{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZLXRA7BPVZBSBGW77WOIMO44OH","short_pith_number":"pith:ZLXRA7BP","canonical_record":{"source":{"id":"2605.17714","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-18T00:31:46Z","cross_cats_sorted":[],"title_canon_sha256":"da5e3a67d1467b351289b4f97dedb02b6733e2e435c592c3d725c789c2c9e88a","abstract_canon_sha256":"b20b1861db6fd52a17c98ffbee3d29712be17270b31b9b83ef62a94512a7ab9c"},"schema_version":"1.0"},"canonical_sha256":"caef107c2fae43209adffd9c863b9c71dc719f09266e87bd612bf0ae04d6d57c","source":{"kind":"arxiv","id":"2605.17714","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17714","created_at":"2026-05-20T00:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17714v1","created_at":"2026-05-20T00:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17714","created_at":"2026-05-20T00:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"ZLXRA7BPVZBS","created_at":"2026-05-20T00:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"ZLXRA7BPVZBSBGW7","created_at":"2026-05-20T00:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"ZLXRA7BP","created_at":"2026-05-20T00:04:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZLXRA7BPVZBSBGW77WOIMO44OH","target":"record","payload":{"canonical_record":{"source":{"id":"2605.17714","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-18T00:31:46Z","cross_cats_sorted":[],"title_canon_sha256":"da5e3a67d1467b351289b4f97dedb02b6733e2e435c592c3d725c789c2c9e88a","abstract_canon_sha256":"b20b1861db6fd52a17c98ffbee3d29712be17270b31b9b83ef62a94512a7ab9c"},"schema_version":"1.0"},"canonical_sha256":"caef107c2fae43209adffd9c863b9c71dc719f09266e87bd612bf0ae04d6d57c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:54.293021Z","signature_b64":"idFhBpafq4l3Q4AjdURvCS+eUlhyQh5w4iBf0RmqHg7/0IZjhXsEy/wKfwNbo+URfWxOeFcTEUCDIPHq13cUAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"caef107c2fae43209adffd9c863b9c71dc719f09266e87bd612bf0ae04d6d57c","last_reissued_at":"2026-05-20T00:04:54.292156Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:54.292156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.17714","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":"2026-05-20T00:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JF29z2DDX+/QD3cwUhnYAxVA5w+WeHC35bqlV03HQk/zki5zIHtjQjqaVRbHjQuPAY6eORfexfWiUj0IKZ7jCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T13:45:15.294534Z"},"content_sha256":"0d6832981b2dedd6db29a298fea667c5528608ca543c0cfe633c870b4fdbd179","schema_version":"1.0","event_id":"sha256:0d6832981b2dedd6db29a298fea667c5528608ca543c0cfe633c870b4fdbd179"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZLXRA7BPVZBSBGW77WOIMO44OH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Documents to Segments: A Contextual Reformulation for Topic Assignment","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Assigning topics to short coherent segments rather than whole documents yields cleaner and more interpretable topics.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dilek Hakkani-T\\\"ur, Hoonsang Yoon, Ilmin Cho, Stanley Jungkyu Choi, Takyoung Kim, Wonkee Lee","submitted_at":"2026-05-18T00:31:46Z","abstract_excerpt":"Traditional topic modeling assigns a single topic to each document. In practice, however, many real-world documents, such as product reviews or open-ended survey responses, contain multiple distinct topics. This mismatch often leads to topic contamination, where unrelated themes are merged into a single topic, making it difficult to identify documents that truly focus on a specific subject. We address this issue by introducing segment-based topic allocation (SBTA), a reformulation of topic modeling that assigns topics not to entire documents, but to segments: short, coherent spans of text that"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"By modeling topical structure at the segment level, our approach yields cleaner and more interpretable topics and better supports analysis of multi-theme documents.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That documents can be reliably decomposed into high-quality topical segments using LLMs followed by human refinement, which underpins both the new SemEval-STM dataset and the claim that segment-level assignment improves topic quality.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SBTA reformulates topic modeling to assign topics at the segment level rather than document level, yielding cleaner topics on a new SemEval-STM dataset created via LLM decomposition and human refinement.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Assigning topics to short coherent segments rather than whole documents yields cleaner and more interpretable topics.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a14710efcd45206d1b30312499673651b9a5e88debb18d9fe7c3bdebc2486a9b"},"source":{"id":"2605.17714","kind":"arxiv","version":1},"verdict":{"id":"6a3f9f0e-a60c-4463-8ef9-3c7a5de9482c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T21:55:31.139987Z","strongest_claim":"By modeling topical structure at the segment level, our approach yields cleaner and more interpretable topics and better supports analysis of multi-theme documents.","one_line_summary":"SBTA reformulates topic modeling to assign topics at the segment level rather than document level, yielding cleaner topics on a new SemEval-STM dataset created via LLM decomposition and human refinement.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That documents can be reliably decomposed into high-quality topical segments using LLMs followed by human refinement, which underpins both the new SemEval-STM dataset and the claim that segment-level assignment improves topic quality.","pith_extraction_headline":"Assigning topics to short coherent segments rather than whole documents yields cleaner and more interpretable topics."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.17714/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T22:01:19.460906Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T22:01:02.325888Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"shingle_duplication","ran_at":"2026-05-19T21:49:43.472280Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T21:49:43.301579Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.505457Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"cited_work_retraction","ran_at":"2026-05-19T21:21:58.137377Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T21:21:57.409982Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"4afcd89a2423f888b3fcd03c549cec0aa7ef1a01aa793bff116ec505032d2a5a"},"references":{"count":60,"sample":[{"doi":"","year":2003,"title":"and Ng, Andrew Y","work_id":"03fb5d46-e3e0-415d-976a-062335946fb5","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.18653/v1/2024.naacl-long.164","year":2024,"title":"Chau Minh Pham, Alexander Hoyle, Simeng Sun, Philip Resnik, and Mohit Iyyer","work_id":"700a4488-2793-4ea0-adba-b6cfd710205e","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.18653/v1/2022.findings-emnlp.390","year":2022,"title":"Are Neural Topic Models Broken?","work_id":"3385c2b5-6d42-4f40-b706-d89b33763e9f","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.18653/v1/2023.emnlp-main.581","year":2023,"title":"Revisiting Automated Topic Model Evaluation with Large Language Models","work_id":"b346ac84-9d11-4043-979a-6b553dd2c2a5","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.18653/v1/s16-1002","year":2016,"title":"S em E val-2016 Task 5: Aspect Based Sentiment Analysis","work_id":"8a70177e-ed28-4252-a581-6ab0777dd00b","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":60,"snapshot_sha256":"a7ea52724d56351baca16d48506ec04e14b7d217bc6fb64b54644b4a2cebaf88","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":"6a3f9f0e-a60c-4463-8ef9-3c7a5de9482c"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5iZdR4xrE93iyC5uTNC9OMpyx4J2czz3lCyq+YCP+RY59XFlVrDOOT4Z4zDEin19mvXJoSxqk6Fr8tBuzRjhBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T13:45:15.295181Z"},"content_sha256":"34114bfd717a77405d273e83894339551936b550526040ffbe02964e7e57f891","schema_version":"1.0","event_id":"sha256:34114bfd717a77405d273e83894339551936b550526040ffbe02964e7e57f891"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZLXRA7BPVZBSBGW77WOIMO44OH/bundle.json","state_url":"https://pith.science/pith/ZLXRA7BPVZBSBGW77WOIMO44OH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZLXRA7BPVZBSBGW77WOIMO44OH/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":"2026-06-05T13:45:15Z","links":{"resolver":"https://pith.science/pith/ZLXRA7BPVZBSBGW77WOIMO44OH","bundle":"https://pith.science/pith/ZLXRA7BPVZBSBGW77WOIMO44OH/bundle.json","state":"https://pith.science/pith/ZLXRA7BPVZBSBGW77WOIMO44OH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZLXRA7BPVZBSBGW77WOIMO44OH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZLXRA7BPVZBSBGW77WOIMO44OH","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":"b20b1861db6fd52a17c98ffbee3d29712be17270b31b9b83ef62a94512a7ab9c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-18T00:31:46Z","title_canon_sha256":"da5e3a67d1467b351289b4f97dedb02b6733e2e435c592c3d725c789c2c9e88a"},"schema_version":"1.0","source":{"id":"2605.17714","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17714","created_at":"2026-05-20T00:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17714v1","created_at":"2026-05-20T00:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17714","created_at":"2026-05-20T00:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"ZLXRA7BPVZBS","created_at":"2026-05-20T00:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"ZLXRA7BPVZBSBGW7","created_at":"2026-05-20T00:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"ZLXRA7BP","created_at":"2026-05-20T00:04:54Z"}],"graph_snapshots":[{"event_id":"sha256:34114bfd717a77405d273e83894339551936b550526040ffbe02964e7e57f891","target":"graph","created_at":"2026-05-20T00:04:54Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"By modeling topical structure at the segment level, our approach yields cleaner and more interpretable topics and better supports analysis of multi-theme documents."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That documents can be reliably decomposed into high-quality topical segments using LLMs followed by human refinement, which underpins both the new SemEval-STM dataset and the claim that segment-level assignment improves topic quality."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"SBTA reformulates topic modeling to assign topics at the segment level rather than document level, yielding cleaner topics on a new SemEval-STM dataset created via LLM decomposition and human refinement."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Assigning topics to short coherent segments rather than whole documents yields cleaner and more interpretable topics."}],"snapshot_sha256":"a14710efcd45206d1b30312499673651b9a5e88debb18d9fe7c3bdebc2486a9b"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T22:01:19.460906Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T22:01:02.325888Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"shingle_duplication","ran_at":"2026-05-19T21:49:43.472280Z","status":"skipped","version":"0.1.0"},{"findings_count":0,"name":"citation_quote_validity","ran_at":"2026-05-19T21:49:43.301579Z","status":"skipped","version":"0.1.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.505457Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"cited_work_retraction","ran_at":"2026-05-19T21:21:58.137377Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T21:21:57.409982Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.17714/integrity.json","findings":[],"snapshot_sha256":"4afcd89a2423f888b3fcd03c549cec0aa7ef1a01aa793bff116ec505032d2a5a","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional topic modeling assigns a single topic to each document. In practice, however, many real-world documents, such as product reviews or open-ended survey responses, contain multiple distinct topics. This mismatch often leads to topic contamination, where unrelated themes are merged into a single topic, making it difficult to identify documents that truly focus on a specific subject. We address this issue by introducing segment-based topic allocation (SBTA), a reformulation of topic modeling that assigns topics not to entire documents, but to segments: short, coherent spans of text that","authors_text":"Dilek Hakkani-T\\\"ur, Hoonsang Yoon, Ilmin Cho, Stanley Jungkyu Choi, Takyoung Kim, Wonkee Lee","cross_cats":[],"headline":"Assigning topics to short coherent segments rather than whole documents yields cleaner and more interpretable topics.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-18T00:31:46Z","title":"From Documents to Segments: A Contextual Reformulation for Topic Assignment"},"references":{"count":60,"internal_anchors":0,"resolved_work":60,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"and Ng, Andrew Y","work_id":"03fb5d46-e3e0-415d-976a-062335946fb5","year":2003},{"cited_arxiv_id":"","doi":"10.18653/v1/2024.naacl-long.164","is_internal_anchor":false,"ref_index":2,"title":"Chau Minh Pham, Alexander Hoyle, Simeng Sun, Philip Resnik, and Mohit Iyyer","work_id":"700a4488-2793-4ea0-adba-b6cfd710205e","year":2024},{"cited_arxiv_id":"","doi":"10.18653/v1/2022.findings-emnlp.390","is_internal_anchor":false,"ref_index":3,"title":"Are Neural Topic Models Broken?","work_id":"3385c2b5-6d42-4f40-b706-d89b33763e9f","year":2022},{"cited_arxiv_id":"","doi":"10.18653/v1/2023.emnlp-main.581","is_internal_anchor":false,"ref_index":4,"title":"Revisiting Automated Topic Model Evaluation with Large Language Models","work_id":"b346ac84-9d11-4043-979a-6b553dd2c2a5","year":2023},{"cited_arxiv_id":"","doi":"10.18653/v1/s16-1002","is_internal_anchor":false,"ref_index":5,"title":"S em E val-2016 Task 5: Aspect Based Sentiment Analysis","work_id":"8a70177e-ed28-4252-a581-6ab0777dd00b","year":2016}],"snapshot_sha256":"a7ea52724d56351baca16d48506ec04e14b7d217bc6fb64b54644b4a2cebaf88"},"source":{"id":"2605.17714","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T21:55:31.139987Z","id":"6a3f9f0e-a60c-4463-8ef9-3c7a5de9482c","model_set":{"reader":"grok-4.3"},"one_line_summary":"SBTA reformulates topic modeling to assign topics at the segment level rather than document level, yielding cleaner topics on a new SemEval-STM dataset created via LLM decomposition and human refinement.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Assigning topics to short coherent segments rather than whole documents yields cleaner and more interpretable topics.","strongest_claim":"By modeling topical structure at the segment level, our approach yields cleaner and more interpretable topics and better supports analysis of multi-theme documents.","weakest_assumption":"That documents can be reliably decomposed into high-quality topical segments using LLMs followed by human refinement, which underpins both the new SemEval-STM dataset and the claim that segment-level assignment improves topic quality."}},"verdict_id":"6a3f9f0e-a60c-4463-8ef9-3c7a5de9482c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0d6832981b2dedd6db29a298fea667c5528608ca543c0cfe633c870b4fdbd179","target":"record","created_at":"2026-05-20T00:04:54Z","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":"b20b1861db6fd52a17c98ffbee3d29712be17270b31b9b83ef62a94512a7ab9c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-18T00:31:46Z","title_canon_sha256":"da5e3a67d1467b351289b4f97dedb02b6733e2e435c592c3d725c789c2c9e88a"},"schema_version":"1.0","source":{"id":"2605.17714","kind":"arxiv","version":1}},"canonical_sha256":"caef107c2fae43209adffd9c863b9c71dc719f09266e87bd612bf0ae04d6d57c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"caef107c2fae43209adffd9c863b9c71dc719f09266e87bd612bf0ae04d6d57c","first_computed_at":"2026-05-20T00:04:54.292156Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:54.292156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"idFhBpafq4l3Q4AjdURvCS+eUlhyQh5w4iBf0RmqHg7/0IZjhXsEy/wKfwNbo+URfWxOeFcTEUCDIPHq13cUAA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:54.293021Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17714","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d6832981b2dedd6db29a298fea667c5528608ca543c0cfe633c870b4fdbd179","sha256:34114bfd717a77405d273e83894339551936b550526040ffbe02964e7e57f891"],"state_sha256":"4128cc7f2528b6454b445919611243d040e452c6a5006633bee83a9a270be539"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6EgBkpQhyW6+9/fGslsk80uwCwPrx236lkx113yqsN16F9sn2L6QXC/cvbgWtGB8O+6vTFQRk4tdXlAQlgUOBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T13:45:15.297882Z","bundle_sha256":"9d262af530a506f1f9df41fab3713bb26d5fbc7dbc40e2a5670179650264a731"}}