{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HOSKEYP4D2YHUGOPLLKDZ2H7HH","short_pith_number":"pith:HOSKEYP4","canonical_record":{"source":{"id":"2506.00985","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T12:38:01Z","cross_cats_sorted":[],"title_canon_sha256":"5273cc7ef3d0363c1ad848eab92507c6d26e475cea532f69caf5bed03d416a9c","abstract_canon_sha256":"f67afb3f4ee89e15580a4109c590998e36d02532d895ba832473f6570b98a0fc"},"schema_version":"1.0"},"canonical_sha256":"3ba4a261fc1eb07a19cf5ad43ce8ff39d992fdca9d3eadbe2cad1b349289e21b","source":{"kind":"arxiv","id":"2506.00985","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00985","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00985v1","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00985","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"pith_short_12","alias_value":"HOSKEYP4D2YH","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"pith_short_16","alias_value":"HOSKEYP4D2YHUGOP","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"pith_short_8","alias_value":"HOSKEYP4","created_at":"2026-07-05T11:13:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HOSKEYP4D2YHUGOPLLKDZ2H7HH","target":"record","payload":{"canonical_record":{"source":{"id":"2506.00985","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T12:38:01Z","cross_cats_sorted":[],"title_canon_sha256":"5273cc7ef3d0363c1ad848eab92507c6d26e475cea532f69caf5bed03d416a9c","abstract_canon_sha256":"f67afb3f4ee89e15580a4109c590998e36d02532d895ba832473f6570b98a0fc"},"schema_version":"1.0"},"canonical_sha256":"3ba4a261fc1eb07a19cf5ad43ce8ff39d992fdca9d3eadbe2cad1b349289e21b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:44.030289Z","signature_b64":"7syoabM0KOJGKHOyEJ7vEcpVI/ccWEE5WfTnzMVKk/+SwrYJ4BmsJV9mARb3mtBcaQoge2ixryC6LWvDJIIgBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ba4a261fc1eb07a19cf5ad43ce8ff39d992fdca9d3eadbe2cad1b349289e21b","last_reissued_at":"2026-07-05T11:13:44.029850Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:44.029850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.00985","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":"2026-07-05T11:13:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"McggpVuN+2Nn+cG4aKZISsK2s4S+FnQK2B8GJ1RbsdLGLjNE6cKoybFUty8ABo+JuzSZMHackS9TBzcTLDdcDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:52:12.830843Z"},"content_sha256":"7c88a419e4133ed16c510e6e0d0150e8573d3bbba6c66f5efb8a43cfa94e8a65","schema_version":"1.0","event_id":"sha256:7c88a419e4133ed16c510e6e0d0150e8573d3bbba6c66f5efb8a43cfa94e8a65"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HOSKEYP4D2YHUGOPLLKDZ2H7HH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do LLMs Understand Why We Write Diaries? A Method for Purpose Extraction and Clustering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Sergeev, Evgeny Kotelnikov, Mikhail Melnichenko, Valeriya Goloviznina","submitted_at":"2025-06-01T12:38:01Z","abstract_excerpt":"Diary analysis presents challenges, particularly in extracting meaningful information from large corpora, where traditional methods often fail to deliver satisfactory results. This study introduces a novel method based on Large Language Models (LLMs) to identify and cluster the various purposes of diary writing. By \"purposes,\" we refer to the intentions behind diary writing, such as documenting life events, self-reflection, or practicing language skills. Our approach is applied to Soviet-era diaries (1922-1929) from the Prozhito digital archive, a rich collection of personal narratives. We eva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00985","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/2506.00985/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":"2026-07-05T11:13:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r9LVD19ACDGyx52iydKfoBVOf0mXyuOoH4ATzBpONPvUalO7J1rA2pTod7pB4+bklj9lmlNdgJ4nTwkhy4ISAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:52:12.831345Z"},"content_sha256":"ebda8e89673c5bea362b3fc93aea9618462f02454d0573de5f66b3bd0047f782","schema_version":"1.0","event_id":"sha256:ebda8e89673c5bea362b3fc93aea9618462f02454d0573de5f66b3bd0047f782"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HOSKEYP4D2YHUGOPLLKDZ2H7HH/bundle.json","state_url":"https://pith.science/pith/HOSKEYP4D2YHUGOPLLKDZ2H7HH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HOSKEYP4D2YHUGOPLLKDZ2H7HH/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":"2026-08-07T23:52:12Z","links":{"resolver":"https://pith.science/pith/HOSKEYP4D2YHUGOPLLKDZ2H7HH","bundle":"https://pith.science/pith/HOSKEYP4D2YHUGOPLLKDZ2H7HH/bundle.json","state":"https://pith.science/pith/HOSKEYP4D2YHUGOPLLKDZ2H7HH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HOSKEYP4D2YHUGOPLLKDZ2H7HH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HOSKEYP4D2YHUGOPLLKDZ2H7HH","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":"f67afb3f4ee89e15580a4109c590998e36d02532d895ba832473f6570b98a0fc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T12:38:01Z","title_canon_sha256":"5273cc7ef3d0363c1ad848eab92507c6d26e475cea532f69caf5bed03d416a9c"},"schema_version":"1.0","source":{"id":"2506.00985","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00985","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00985v1","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00985","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"pith_short_12","alias_value":"HOSKEYP4D2YH","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"pith_short_16","alias_value":"HOSKEYP4D2YHUGOP","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"pith_short_8","alias_value":"HOSKEYP4","created_at":"2026-07-05T11:13:44Z"}],"graph_snapshots":[{"event_id":"sha256:ebda8e89673c5bea362b3fc93aea9618462f02454d0573de5f66b3bd0047f782","target":"graph","created_at":"2026-07-05T11:13:44Z","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/2506.00985/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diary analysis presents challenges, particularly in extracting meaningful information from large corpora, where traditional methods often fail to deliver satisfactory results. This study introduces a novel method based on Large Language Models (LLMs) to identify and cluster the various purposes of diary writing. By \"purposes,\" we refer to the intentions behind diary writing, such as documenting life events, self-reflection, or practicing language skills. Our approach is applied to Soviet-era diaries (1922-1929) from the Prozhito digital archive, a rich collection of personal narratives. We eva","authors_text":"Alexander Sergeev, Evgeny Kotelnikov, Mikhail Melnichenko, Valeriya Goloviznina","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T12:38:01Z","title":"Do LLMs Understand Why We Write Diaries? A Method for Purpose Extraction and Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00985","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":"sha256:7c88a419e4133ed16c510e6e0d0150e8573d3bbba6c66f5efb8a43cfa94e8a65","target":"record","created_at":"2026-07-05T11:13:44Z","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":"f67afb3f4ee89e15580a4109c590998e36d02532d895ba832473f6570b98a0fc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T12:38:01Z","title_canon_sha256":"5273cc7ef3d0363c1ad848eab92507c6d26e475cea532f69caf5bed03d416a9c"},"schema_version":"1.0","source":{"id":"2506.00985","kind":"arxiv","version":1}},"canonical_sha256":"3ba4a261fc1eb07a19cf5ad43ce8ff39d992fdca9d3eadbe2cad1b349289e21b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ba4a261fc1eb07a19cf5ad43ce8ff39d992fdca9d3eadbe2cad1b349289e21b","first_computed_at":"2026-07-05T11:13:44.029850Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:44.029850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7syoabM0KOJGKHOyEJ7vEcpVI/ccWEE5WfTnzMVKk/+SwrYJ4BmsJV9mARb3mtBcaQoge2ixryC6LWvDJIIgBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:44.030289Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00985","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c88a419e4133ed16c510e6e0d0150e8573d3bbba6c66f5efb8a43cfa94e8a65","sha256:ebda8e89673c5bea362b3fc93aea9618462f02454d0573de5f66b3bd0047f782"],"state_sha256":"0120180a144373972a90e9934a3a837be7618644d76062806682d7501b0aab4a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7sxg179rYgMgsDsuzaF2b8/rdfSuMYsauhiJ2EtVgpcbEk1VWS2niWTO3w15UyIzILqoH0kwGBihwozdmsydAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:52:12.836516Z","bundle_sha256":"d00382994c9de607161f3901664c43f781deedcbccd08df5d642fdf41f2a0a83"}}