{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6YVIGAUVNXBA7EKRBHU3H7DVFF","short_pith_number":"pith:6YVIGAUV","canonical_record":{"source":{"id":"2607.03870","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-04T13:25:18Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"6985b0e94b939078478b955fd5752ad71f1b63d78ac195e9f27711b9ae7e6581","abstract_canon_sha256":"cd34c06d9952751cc1d0cff9cd45cf918cba0dd6e360ba99d385f1c8619d1207"},"schema_version":"1.0"},"canonical_sha256":"f62a8302956dc20f915109e9b3fc7529677c5296eada7c12b57ce215513f877b","source":{"kind":"arxiv","id":"2607.03870","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.03870","created_at":"2026-07-07T02:18:11Z"},{"alias_kind":"arxiv_version","alias_value":"2607.03870v1","created_at":"2026-07-07T02:18:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03870","created_at":"2026-07-07T02:18:11Z"},{"alias_kind":"pith_short_12","alias_value":"6YVIGAUVNXBA","created_at":"2026-07-07T02:18:11Z"},{"alias_kind":"pith_short_16","alias_value":"6YVIGAUVNXBA7EKR","created_at":"2026-07-07T02:18:11Z"},{"alias_kind":"pith_short_8","alias_value":"6YVIGAUV","created_at":"2026-07-07T02:18:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6YVIGAUVNXBA7EKRBHU3H7DVFF","target":"record","payload":{"canonical_record":{"source":{"id":"2607.03870","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-04T13:25:18Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"6985b0e94b939078478b955fd5752ad71f1b63d78ac195e9f27711b9ae7e6581","abstract_canon_sha256":"cd34c06d9952751cc1d0cff9cd45cf918cba0dd6e360ba99d385f1c8619d1207"},"schema_version":"1.0"},"canonical_sha256":"f62a8302956dc20f915109e9b3fc7529677c5296eada7c12b57ce215513f877b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:18:11.709403Z","signature_b64":"rGSnYwjIAZmrUgb2rNc4hlDkv4Cx0bVKwVaWa5qJtv1+mylgtyYif3HEqy9XMAEWmO4NM7TDTJqptM6UcGJfCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f62a8302956dc20f915109e9b3fc7529677c5296eada7c12b57ce215513f877b","last_reissued_at":"2026-07-07T02:18:11.708746Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:18:11.708746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.03870","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":"2026-07-07T02:18:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dq08vstW/U6fDXJtkAQhVo8NXsNASbS0XtIY1FsAkHF73nIRlz9DEXZRMN7GGb8NhDDf/DTUcY24ciNEJmOWDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:58:54.694440Z"},"content_sha256":"f62bc22f88158ddcd518fb2d92b8c4cbf691210909b3681882297e600a819d0a","schema_version":"1.0","event_id":"sha256:f62bc22f88158ddcd518fb2d92b8c4cbf691210909b3681882297e600a819d0a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6YVIGAUVNXBA7EKRBHU3H7DVFF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating LLM Uncertainty in Long-Form Generation Using Deterministic Ground Truth","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Ido Amit, Ido Galil, Ran El-Yaniv","submitted_at":"2026-07-04T13:25:18Z","abstract_excerpt":"As LLMs generate increasingly long outputs, effective uncertainty estimation must identify errors at fine-grained levels rather than discard entire responses. While such methods exist, evaluating uncertainty at any resolution (token to an entire generation) is challenging and highly sensitive to label imperfections, making zero-noise benchmarks essential; yet, long-form generation benchmarks tend to rely on fallible labels rather than deterministic ground truth. We introduce Single-answer Atomic Long-form Target (SALT), a benchmark of six procedurally generated tasks with single deterministic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03870","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/2607.03870/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":"2026-07-07T02:18:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B66+6REQRCY1e/Ck4jVBa1MYiRTHnFj2i7L/UWyx+4f5BOIkjfAnsuvNdQj4VylIz4UL0plRqq8SGQfn+M/pDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:58:54.695767Z"},"content_sha256":"cd626d95d4031b0fd3b3f19d660c5538f7a88480296b10909a9bb6da4997f225","schema_version":"1.0","event_id":"sha256:cd626d95d4031b0fd3b3f19d660c5538f7a88480296b10909a9bb6da4997f225"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:6YVIGAUVNXBA7EKRBHU3H7DVFF","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1162/tacl_a_00737.Wang) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"URL https://api.semanticscholar. org/CorpusID:235899031. Vashurin, R., Fadeeva, E., Vazhentsev, A., Rvanova, L., Vasilev, D., Tsvigun, A., Petrakov, S., Xing, R., Sadal- lah, A. B., Grishchenkov, K., Panchenko, A., Baldwin, T., Nakov, P., P","arxiv_id":"2607.03870","detector":"doi_compliance","evidence":{"ref_index":15,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"URL https://api.semanticscholar. org/CorpusID:235899031. Vashurin, R., Fadeeva, E., Vazhentsev, A., Rvanova, L., Vasilev, D., Tsvigun, A., Petrakov, S., Xing, R., Sadal- lah, A. B., Grishchenkov, K., Panchenko, A., Baldwin, T., Nakov, P., P","reconstructed_doi":"10.1162/tacl_a_00737.Wang"},"severity":"advisory","ref_index":15,"audited_at":"2026-07-11T23:27:07.585795Z","event_type":"pith.integrity.v1","detected_doi":"10.1162/tacl_a_00737.Wang","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"5cbdcec7e80150d9a90362ed1476c7c76e925851a9506759b02fdce2c708eaa5","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":12343,"payload_sha256":"fd272e88f3cf06c38ede61bfe46f37c3b9a4ebd0d2452e5b98928634cf4c82e9","signature_b64":"+7yrUmsLdm2FbHw7dYhB56FZCql01oT0M45qNQ/W5ITnQ3rhE80dTJfV5jMFEsu/8acqTShuepRC5Brpovn0Dw==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-11T23:31:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wcwt0pP+8+waYeEsNNaYsRY6ypabFp7L39tXEP76JPyMBi5QzqrQDW6tQ4KnzHeUMHP3uDZxwr4ulTP9ro4zAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:58:54.702678Z"},"content_sha256":"8ed4dc3b02b92b6712dc6f778b9c8863477d89127e6e366be5084ce2f7319ac4","schema_version":"1.0","event_id":"sha256:8ed4dc3b02b92b6712dc6f778b9c8863477d89127e6e366be5084ce2f7319ac4"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:6YVIGAUVNXBA7EKRBHU3H7DVFF","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.18653/V1/2023.EMNLP-MAIN.557.URL) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"URL https://openreview.net/forum? id=jN5y-zb5Q7m. Manakul, P., Liusie, A., and Gales, M. J. F. Selfcheck- gpt: Zero-resource black-box hallucination detection for generative large language models. In Bouamor, H., Pino, J., and Bali, K. (eds","arxiv_id":"2607.03870","detector":"doi_compliance","evidence":{"ref_index":13,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"URL https://openreview.net/forum? id=jN5y-zb5Q7m. Manakul, P., Liusie, A., and Gales, M. J. F. Selfcheck- gpt: Zero-resource black-box hallucination detection for generative large language models. In Bouamor, H., Pino, J., and Bali, K. (eds","reconstructed_doi":"10.18653/V1/2023.EMNLP-MAIN.557.URL"},"severity":"advisory","ref_index":13,"audited_at":"2026-07-11T23:27:07.585795Z","event_type":"pith.integrity.v1","detected_doi":"10.18653/V1/2023.EMNLP-MAIN.557.URL","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"a4885f57ec492593de47855db5842977f5d59ea780ac5924148b7f2daf53af6a","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":12342,"payload_sha256":"8c643830214e1210d516dc75c5819d533f3b7ef3e3fa6ced9c475d722d227b6d","signature_b64":"Nwb+l6wkitMHzMCNJ5w/he4BhTneC/iZwqTnR5e25q6IlKF8x49jVfyCKIWhFspkQAZfm1vSD+dStnIP4kjiDw==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-11T23:31:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y/rYwJrx915LJ5LzHcEFn3NHD+4m5b0lDj9oh10LeZwj5dH4TbOpgweHytI+FKEGdLS576vzcTtLirAv0bsaDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:58:54.703244Z"},"content_sha256":"838d8f8474c29b55dd3b7078c037b1ba05616df28e26ad62d6d1df0af394e878","schema_version":"1.0","event_id":"sha256:838d8f8474c29b55dd3b7078c037b1ba05616df28e26ad62d6d1df0af394e878"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:6YVIGAUVNXBA7EKRBHU3H7DVFF","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1109/TEC.1957.5222035.URL) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"URL https://api.semanticscholar. org/CorpusID:85528548. Chow, C. K. An optimum character recognition system using decision functions.IRE Trans. Electron. Com- put., 6(4):247–254, 1957. doi: 10.1109/TEC.1957. 5222035. URL https://doi.org/10.","arxiv_id":"2607.03870","detector":"doi_compliance","evidence":{"ref_index":5,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"URL https://api.semanticscholar. org/CorpusID:85528548. Chow, C. K. An optimum character recognition system using decision functions.IRE Trans. Electron. Com- put., 6(4):247–254, 1957. doi: 10.1109/TEC.1957. 5222035. URL https://doi.org/10.","reconstructed_doi":"10.1109/TEC.1957.5222035.URL"},"severity":"advisory","ref_index":5,"audited_at":"2026-07-11T23:27:07.585795Z","event_type":"pith.integrity.v1","detected_doi":"10.1109/TEC.1957.5222035.URL","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"c83056632cbd05eb77e6bcf4de62726d6b0fdb6d72dd3feee024b100409eb8b5","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":12341,"payload_sha256":"50910eb2fdf6114a92a968a8089fdeeaf6ec7325ae2868ea03755df8ba719279","signature_b64":"zm57CVHPDq3ohtR77DYRa8Ayu4/+s9E2l2LV5hnAUuM4xTyI2OEYrXcjRO/v8noy9Il1YWZy+BzCQRjMHlOQAw==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-11T23:31:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bPx9CR6vFKOzew3tr/go89HBrqOhNa65Q73YoInHwrSFlpMS69+MWqfRvEZTFA+W0ShYagP2Q3y29cZz2wfoAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:58:54.703866Z"},"content_sha256":"80186a53550272b7cdf84c36b54f9a5cea9fce857b68464368cf7395b46e538b","schema_version":"1.0","event_id":"sha256:80186a53550272b7cdf84c36b54f9a5cea9fce857b68464368cf7395b46e538b"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:6YVIGAUVNXBA7EKRBHU3H7DVFF","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1609/aaai.v34i05.6239.Bl¨obaum) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"URL https://doi.org/10.1609/aaai. v34i05.6239. Bl¨obaum, P., G ¨otz, P., Budhathoki, K., Mastakouri, A. A., and Janzing, D. Dowhy-gcm: An extension of dowhy for causal inference in graphical causal mod- els.Journal of Machine Learning Resea","arxiv_id":"2607.03870","detector":"doi_compliance","evidence":{"ref_index":3,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"URL https://doi.org/10.1609/aaai. v34i05.6239. Bl¨obaum, P., G ¨otz, P., Budhathoki, K., Mastakouri, A. A., and Janzing, D. Dowhy-gcm: An extension of dowhy for causal inference in graphical causal mod- els.Journal of Machine Learning Resea","reconstructed_doi":"10.1609/aaai.v34i05.6239.Bl¨obaum"},"severity":"advisory","ref_index":3,"audited_at":"2026-07-11T23:27:07.585795Z","event_type":"pith.integrity.v1","detected_doi":"10.1609/aaai.v34i05.6239.Bl¨obaum","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"1de3f1cb1fd943b519862da905707fa5cebec559b02f5452d1d2710558de7cfa","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":12340,"payload_sha256":"e9940d990d7cf332031b852002265174a51c64d31e26216bc5bc5b54c1d454cc","signature_b64":"qsdRG+VgHG6U9u6tGBnvmgHgZlcgt57jopJ97uCeK4jxZ4QmTRUnPw8Y+Y3iuc4Fm3/XLCk+hyDUl3emjh+8BA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-11T23:31:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/3RZ4z5V2lyU2VlnK18gyagH1h33oI8i6j94QPaAu8V1Brq670bNG5iRx1iDqDHmROon/vHjg9LketLs+kAlCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:58:54.704582Z"},"content_sha256":"b22789824ed9b0ee552594bc0b7f1d99a154cba6d7285d7ef9fb3bb84d011d67","schema_version":"1.0","event_id":"sha256:b22789824ed9b0ee552594bc0b7f1d99a154cba6d7285d7ef9fb3bb84d011d67"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:6YVIGAUVNXBA7EKRBHU3H7DVFF","target":"integrity","payload":{"note":"Identifier '10.1609/aaai.v34i05' is syntactically valid but the DOI registry (doi.org) returned 404, and Crossref / OpenAlex / internal corpus also have no record. The cited work could not be located through any authoritative source.","snippet":"AAAI Press, 2020. doi: 10.1609/AAAI.V34I05","arxiv_id":"2607.03870","detector":"doi_compliance","evidence":{"doi":"10.1609/aaai.v34i05","arxiv_id":null,"ref_index":2,"raw_excerpt":"AAAI Press, 2020. doi: 10.1609/AAAI.V34I05","verdict_class":"cross_source","checked_sources":["crossref_by_doi","openalex_by_doi","doi_org_head"]},"severity":"critical","ref_index":2,"audited_at":"2026-07-11T23:27:07.585795Z","event_type":"pith.integrity.v1","detected_doi":"10.1609/aaai.v34i05","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"unresolvable_identifier","evidence_hash":"fac4cf58b20c1db22eef41b459dc0ac15a8efbdd34cd8a01211dba6f164445b9","paper_version":1,"verdict_class":"cross_source","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":12339,"payload_sha256":"3b2cdbc38677816f448623eb952f607e01f6becab44e4cd98cfce3b2083a16c8","signature_b64":"LseFYRr9TD5jMklZabdzyVIjj5t5s9F/Znwm+dWuKYSTzoQqidRoAtwD1zXAQQl/NJC6x2TWmGba9S+bMP6rDg==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-11T23:31:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rGYX2qSJalsXZI25jTMr2YeSur4gKhL0ZMTPyoImrmdVwqsvYJFVt8vmMgN2XBtisMEgw9FiNDQsTwfpu8OrDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:58:54.705198Z"},"content_sha256":"d8b485c835a4784684d4b52de33ee0d58e8044cb8236874909ac7ff165f5a371","schema_version":"1.0","event_id":"sha256:d8b485c835a4784684d4b52de33ee0d58e8044cb8236874909ac7ff165f5a371"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6YVIGAUVNXBA7EKRBHU3H7DVFF/bundle.json","state_url":"https://pith.science/pith/6YVIGAUVNXBA7EKRBHU3H7DVFF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6YVIGAUVNXBA7EKRBHU3H7DVFF/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":"2026-08-10T10:58:54Z","links":{"resolver":"https://pith.science/pith/6YVIGAUVNXBA7EKRBHU3H7DVFF","bundle":"https://pith.science/pith/6YVIGAUVNXBA7EKRBHU3H7DVFF/bundle.json","state":"https://pith.science/pith/6YVIGAUVNXBA7EKRBHU3H7DVFF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6YVIGAUVNXBA7EKRBHU3H7DVFF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6YVIGAUVNXBA7EKRBHU3H7DVFF","merge_version":"pith-open-graph-merge-v1","event_count":7,"valid_event_count":7,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"cd34c06d9952751cc1d0cff9cd45cf918cba0dd6e360ba99d385f1c8619d1207","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-04T13:25:18Z","title_canon_sha256":"6985b0e94b939078478b955fd5752ad71f1b63d78ac195e9f27711b9ae7e6581"},"schema_version":"1.0","source":{"id":"2607.03870","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.03870","created_at":"2026-07-07T02:18:11Z"},{"alias_kind":"arxiv_version","alias_value":"2607.03870v1","created_at":"2026-07-07T02:18:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03870","created_at":"2026-07-07T02:18:11Z"},{"alias_kind":"pith_short_12","alias_value":"6YVIGAUVNXBA","created_at":"2026-07-07T02:18:11Z"},{"alias_kind":"pith_short_16","alias_value":"6YVIGAUVNXBA7EKR","created_at":"2026-07-07T02:18:11Z"},{"alias_kind":"pith_short_8","alias_value":"6YVIGAUV","created_at":"2026-07-07T02:18:11Z"}],"graph_snapshots":[{"event_id":"sha256:cd626d95d4031b0fd3b3f19d660c5538f7a88480296b10909a9bb6da4997f225","target":"graph","created_at":"2026-07-07T02:18:11Z","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/2607.03870/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As LLMs generate increasingly long outputs, effective uncertainty estimation must identify errors at fine-grained levels rather than discard entire responses. While such methods exist, evaluating uncertainty at any resolution (token to an entire generation) is challenging and highly sensitive to label imperfections, making zero-noise benchmarks essential; yet, long-form generation benchmarks tend to rely on fallible labels rather than deterministic ground truth. We introduce Single-answer Atomic Long-form Target (SALT), a benchmark of six procedurally generated tasks with single deterministic ","authors_text":"Ido Amit, Ido Galil, Ran El-Yaniv","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-04T13:25:18Z","title":"Evaluating LLM Uncertainty in Long-Form Generation Using Deterministic Ground Truth"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03870","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:f62bc22f88158ddcd518fb2d92b8c4cbf691210909b3681882297e600a819d0a","target":"record","created_at":"2026-07-07T02:18:11Z","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":"cd34c06d9952751cc1d0cff9cd45cf918cba0dd6e360ba99d385f1c8619d1207","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-04T13:25:18Z","title_canon_sha256":"6985b0e94b939078478b955fd5752ad71f1b63d78ac195e9f27711b9ae7e6581"},"schema_version":"1.0","source":{"id":"2607.03870","kind":"arxiv","version":1}},"canonical_sha256":"f62a8302956dc20f915109e9b3fc7529677c5296eada7c12b57ce215513f877b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f62a8302956dc20f915109e9b3fc7529677c5296eada7c12b57ce215513f877b","first_computed_at":"2026-07-07T02:18:11.708746Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:18:11.708746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rGSnYwjIAZmrUgb2rNc4hlDkv4Cx0bVKwVaWa5qJtv1+mylgtyYif3HEqy9XMAEWmO4NM7TDTJqptM6UcGJfCg==","signature_status":"signed_v1","signed_at":"2026-07-07T02:18:11.709403Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.03870","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:80186a53550272b7cdf84c36b54f9a5cea9fce857b68464368cf7395b46e538b","sha256:838d8f8474c29b55dd3b7078c037b1ba05616df28e26ad62d6d1df0af394e878","sha256:8ed4dc3b02b92b6712dc6f778b9c8863477d89127e6e366be5084ce2f7319ac4","sha256:b22789824ed9b0ee552594bc0b7f1d99a154cba6d7285d7ef9fb3bb84d011d67","sha256:d8b485c835a4784684d4b52de33ee0d58e8044cb8236874909ac7ff165f5a371"]}],"invalid_events":[],"applied_event_ids":["sha256:f62bc22f88158ddcd518fb2d92b8c4cbf691210909b3681882297e600a819d0a","sha256:cd626d95d4031b0fd3b3f19d660c5538f7a88480296b10909a9bb6da4997f225"],"state_sha256":"cc2575257fc7a20f3f2dd004a913aa0be6c5a1a2e95b2cd2f265617b14d680a8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JsvIczkfUqDwLu6lluWNhNYf9p8SuKhysXi6AjzAbTKmV1PbuwKaw/H8J9pxj8IScbQHd4nLBdi4BGZUKHATCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T10:58:54.710423Z","bundle_sha256":"c7f756dabecba2bc37170be73f105c67b001b34a809a208771166cd3b8f6a334"}}