{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6WWWHJ4WGQHTVZTHPCZYKEY4UF","short_pith_number":"pith:6WWWHJ4W","canonical_record":{"source":{"id":"2605.29687","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T09:51:33Z","cross_cats_sorted":["cs.LO"],"title_canon_sha256":"21eb00e7a3e983d76493c9ce68378dd278e0eb290fdca560f4a0af4666def45e","abstract_canon_sha256":"946711563f52fe469c06655babda8b36fb53d1e7cf6d95cc344882961433dd1a"},"schema_version":"1.0"},"canonical_sha256":"f5ad63a796340f3ae66778b385131ca1480c35823d8af4501f663ddf52e770b8","source":{"kind":"arxiv","id":"2605.29687","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29687","created_at":"2026-05-29T01:05:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29687v1","created_at":"2026-05-29T01:05:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29687","created_at":"2026-05-29T01:05:55Z"},{"alias_kind":"pith_short_12","alias_value":"6WWWHJ4WGQHT","created_at":"2026-05-29T01:05:55Z"},{"alias_kind":"pith_short_16","alias_value":"6WWWHJ4WGQHTVZTH","created_at":"2026-05-29T01:05:55Z"},{"alias_kind":"pith_short_8","alias_value":"6WWWHJ4W","created_at":"2026-05-29T01:05:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6WWWHJ4WGQHTVZTHPCZYKEY4UF","target":"record","payload":{"canonical_record":{"source":{"id":"2605.29687","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T09:51:33Z","cross_cats_sorted":["cs.LO"],"title_canon_sha256":"21eb00e7a3e983d76493c9ce68378dd278e0eb290fdca560f4a0af4666def45e","abstract_canon_sha256":"946711563f52fe469c06655babda8b36fb53d1e7cf6d95cc344882961433dd1a"},"schema_version":"1.0"},"canonical_sha256":"f5ad63a796340f3ae66778b385131ca1480c35823d8af4501f663ddf52e770b8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:55.649086Z","signature_b64":"i+zfiHcVu1BPNOwCtuaAR9ydQFH90Qha3VETcWiXe3IcsdpxWbVW7Hfkk9d9QFtJTsOvC9WlP4ODEQVg6SqpCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5ad63a796340f3ae66778b385131ca1480c35823d8af4501f663ddf52e770b8","last_reissued_at":"2026-05-29T01:05:55.648523Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:55.648523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.29687","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":"2026-05-29T01:05:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W13uU92R26ng6G5H5lP43XNVImy2BeSSLcoZ7ZUt7YzrVcKj+C+KSa7knOVN1PEgL3p9GwvJIkAzbQajrkmRBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T11:01:38.722081Z"},"content_sha256":"286bbab23b49d0b7b2d08ada2aeaacc23665d46c861f6a4b7f1d85fc89fc07ab","schema_version":"1.0","event_id":"sha256:286bbab23b49d0b7b2d08ada2aeaacc23665d46c861f6a4b7f1d85fc89fc07ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6WWWHJ4WGQHTVZTHPCZYKEY4UF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reliable Reasoning with Large Language Models via Preference-Based Maximum Satisfiability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LO"],"primary_cat":"cs.AI","authors_text":"Felip Many\\`a, Guillem Aleny\\`a, Marta Kwiatkowska, Pedro Orvalho","submitted_at":"2026-05-28T09:51:33Z","abstract_excerpt":"Large Language Models (LLMs) excel at understanding natural language but struggle with optimisation tasks involving multiple constraints and user-defined preferences, which commonly arise in domains such as robotics. We propose a hybrid reasoning approach in which LLMs externalise reasoning through code generation. Given a natural language problem description, an LLM generates Python code that encodes user-defined constraints and preferences as a preference-based Maximum Satisfiability (MaxSAT) problem, which is then solved by an exact MaxSAT solver. To ensure correctness, solutions returned b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29687","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/2605.29687/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":"2026-05-29T01:05:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TxHCgEHON7megCwji3osF3aPu51SuHHuqYiUf7LvUTesVH1QAMRRnv6F6xMhCKqntTjuKMrWQziz3W3s2IJ3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T11:01:38.722489Z"},"content_sha256":"dd87cd2dd18a04277603495989c1e8a8c40be95632d6ce60951da51ab02ca09d","schema_version":"1.0","event_id":"sha256:dd87cd2dd18a04277603495989c1e8a8c40be95632d6ce60951da51ab02ca09d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6WWWHJ4WGQHTVZTHPCZYKEY4UF/bundle.json","state_url":"https://pith.science/pith/6WWWHJ4WGQHTVZTHPCZYKEY4UF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6WWWHJ4WGQHTVZTHPCZYKEY4UF/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":"2026-06-03T11:01:38Z","links":{"resolver":"https://pith.science/pith/6WWWHJ4WGQHTVZTHPCZYKEY4UF","bundle":"https://pith.science/pith/6WWWHJ4WGQHTVZTHPCZYKEY4UF/bundle.json","state":"https://pith.science/pith/6WWWHJ4WGQHTVZTHPCZYKEY4UF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6WWWHJ4WGQHTVZTHPCZYKEY4UF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6WWWHJ4WGQHTVZTHPCZYKEY4UF","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":"946711563f52fe469c06655babda8b36fb53d1e7cf6d95cc344882961433dd1a","cross_cats_sorted":["cs.LO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T09:51:33Z","title_canon_sha256":"21eb00e7a3e983d76493c9ce68378dd278e0eb290fdca560f4a0af4666def45e"},"schema_version":"1.0","source":{"id":"2605.29687","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29687","created_at":"2026-05-29T01:05:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29687v1","created_at":"2026-05-29T01:05:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29687","created_at":"2026-05-29T01:05:55Z"},{"alias_kind":"pith_short_12","alias_value":"6WWWHJ4WGQHT","created_at":"2026-05-29T01:05:55Z"},{"alias_kind":"pith_short_16","alias_value":"6WWWHJ4WGQHTVZTH","created_at":"2026-05-29T01:05:55Z"},{"alias_kind":"pith_short_8","alias_value":"6WWWHJ4W","created_at":"2026-05-29T01:05:55Z"}],"graph_snapshots":[{"event_id":"sha256:dd87cd2dd18a04277603495989c1e8a8c40be95632d6ce60951da51ab02ca09d","target":"graph","created_at":"2026-05-29T01:05:55Z","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/2605.29687/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) excel at understanding natural language but struggle with optimisation tasks involving multiple constraints and user-defined preferences, which commonly arise in domains such as robotics. We propose a hybrid reasoning approach in which LLMs externalise reasoning through code generation. Given a natural language problem description, an LLM generates Python code that encodes user-defined constraints and preferences as a preference-based Maximum Satisfiability (MaxSAT) problem, which is then solved by an exact MaxSAT solver. To ensure correctness, solutions returned b","authors_text":"Felip Many\\`a, Guillem Aleny\\`a, Marta Kwiatkowska, Pedro Orvalho","cross_cats":["cs.LO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T09:51:33Z","title":"Reliable Reasoning with Large Language Models via Preference-Based Maximum Satisfiability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29687","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":"sha256:286bbab23b49d0b7b2d08ada2aeaacc23665d46c861f6a4b7f1d85fc89fc07ab","target":"record","created_at":"2026-05-29T01:05:55Z","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":"946711563f52fe469c06655babda8b36fb53d1e7cf6d95cc344882961433dd1a","cross_cats_sorted":["cs.LO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T09:51:33Z","title_canon_sha256":"21eb00e7a3e983d76493c9ce68378dd278e0eb290fdca560f4a0af4666def45e"},"schema_version":"1.0","source":{"id":"2605.29687","kind":"arxiv","version":1}},"canonical_sha256":"f5ad63a796340f3ae66778b385131ca1480c35823d8af4501f663ddf52e770b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5ad63a796340f3ae66778b385131ca1480c35823d8af4501f663ddf52e770b8","first_computed_at":"2026-05-29T01:05:55.648523Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:55.648523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i+zfiHcVu1BPNOwCtuaAR9ydQFH90Qha3VETcWiXe3IcsdpxWbVW7Hfkk9d9QFtJTsOvC9WlP4ODEQVg6SqpCw==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:55.649086Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29687","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:286bbab23b49d0b7b2d08ada2aeaacc23665d46c861f6a4b7f1d85fc89fc07ab","sha256:dd87cd2dd18a04277603495989c1e8a8c40be95632d6ce60951da51ab02ca09d"],"state_sha256":"ae26443371c0271c0db4d981345e752e97a7c2c4d9716da5848ac3f484dcb9f8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uIovy1rV7Tn+EbMGMcuRxtEWVYcLKsKiJh87TFAzmGuuqKXfR90/Epd6LhFtTxbfhnYjj9wvjUBTVlN/o1yODA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T11:01:38.724602Z","bundle_sha256":"70541db78603e370867dfe617c12a2b7130cc68a96a90c74523430fcb2193030"}}