{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LLWA536D63MJCUMC2RYMP4R2SK","short_pith_number":"pith:LLWA536D","canonical_record":{"source":{"id":"2507.12064","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-16T09:21:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f35b16c63e7af3c9f206f6d88a62287eb562d79609233e680e5973b2751da14d","abstract_canon_sha256":"b10b63cf64ec20e00c1e28ad8f63a7b53717ab9bec448f5382d39170bf0e04ee"},"schema_version":"1.0"},"canonical_sha256":"5aec0eefc3f6d8915182d470c7f23a9283f08e08aa1ed02c004ef6462a378866","source":{"kind":"arxiv","id":"2507.12064","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.12064","created_at":"2026-07-05T11:38:13Z"},{"alias_kind":"arxiv_version","alias_value":"2507.12064v1","created_at":"2026-07-05T11:38:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12064","created_at":"2026-07-05T11:38:13Z"},{"alias_kind":"pith_short_12","alias_value":"LLWA536D63MJ","created_at":"2026-07-05T11:38:13Z"},{"alias_kind":"pith_short_16","alias_value":"LLWA536D63MJCUMC","created_at":"2026-07-05T11:38:13Z"},{"alias_kind":"pith_short_8","alias_value":"LLWA536D","created_at":"2026-07-05T11:38:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LLWA536D63MJCUMC2RYMP4R2SK","target":"record","payload":{"canonical_record":{"source":{"id":"2507.12064","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-16T09:21:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f35b16c63e7af3c9f206f6d88a62287eb562d79609233e680e5973b2751da14d","abstract_canon_sha256":"b10b63cf64ec20e00c1e28ad8f63a7b53717ab9bec448f5382d39170bf0e04ee"},"schema_version":"1.0"},"canonical_sha256":"5aec0eefc3f6d8915182d470c7f23a9283f08e08aa1ed02c004ef6462a378866","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:13.837437Z","signature_b64":"aswpljN6xImehA66Eoh+djvzOCW2RyX1uhCisvqVPAU82lkbXgiTSUmc7JLhW6u7JHOJnVZcTNOcYWce2d6WDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5aec0eefc3f6d8915182d470c7f23a9283f08e08aa1ed02c004ef6462a378866","last_reissued_at":"2026-07-05T11:38:13.836966Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:13.836966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.12064","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":"2026-07-05T11:38:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3ALcjCTwkm5LHzXFoMSKGjw8LZpljg7EY8ehLE1hVdctOR9FYFBo4SpGXlWbSKsv99uUqgnta8tvlKJVl1ezCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:05:32.214928Z"},"content_sha256":"be5388de2650036ac6b421bfacdc26bf0a72aa56356e4eda99aa706ef9e21c46","schema_version":"1.0","event_id":"sha256:be5388de2650036ac6b421bfacdc26bf0a72aa56356e4eda99aa706ef9e21c46"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LLWA536D63MJCUMC2RYMP4R2SK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"StylOch at PAN: Gradient-Boosted Trees with Frequency-Based Stylometric Features","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jeremi K. Ochab, Mateusz Matias, Tomasz Walkowiak, Tymoteusz Boba","submitted_at":"2025-07-16T09:21:20Z","abstract_excerpt":"This submission to the binary AI detection task is based on a modular stylometric pipeline, where: public spaCy models are used for text preprocessing (including tokenisation, named entity recognition, dependency parsing, part-of-speech tagging, and morphology annotation) and extracting several thousand features (frequencies of n-grams of the above linguistic annotations); light-gradient boosting machines are used as the classifier. We collect a large corpus of more than 500 000 machine-generated texts for the classifier's training. We explore several parameter options to increase the classifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12064","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/2507.12064/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":"2026-07-05T11:38:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eEzOIkzw1WKFC5PRldar8BLn6Mlsakpkw4wREugYPj4dDUfcpsMqLUtcagrQzo5TE82blNDrRR4qO3FBIvBVBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:05:32.215852Z"},"content_sha256":"6a985729947cf32bda959225f0907090b9affc1f23392284f265445c02088331","schema_version":"1.0","event_id":"sha256:6a985729947cf32bda959225f0907090b9affc1f23392284f265445c02088331"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LLWA536D63MJCUMC2RYMP4R2SK/bundle.json","state_url":"https://pith.science/pith/LLWA536D63MJCUMC2RYMP4R2SK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LLWA536D63MJCUMC2RYMP4R2SK/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":"2026-08-08T09:05:32Z","links":{"resolver":"https://pith.science/pith/LLWA536D63MJCUMC2RYMP4R2SK","bundle":"https://pith.science/pith/LLWA536D63MJCUMC2RYMP4R2SK/bundle.json","state":"https://pith.science/pith/LLWA536D63MJCUMC2RYMP4R2SK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LLWA536D63MJCUMC2RYMP4R2SK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LLWA536D63MJCUMC2RYMP4R2SK","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":"b10b63cf64ec20e00c1e28ad8f63a7b53717ab9bec448f5382d39170bf0e04ee","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-16T09:21:20Z","title_canon_sha256":"f35b16c63e7af3c9f206f6d88a62287eb562d79609233e680e5973b2751da14d"},"schema_version":"1.0","source":{"id":"2507.12064","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.12064","created_at":"2026-07-05T11:38:13Z"},{"alias_kind":"arxiv_version","alias_value":"2507.12064v1","created_at":"2026-07-05T11:38:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12064","created_at":"2026-07-05T11:38:13Z"},{"alias_kind":"pith_short_12","alias_value":"LLWA536D63MJ","created_at":"2026-07-05T11:38:13Z"},{"alias_kind":"pith_short_16","alias_value":"LLWA536D63MJCUMC","created_at":"2026-07-05T11:38:13Z"},{"alias_kind":"pith_short_8","alias_value":"LLWA536D","created_at":"2026-07-05T11:38:13Z"}],"graph_snapshots":[{"event_id":"sha256:6a985729947cf32bda959225f0907090b9affc1f23392284f265445c02088331","target":"graph","created_at":"2026-07-05T11:38:13Z","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/2507.12064/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This submission to the binary AI detection task is based on a modular stylometric pipeline, where: public spaCy models are used for text preprocessing (including tokenisation, named entity recognition, dependency parsing, part-of-speech tagging, and morphology annotation) and extracting several thousand features (frequencies of n-grams of the above linguistic annotations); light-gradient boosting machines are used as the classifier. We collect a large corpus of more than 500 000 machine-generated texts for the classifier's training. We explore several parameter options to increase the classifi","authors_text":"Jeremi K. Ochab, Mateusz Matias, Tomasz Walkowiak, Tymoteusz Boba","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-16T09:21:20Z","title":"StylOch at PAN: Gradient-Boosted Trees with Frequency-Based Stylometric Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12064","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:be5388de2650036ac6b421bfacdc26bf0a72aa56356e4eda99aa706ef9e21c46","target":"record","created_at":"2026-07-05T11:38:13Z","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":"b10b63cf64ec20e00c1e28ad8f63a7b53717ab9bec448f5382d39170bf0e04ee","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-16T09:21:20Z","title_canon_sha256":"f35b16c63e7af3c9f206f6d88a62287eb562d79609233e680e5973b2751da14d"},"schema_version":"1.0","source":{"id":"2507.12064","kind":"arxiv","version":1}},"canonical_sha256":"5aec0eefc3f6d8915182d470c7f23a9283f08e08aa1ed02c004ef6462a378866","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5aec0eefc3f6d8915182d470c7f23a9283f08e08aa1ed02c004ef6462a378866","first_computed_at":"2026-07-05T11:38:13.836966Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:13.836966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aswpljN6xImehA66Eoh+djvzOCW2RyX1uhCisvqVPAU82lkbXgiTSUmc7JLhW6u7JHOJnVZcTNOcYWce2d6WDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:13.837437Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.12064","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be5388de2650036ac6b421bfacdc26bf0a72aa56356e4eda99aa706ef9e21c46","sha256:6a985729947cf32bda959225f0907090b9affc1f23392284f265445c02088331"],"state_sha256":"e60ee6e8b5954ef5994f4f8c1e2e14d143fd96aa12b8d351c35d48f7a53b8bcb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LHojZ/mjhKTD09AMzcwY7IH2dnMbpWVJKx7jEykUpWOAo9uuOsQ5gC+B364WaW9KxsrIrEE8vVjy77IWlx3mAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:05:32.222727Z","bundle_sha256":"2fe57da4c45886cb2acb3da96a677b198efc0b0892299ca885e283008902858f"}}