{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6PATNCQZCHQ6OJI33H2LKXGZOS","short_pith_number":"pith:6PATNCQZ","canonical_record":{"source":{"id":"2601.21463","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-01-29T09:39:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b894be1e20f9458f07b5150de3e1fdf599ffe125ef2f27f64edad3fe52c789b2","abstract_canon_sha256":"5af8683e7ca58e77d82192569bac84d26da273c8b0fcdf206a3a5dda6ff6eebd"},"schema_version":"1.0"},"canonical_sha256":"f3c1368a1911e1e7251bd9f4b55cd974b6bf184126a2b23260df221e6b53f4a4","source":{"kind":"arxiv","id":"2601.21463","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.21463","created_at":"2026-05-26T01:03:23Z"},{"alias_kind":"arxiv_version","alias_value":"2601.21463v3","created_at":"2026-05-26T01:03:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21463","created_at":"2026-05-26T01:03:23Z"},{"alias_kind":"pith_short_12","alias_value":"6PATNCQZCHQ6","created_at":"2026-05-26T01:03:23Z"},{"alias_kind":"pith_short_16","alias_value":"6PATNCQZCHQ6OJI3","created_at":"2026-05-26T01:03:23Z"},{"alias_kind":"pith_short_8","alias_value":"6PATNCQZ","created_at":"2026-05-26T01:03:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6PATNCQZCHQ6OJI33H2LKXGZOS","target":"record","payload":{"canonical_record":{"source":{"id":"2601.21463","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-01-29T09:39:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b894be1e20f9458f07b5150de3e1fdf599ffe125ef2f27f64edad3fe52c789b2","abstract_canon_sha256":"5af8683e7ca58e77d82192569bac84d26da273c8b0fcdf206a3a5dda6ff6eebd"},"schema_version":"1.0"},"canonical_sha256":"f3c1368a1911e1e7251bd9f4b55cd974b6bf184126a2b23260df221e6b53f4a4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:23.488729Z","signature_b64":"sb2Efv1LLt4YDDyqZgBqrFNOj8jFVmeaAhJTc4pAttJXmL20rdMvPz9LxJhucsE7aqYA7dXLwKQxwSR6DBz7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3c1368a1911e1e7251bd9f4b55cd974b6bf184126a2b23260df221e6b53f4a4","last_reissued_at":"2026-05-26T01:03:23.487775Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:23.487775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.21463","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T01:03:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gUZKRmDcCBfY/OmBw5nwuW2eagty7bOWm/kF86GrJmQcgq9vB+MXmNJng3OkAryRDlGbGWxcrXjqroiA3e9pAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T18:02:36.476677Z"},"content_sha256":"7bc15f1d70a9beb47faddad59f941b0f33dc98e59d4c0fee94d05e279abc3e75","schema_version":"1.0","event_id":"sha256:7bc15f1d70a9beb47faddad59f941b0f33dc98e59d4c0fee94d05e279abc3e75"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6PATNCQZCHQ6OJI33H2LKXGZOS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unifying Speech Editing Detection and Content Localization via Prior-Enhanced Audio LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Audio LLMs reformulated as text generators detect speech edits and localize their content on a new realistic dataset.","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Jinshen He, Jun Xue, Yanzhen Ren, Yi Chai, Yihuan Huang, Yuankun Xie, Yujie Chen, Zhiqiang Tang, Zhuolin Yi","submitted_at":"2026-01-29T09:39:28Z","abstract_excerpt":"Existing speech editing detection (SED) datasets are predominantly constructed using manual splicing or limited editing operations, resulting in restricted diversity and poor coverage of realistic editing scenarios. Meanwhile, current SED methods rely heavily on frame-level supervision to detect observable acoustic anomalies, which fundamentally limits their ability to handle deletion-type edits, where the manipulated content is entirely absent from the signal. To address these challenges, we present a unified framework that bridges speech editing detection and content localization through a g"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experimental results demonstrate that the proposed approach consistently outperforms existing methods across both detection and localization tasks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the AiEdit dataset constructed with state-of-the-art end-to-end speech editing systems provides realistic coverage of modern editing threats and that the prior-enhanced prompting strategy successfully grounds the generative model in acoustic evidence.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"The paper introduces the AiEdit dataset of 140 hours of realistic speech edits and a prior-enhanced Audio LLM framework that unifies detection and localization via text generation and an acoustic consistency loss.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Audio LLMs reformulated as text generators detect speech edits and localize their content on a new realistic dataset.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9f7a656f484f336dd34ddd54f29ebf3ff0bfaa14deb151a1c09e1d2dfb456dc6"},"source":{"id":"2601.21463","kind":"arxiv","version":3},"verdict":{"id":"fe66a404-e947-4cb3-9370-efbd7d927628","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T09:58:55.142736Z","strongest_claim":"Experimental results demonstrate that the proposed approach consistently outperforms existing methods across both detection and localization tasks.","one_line_summary":"The paper introduces the AiEdit dataset of 140 hours of realistic speech edits and a prior-enhanced Audio LLM framework that unifies detection and localization via text generation and an acoustic consistency loss.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the AiEdit dataset constructed with state-of-the-art end-to-end speech editing systems provides realistic coverage of modern editing threats and that the prior-enhanced prompting strategy successfully grounds the generative model in acoustic evidence.","pith_extraction_headline":"Audio LLMs reformulated as text generators detect speech edits and localize their content on a new realistic dataset."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2601.21463/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":"fe66a404-e947-4cb3-9370-efbd7d927628"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T01:03:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Le2YAF4k3AT3CIbNSq7v6mDjEINArXgvuFyJ732Zuwg5/5DvTUG9a9uKwu2wLq8v8v/7Cs8DN53UCiiWcb28AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T18:02:36.477194Z"},"content_sha256":"03959a2b09dedb58a3fafe89c5f9a496075ad265d321eefa0d6def9a3f0b6772","schema_version":"1.0","event_id":"sha256:03959a2b09dedb58a3fafe89c5f9a496075ad265d321eefa0d6def9a3f0b6772"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6PATNCQZCHQ6OJI33H2LKXGZOS/bundle.json","state_url":"https://pith.science/pith/6PATNCQZCHQ6OJI33H2LKXGZOS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6PATNCQZCHQ6OJI33H2LKXGZOS/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":"2026-06-06T18:02:36Z","links":{"resolver":"https://pith.science/pith/6PATNCQZCHQ6OJI33H2LKXGZOS","bundle":"https://pith.science/pith/6PATNCQZCHQ6OJI33H2LKXGZOS/bundle.json","state":"https://pith.science/pith/6PATNCQZCHQ6OJI33H2LKXGZOS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6PATNCQZCHQ6OJI33H2LKXGZOS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6PATNCQZCHQ6OJI33H2LKXGZOS","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":"5af8683e7ca58e77d82192569bac84d26da273c8b0fcdf206a3a5dda6ff6eebd","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-01-29T09:39:28Z","title_canon_sha256":"b894be1e20f9458f07b5150de3e1fdf599ffe125ef2f27f64edad3fe52c789b2"},"schema_version":"1.0","source":{"id":"2601.21463","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.21463","created_at":"2026-05-26T01:03:23Z"},{"alias_kind":"arxiv_version","alias_value":"2601.21463v3","created_at":"2026-05-26T01:03:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21463","created_at":"2026-05-26T01:03:23Z"},{"alias_kind":"pith_short_12","alias_value":"6PATNCQZCHQ6","created_at":"2026-05-26T01:03:23Z"},{"alias_kind":"pith_short_16","alias_value":"6PATNCQZCHQ6OJI3","created_at":"2026-05-26T01:03:23Z"},{"alias_kind":"pith_short_8","alias_value":"6PATNCQZ","created_at":"2026-05-26T01:03:23Z"}],"graph_snapshots":[{"event_id":"sha256:03959a2b09dedb58a3fafe89c5f9a496075ad265d321eefa0d6def9a3f0b6772","target":"graph","created_at":"2026-05-26T01:03:23Z","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":"Experimental results demonstrate that the proposed approach consistently outperforms existing methods across both detection and localization tasks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the AiEdit dataset constructed with state-of-the-art end-to-end speech editing systems provides realistic coverage of modern editing threats and that the prior-enhanced prompting strategy successfully grounds the generative model in acoustic evidence."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"The paper introduces the AiEdit dataset of 140 hours of realistic speech edits and a prior-enhanced Audio LLM framework that unifies detection and localization via text generation and an acoustic consistency loss."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Audio LLMs reformulated as text generators detect speech edits and localize their content on a new realistic dataset."}],"snapshot_sha256":"9f7a656f484f336dd34ddd54f29ebf3ff0bfaa14deb151a1c09e1d2dfb456dc6"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2601.21463/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing speech editing detection (SED) datasets are predominantly constructed using manual splicing or limited editing operations, resulting in restricted diversity and poor coverage of realistic editing scenarios. Meanwhile, current SED methods rely heavily on frame-level supervision to detect observable acoustic anomalies, which fundamentally limits their ability to handle deletion-type edits, where the manipulated content is entirely absent from the signal. To address these challenges, we present a unified framework that bridges speech editing detection and content localization through a g","authors_text":"Jinshen He, Jun Xue, Yanzhen Ren, Yi Chai, Yihuan Huang, Yuankun Xie, Yujie Chen, Zhiqiang Tang, Zhuolin Yi","cross_cats":["cs.AI"],"headline":"Audio LLMs reformulated as text generators detect speech edits and localize their content on a new realistic dataset.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-01-29T09:39:28Z","title":"Unifying Speech Editing Detection and Content Localization via Prior-Enhanced Audio LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21463","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T09:58:55.142736Z","id":"fe66a404-e947-4cb3-9370-efbd7d927628","model_set":{"reader":"grok-4.3"},"one_line_summary":"The paper introduces the AiEdit dataset of 140 hours of realistic speech edits and a prior-enhanced Audio LLM framework that unifies detection and localization via text generation and an acoustic consistency loss.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Audio LLMs reformulated as text generators detect speech edits and localize their content on a new realistic dataset.","strongest_claim":"Experimental results demonstrate that the proposed approach consistently outperforms existing methods across both detection and localization tasks.","weakest_assumption":"That the AiEdit dataset constructed with state-of-the-art end-to-end speech editing systems provides realistic coverage of modern editing threats and that the prior-enhanced prompting strategy successfully grounds the generative model in acoustic evidence."}},"verdict_id":"fe66a404-e947-4cb3-9370-efbd7d927628"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7bc15f1d70a9beb47faddad59f941b0f33dc98e59d4c0fee94d05e279abc3e75","target":"record","created_at":"2026-05-26T01:03:23Z","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":"5af8683e7ca58e77d82192569bac84d26da273c8b0fcdf206a3a5dda6ff6eebd","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-01-29T09:39:28Z","title_canon_sha256":"b894be1e20f9458f07b5150de3e1fdf599ffe125ef2f27f64edad3fe52c789b2"},"schema_version":"1.0","source":{"id":"2601.21463","kind":"arxiv","version":3}},"canonical_sha256":"f3c1368a1911e1e7251bd9f4b55cd974b6bf184126a2b23260df221e6b53f4a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3c1368a1911e1e7251bd9f4b55cd974b6bf184126a2b23260df221e6b53f4a4","first_computed_at":"2026-05-26T01:03:23.487775Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:23.487775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sb2Efv1LLt4YDDyqZgBqrFNOj8jFVmeaAhJTc4pAttJXmL20rdMvPz9LxJhucsE7aqYA7dXLwKQxwSR6DBz7BA==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:23.488729Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.21463","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7bc15f1d70a9beb47faddad59f941b0f33dc98e59d4c0fee94d05e279abc3e75","sha256:03959a2b09dedb58a3fafe89c5f9a496075ad265d321eefa0d6def9a3f0b6772"],"state_sha256":"f8d28d4e5579aa5ac64b34c72918f17fb130da3d29072a09d18c5adb5554cbd3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1uVV5BggBGtXtCAOiPkDWNj6akdMB8UQv3axylhjeA7nrJFFdpUqIDwDaSz0XgUCeYF4dS5Aubr+6y09S/msDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T18:02:36.480192Z","bundle_sha256":"f6bc8d1130f2ff945f6773e5d5176d7e9426677cc77b36a89fc6c2e2cd0f8e24"}}