{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:MH3RHCTSEXBBCOWANBVJY4V4M4","short_pith_number":"pith:MH3RHCTS","canonical_record":{"source":{"id":"2607.22661","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T00:47:48Z","cross_cats_sorted":[],"title_canon_sha256":"6efb836fdf157b98257fce61a6c109256169eb29ce56d0a605290e31ef32ed28","abstract_canon_sha256":"b2c945388143aac6de04db4a312f6843f7e6f7575d5358ef24944b98dec82b83"},"schema_version":"1.0"},"canonical_sha256":"61f7138a7225c2113ac0686a9c72bc670d69f4fe8ec995a917ea46b3fa4fffc6","source":{"kind":"arxiv","id":"2607.22661","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22661","created_at":"2026-07-28T00:21:47Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22661v1","created_at":"2026-07-28T00:21:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22661","created_at":"2026-07-28T00:21:47Z"},{"alias_kind":"pith_short_12","alias_value":"MH3RHCTSEXBB","created_at":"2026-07-28T00:21:47Z"},{"alias_kind":"pith_short_16","alias_value":"MH3RHCTSEXBBCOWA","created_at":"2026-07-28T00:21:47Z"},{"alias_kind":"pith_short_8","alias_value":"MH3RHCTS","created_at":"2026-07-28T00:21:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:MH3RHCTSEXBBCOWANBVJY4V4M4","target":"record","payload":{"canonical_record":{"source":{"id":"2607.22661","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T00:47:48Z","cross_cats_sorted":[],"title_canon_sha256":"6efb836fdf157b98257fce61a6c109256169eb29ce56d0a605290e31ef32ed28","abstract_canon_sha256":"b2c945388143aac6de04db4a312f6843f7e6f7575d5358ef24944b98dec82b83"},"schema_version":"1.0"},"canonical_sha256":"61f7138a7225c2113ac0686a9c72bc670d69f4fe8ec995a917ea46b3fa4fffc6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T00:21:47.717821Z","signature_b64":"6WLYaR6TxXoj3WH4JuEq8ymXXgj6NxvRLfpmHQM8JevVK6aXvLzzZ6/oZxv7C4YLhAJ1Oa2CFVyTtdtOp1AkBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61f7138a7225c2113ac0686a9c72bc670d69f4fe8ec995a917ea46b3fa4fffc6","last_reissued_at":"2026-07-28T00:21:47.716990Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T00:21:47.716990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.22661","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":"2026-07-28T00:21:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bYVgEgFoqJvyM3esXPxBxmB/aGJgxgF3lISphWlcKvPR/0CMlXym4dywODGkSI2f+iuX2Rmj8xFqUCJi70wuCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:57:28.228590Z"},"content_sha256":"4908caa970abbe39679c46cbe04488ba9313da3b36cffaa98f210d264a605550","schema_version":"1.0","event_id":"sha256:4908caa970abbe39679c46cbe04488ba9313da3b36cffaa98f210d264a605550"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:MH3RHCTSEXBBCOWANBVJY4V4M4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TRE: Training-Free Hallucination Detection for Diffusion Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Pengcheng Weng, Yanyu Qian, Yixin Liu, Yue Tan","submitted_at":"2026-06-29T00:47:48Z","abstract_excerpt":"Diffusion large language models (D-LLMs) have recently gained increasing attention, yet their reliability is significantly hindered by the hallucination problem. Existing hallucination detection approaches for D-LLMs mainly follow a training-based paradigm, relying on data-driven training to optimize the detector. Such reliance not only limits their generalizability across domains models but also incurs additional training cost and deployment overhead. To address these limitations, we propose TRE, a training-free hallucination detection metric for D-LLMs. TRE is a parameter-free and single-run"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22661","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/2607.22661/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":"2026-07-28T00:21:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kBJtn+kZZ8r9jVx/7F+FSxNY/yuRRocdrj6ofCCUKj97ttEbEYAtWlPgHWJTdZgI/AjBVN1g7byrELaHu1tkDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:57:28.229064Z"},"content_sha256":"03215f09c1751b803baf3360f79540e3be8bc981d426729966ff9300e8c0e466","schema_version":"1.0","event_id":"sha256:03215f09c1751b803baf3360f79540e3be8bc981d426729966ff9300e8c0e466"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MH3RHCTSEXBBCOWANBVJY4V4M4/bundle.json","state_url":"https://pith.science/pith/MH3RHCTSEXBBCOWANBVJY4V4M4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MH3RHCTSEXBBCOWANBVJY4V4M4/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":"2026-08-04T03:57:28Z","links":{"resolver":"https://pith.science/pith/MH3RHCTSEXBBCOWANBVJY4V4M4","bundle":"https://pith.science/pith/MH3RHCTSEXBBCOWANBVJY4V4M4/bundle.json","state":"https://pith.science/pith/MH3RHCTSEXBBCOWANBVJY4V4M4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MH3RHCTSEXBBCOWANBVJY4V4M4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MH3RHCTSEXBBCOWANBVJY4V4M4","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":"b2c945388143aac6de04db4a312f6843f7e6f7575d5358ef24944b98dec82b83","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T00:47:48Z","title_canon_sha256":"6efb836fdf157b98257fce61a6c109256169eb29ce56d0a605290e31ef32ed28"},"schema_version":"1.0","source":{"id":"2607.22661","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22661","created_at":"2026-07-28T00:21:47Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22661v1","created_at":"2026-07-28T00:21:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22661","created_at":"2026-07-28T00:21:47Z"},{"alias_kind":"pith_short_12","alias_value":"MH3RHCTSEXBB","created_at":"2026-07-28T00:21:47Z"},{"alias_kind":"pith_short_16","alias_value":"MH3RHCTSEXBBCOWA","created_at":"2026-07-28T00:21:47Z"},{"alias_kind":"pith_short_8","alias_value":"MH3RHCTS","created_at":"2026-07-28T00:21:47Z"}],"graph_snapshots":[{"event_id":"sha256:03215f09c1751b803baf3360f79540e3be8bc981d426729966ff9300e8c0e466","target":"graph","created_at":"2026-07-28T00:21:47Z","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/2607.22661/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion large language models (D-LLMs) have recently gained increasing attention, yet their reliability is significantly hindered by the hallucination problem. Existing hallucination detection approaches for D-LLMs mainly follow a training-based paradigm, relying on data-driven training to optimize the detector. Such reliance not only limits their generalizability across domains models but also incurs additional training cost and deployment overhead. To address these limitations, we propose TRE, a training-free hallucination detection metric for D-LLMs. TRE is a parameter-free and single-run","authors_text":"Pengcheng Weng, Yanyu Qian, Yixin Liu, Yue Tan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T00:47:48Z","title":"TRE: Training-Free Hallucination Detection for Diffusion Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22661","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":"sha256:4908caa970abbe39679c46cbe04488ba9313da3b36cffaa98f210d264a605550","target":"record","created_at":"2026-07-28T00:21:47Z","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":"b2c945388143aac6de04db4a312f6843f7e6f7575d5358ef24944b98dec82b83","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T00:47:48Z","title_canon_sha256":"6efb836fdf157b98257fce61a6c109256169eb29ce56d0a605290e31ef32ed28"},"schema_version":"1.0","source":{"id":"2607.22661","kind":"arxiv","version":1}},"canonical_sha256":"61f7138a7225c2113ac0686a9c72bc670d69f4fe8ec995a917ea46b3fa4fffc6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61f7138a7225c2113ac0686a9c72bc670d69f4fe8ec995a917ea46b3fa4fffc6","first_computed_at":"2026-07-28T00:21:47.716990Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T00:21:47.716990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6WLYaR6TxXoj3WH4JuEq8ymXXgj6NxvRLfpmHQM8JevVK6aXvLzzZ6/oZxv7C4YLhAJ1Oa2CFVyTtdtOp1AkBg==","signature_status":"signed_v1","signed_at":"2026-07-28T00:21:47.717821Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.22661","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4908caa970abbe39679c46cbe04488ba9313da3b36cffaa98f210d264a605550","sha256:03215f09c1751b803baf3360f79540e3be8bc981d426729966ff9300e8c0e466"],"state_sha256":"94a2e889dbea7cf5509769c29581df81e13a2b113adb4b67d2a0e8628ebc57e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"43xze7Lmie92LudPkmoVWx252mBvw/oiC6f/T4mKUwACgnU05HDKXmlmF3QLnEXBOvK9AllCTWry89bIpvwBBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T03:57:28.233551Z","bundle_sha256":"be22262d0fc7ad7fee4fb6f4cd5bdbb2fd30356b202548c8d53f0a0144c5d806"}}