44GBFN7Q24","created_at":"2026-06-03T01:05:37Z"},{"alias_kind":"pith_short_8","alias_value":"NLJNVV44","created_at":"2026-06-03T01:05:37Z"}],"graph_snapshots":[{"event_id":"sha256:3c97419f31eb88b5f3ab8628df7711e58d7e268b3cbd73c8bbcf7f663e68bd2c","target":"graph","created_at":"2026-06-03T01:05:37Z","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/2606.03269/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Question Answering (VQA) is the task of answering questions about images, requiring the integration of multimodal input and reasoning. Modular approaches that incorporate logic-based representations into the reasoning component offer clear advantages over end-to-end trained systems, particularly in terms of interpretability. However, adapting or extending these representations when task requirements change can place a significant burden on developers. To address this challenge, we present an approach for distilling rules from Large Language Models (LLMs). Our method prompts an LLM to ex","authors_text":"Johannes Oetsch, Nelson Higuera Ruiz, Thomas Eiter","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T07:35:31Z","title":"Distilling Answer-Set Programming Rules from LLMs for Neurosymbolic Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03269","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":"sha256:547811a0d4eec10e4eb796fda610d7f32c0a8f023d6aa74fb3e158166911a915","target":"record","created_at":"2026-06-03T01:05:37Z","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":"abb15fab29df9fa03cd234f6b113fd16caf0838368ea91a3d0929aa5601ef666","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T07:35:31Z","title_canon_sha256":"40f7662295b292e5f1594db64c03cbfbf4ce2230e66706c6782a89c4cfe266fc"},"schema_version":"1.0","source":{"id":"2606.03269","kind":"arxiv","version":1}},"canonical_sha256":"6ad2dad79c304adfc35c20a50b04778ab6e3cdff0832efed06257624fd7c35d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ad2dad79c304adfc35c20a50b04778ab6e3cdff0832efed06257624fd7c35d5","first_computed_at":"2026-06-03T01:05:37.486984Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:37.486984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MVSBiXeRbs8nZ21ZtX283ho+sbfDMqYgm2Ot6AVf3WqInUAmjmaIBNgqZ0awZzLq9g6M/B+Jm7Iked7V5CC9Ag==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:37.487407Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03269","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:547811a0d4eec10e4eb796fda610d7f32c0a8f023d6aa74fb3e158166911a915","sha256:3c97419f31eb88b5f3ab8628df7711e58d7e268b3cbd73c8bbcf7f663e68bd2c"],"state_sha256":"dc56859928b0dc8fcf0c563f06bc6e5c3efffacb2e114db7d760ef59a3233081"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UK++VdP9xjQuoHaxu34zkv77mjSCXjsd+ncW8VtcEYCbzUS7v4mVVjc1IlCvnquSXfIdbOFrUz6UUJJDbIRKCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T15:29:06.911767Z","bundle_sha256":"ddd7b5d9d9ed7a994ae4cc4699ea24caba5befcf8afe20b07a397b02cc336207"}}