{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:62NIU4XODP23PRMANAMRYAIQM7","short_pith_number":"pith:62NIU4XO","canonical_record":{"source":{"id":"2606.05716","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T05:17:23Z","cross_cats_sorted":[],"title_canon_sha256":"ed4e8ac10982619cb946c57e4a21f942d2dd5eea66ca7a13d050fea8ec5b59bb","abstract_canon_sha256":"027bc8bafa5005785eaae4813d90231e5f8188e0778106be57a2f3537687af8e"},"schema_version":"1.0"},"canonical_sha256":"f69a8a72ee1bf5b7c58068191c011067db78d921f05c4d94e3281079b792b7f0","source":{"kind":"arxiv","id":"2606.05716","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05716","created_at":"2026-06-05T01:15:00Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05716v1","created_at":"2026-06-05T01:15:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05716","created_at":"2026-06-05T01:15:00Z"},{"alias_kind":"pith_short_12","alias_value":"62NIU4XODP23","created_at":"2026-06-05T01:15:00Z"},{"alias_kind":"pith_short_16","alias_value":"62NIU4XODP23PRMA","created_at":"2026-06-05T01:15:00Z"},{"alias_kind":"pith_short_8","alias_value":"62NIU4XO","created_at":"2026-06-05T01:15:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:62NIU4XODP23PRMANAMRYAIQM7","target":"record","payload":{"canonical_record":{"source":{"id":"2606.05716","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T05:17:23Z","cross_cats_sorted":[],"title_canon_sha256":"ed4e8ac10982619cb946c57e4a21f942d2dd5eea66ca7a13d050fea8ec5b59bb","abstract_canon_sha256":"027bc8bafa5005785eaae4813d90231e5f8188e0778106be57a2f3537687af8e"},"schema_version":"1.0"},"canonical_sha256":"f69a8a72ee1bf5b7c58068191c011067db78d921f05c4d94e3281079b792b7f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:00.120820Z","signature_b64":"lLP7EcdcRPBTHrqzSI7h88qjJ7TsofpwDXpKNDOipiqvb9Bs7C3tu7oIUAviCaaSx3qdKlb4Z35xeq4xNQEVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f69a8a72ee1bf5b7c58068191c011067db78d921f05c4d94e3281079b792b7f0","last_reissued_at":"2026-06-05T01:15:00.120161Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:00.120161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.05716","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":"2026-06-05T01:15:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u0pWCsWtFpB/q3xOVv5vov6AufBx4FEuUTKf/0BgaX1yeFXLy9y4Ni03493RlOTO9sGXOI/D5sO5l3FGzpsMDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T08:47:01.782723Z"},"content_sha256":"1ed5bb0b77742a4168c024f6a3e4ddcfb98a5bf8533ad85a13160c8f5a669641","schema_version":"1.0","event_id":"sha256:1ed5bb0b77742a4168c024f6a3e4ddcfb98a5bf8533ad85a13160c8f5a669641"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:62NIU4XODP23PRMANAMRYAIQM7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Interpreting Style Representations via Style-Eliciting Prompts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Jurgens, Junghwan Kim","submitted_at":"2026-06-04T05:17:23Z","abstract_excerpt":"Style representation learning is a powerful tool for authorship analysis and modeling writing style, yet the latent nature of learned representations makes them difficult to interpret. Recent work has attempted to explain these representations by generating natural language descriptions with large language models (LLMs) conditioned on input text. However, such descriptions are often prone to the LLM's biases and hallucinations, and they lack an explicit objective and practical utility. In this work, we propose a novel framework for interpreting style representations through style-eliciting pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05716","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/2606.05716/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":"2026-06-05T01:15:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fflhYtGaebYJw7v2pkY8brNY+MY/izgAq9qsdOaKr8oKc6BppR6cZBz1s4EbzlOHQIALfaAJqUxMbzwHC7VqDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T08:47:01.783102Z"},"content_sha256":"0050465efe4e8ad5cf6dbd754e1b296cc9ebb758926740c5a9a36a0dea74fb31","schema_version":"1.0","event_id":"sha256:0050465efe4e8ad5cf6dbd754e1b296cc9ebb758926740c5a9a36a0dea74fb31"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/62NIU4XODP23PRMANAMRYAIQM7/bundle.json","state_url":"https://pith.science/pith/62NIU4XODP23PRMANAMRYAIQM7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/62NIU4XODP23PRMANAMRYAIQM7/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":"2026-06-28T08:47:01Z","links":{"resolver":"https://pith.science/pith/62NIU4XODP23PRMANAMRYAIQM7","bundle":"https://pith.science/pith/62NIU4XODP23PRMANAMRYAIQM7/bundle.json","state":"https://pith.science/pith/62NIU4XODP23PRMANAMRYAIQM7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/62NIU4XODP23PRMANAMRYAIQM7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:62NIU4XODP23PRMANAMRYAIQM7","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":"027bc8bafa5005785eaae4813d90231e5f8188e0778106be57a2f3537687af8e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T05:17:23Z","title_canon_sha256":"ed4e8ac10982619cb946c57e4a21f942d2dd5eea66ca7a13d050fea8ec5b59bb"},"schema_version":"1.0","source":{"id":"2606.05716","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05716","created_at":"2026-06-05T01:15:00Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05716v1","created_at":"2026-06-05T01:15:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05716","created_at":"2026-06-05T01:15:00Z"},{"alias_kind":"pith_short_12","alias_value":"62NIU4XODP23","created_at":"2026-06-05T01:15:00Z"},{"alias_kind":"pith_short_16","alias_value":"62NIU4XODP23PRMA","created_at":"2026-06-05T01:15:00Z"},{"alias_kind":"pith_short_8","alias_value":"62NIU4XO","created_at":"2026-06-05T01:15:00Z"}],"graph_snapshots":[{"event_id":"sha256:0050465efe4e8ad5cf6dbd754e1b296cc9ebb758926740c5a9a36a0dea74fb31","target":"graph","created_at":"2026-06-05T01:15:00Z","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/2606.05716/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Style representation learning is a powerful tool for authorship analysis and modeling writing style, yet the latent nature of learned representations makes them difficult to interpret. Recent work has attempted to explain these representations by generating natural language descriptions with large language models (LLMs) conditioned on input text. However, such descriptions are often prone to the LLM's biases and hallucinations, and they lack an explicit objective and practical utility. In this work, we propose a novel framework for interpreting style representations through style-eliciting pro","authors_text":"David Jurgens, Junghwan Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T05:17:23Z","title":"Interpreting Style Representations via Style-Eliciting Prompts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05716","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":"sha256:1ed5bb0b77742a4168c024f6a3e4ddcfb98a5bf8533ad85a13160c8f5a669641","target":"record","created_at":"2026-06-05T01:15:00Z","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":"027bc8bafa5005785eaae4813d90231e5f8188e0778106be57a2f3537687af8e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T05:17:23Z","title_canon_sha256":"ed4e8ac10982619cb946c57e4a21f942d2dd5eea66ca7a13d050fea8ec5b59bb"},"schema_version":"1.0","source":{"id":"2606.05716","kind":"arxiv","version":1}},"canonical_sha256":"f69a8a72ee1bf5b7c58068191c011067db78d921f05c4d94e3281079b792b7f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f69a8a72ee1bf5b7c58068191c011067db78d921f05c4d94e3281079b792b7f0","first_computed_at":"2026-06-05T01:15:00.120161Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:00.120161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lLP7EcdcRPBTHrqzSI7h88qjJ7TsofpwDXpKNDOipiqvb9Bs7C3tu7oIUAviCaaSx3qdKlb4Z35xeq4xNQEVDg==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:00.120820Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05716","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ed5bb0b77742a4168c024f6a3e4ddcfb98a5bf8533ad85a13160c8f5a669641","sha256:0050465efe4e8ad5cf6dbd754e1b296cc9ebb758926740c5a9a36a0dea74fb31"],"state_sha256":"d95876e793ca402cd33e18572b25ca674ac5a6bb33acea285dcc313892dbc902"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hUnVggr2DbP9aP/2zp3mnJVQwHKwcptWWMdT/NRbPGQgR7923qoG0qP79R5EOVa94DNBst5ZYH09DqJNchH5Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T08:47:01.785135Z","bundle_sha256":"38ac74e3562b3663f8fa79e299a4a9bfc4f776c14f5ed953a71f2fd36995ca12"}}