{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:24UUIQ3B76RW5E65Q5CCW57G2R","short_pith_number":"pith:24UUIQ3B","canonical_record":{"source":{"id":"2605.28227","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T09:41:22Z","cross_cats_sorted":[],"title_canon_sha256":"63f8bdf39a55165b2f3b383530835c83716fa5be513276ad3d0670dc45adb809","abstract_canon_sha256":"67c15c69356901bf91a2ce9cb83985569e2db4b96230afde8430cb80ebaef92e"},"schema_version":"1.0"},"canonical_sha256":"d729444361ffa36e93dd87442b77e6d4430b63a08472435baf229847b445b48e","source":{"kind":"arxiv","id":"2605.28227","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28227","created_at":"2026-05-28T01:05:03Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28227v1","created_at":"2026-05-28T01:05:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28227","created_at":"2026-05-28T01:05:03Z"},{"alias_kind":"pith_short_12","alias_value":"24UUIQ3B76RW","created_at":"2026-05-28T01:05:03Z"},{"alias_kind":"pith_short_16","alias_value":"24UUIQ3B76RW5E65","created_at":"2026-05-28T01:05:03Z"},{"alias_kind":"pith_short_8","alias_value":"24UUIQ3B","created_at":"2026-05-28T01:05:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:24UUIQ3B76RW5E65Q5CCW57G2R","target":"record","payload":{"canonical_record":{"source":{"id":"2605.28227","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T09:41:22Z","cross_cats_sorted":[],"title_canon_sha256":"63f8bdf39a55165b2f3b383530835c83716fa5be513276ad3d0670dc45adb809","abstract_canon_sha256":"67c15c69356901bf91a2ce9cb83985569e2db4b96230afde8430cb80ebaef92e"},"schema_version":"1.0"},"canonical_sha256":"d729444361ffa36e93dd87442b77e6d4430b63a08472435baf229847b445b48e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:05:03.220282Z","signature_b64":"/tykXrmYUx7TZgt+PNpk7sB3iO8NBH0lZELCS3Zl5ih4aNUBHOMNWy0XK0gEYi3FROzBHNPXZYc9FAWzqjgjBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d729444361ffa36e93dd87442b77e6d4430b63a08472435baf229847b445b48e","last_reissued_at":"2026-05-28T01:05:03.219873Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:05:03.219873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.28227","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":"2026-05-28T01:05:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bc2C8+xa9YOAiHfHiSl7gE6frL6fzyXu9Hv2AYnzkO7Yu/OSwU1+TWI083MUKX2rNP48pdwaBrOec9WAp8d3Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T19:25:28.674701Z"},"content_sha256":"681ce86564fa925f23cb26aa26a8b32119eba2943d5bbc17aa23eae5171d69b2","schema_version":"1.0","event_id":"sha256:681ce86564fa925f23cb26aa26a8b32119eba2943d5bbc17aa23eae5171d69b2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:24UUIQ3B76RW5E65Q5CCW57G2R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Why We Need Speech to Evaluate Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Danni Liu, Jan Niehues, Maike Z\\\"ufle, Vil\\'em Zouhar","submitted_at":"2026-05-27T09:41:22Z","abstract_excerpt":"Speech translation models are increasingly capable of preserving speech-specific information (e.g., speaker gender, prosody, and emphasis), yet evaluation metrics remain blind to such phenomena. We meta-evaluate both text- and speech-based quality estimation metrics on two contrastive datasets targeting gender agreement and prosody, and find that both fall short, even when given direct access to the speech signal. We then train SpeechCOMET, a family of quality estimation models with speech encoders, and evaluate a state-of-the-art SpeechLLM as a judge. Both match or exceed text-based COMET on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28227","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/2605.28227/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":"2026-05-28T01:05:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TYZKZMQtfxlreXxk54tWoEmShbs1fXNyrpOVITBSljcuKz/xEMfLIv1jOKiSsf3oKqGGO8RF6addBHYDR521Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T19:25:28.675076Z"},"content_sha256":"e94feb82abaf7caf8534b229ac17cde63dc959b944a22d6e7f792a2e37195d06","schema_version":"1.0","event_id":"sha256:e94feb82abaf7caf8534b229ac17cde63dc959b944a22d6e7f792a2e37195d06"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/24UUIQ3B76RW5E65Q5CCW57G2R/bundle.json","state_url":"https://pith.science/pith/24UUIQ3B76RW5E65Q5CCW57G2R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/24UUIQ3B76RW5E65Q5CCW57G2R/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":"2026-07-03T19:25:28Z","links":{"resolver":"https://pith.science/pith/24UUIQ3B76RW5E65Q5CCW57G2R","bundle":"https://pith.science/pith/24UUIQ3B76RW5E65Q5CCW57G2R/bundle.json","state":"https://pith.science/pith/24UUIQ3B76RW5E65Q5CCW57G2R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/24UUIQ3B76RW5E65Q5CCW57G2R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:24UUIQ3B76RW5E65Q5CCW57G2R","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":"67c15c69356901bf91a2ce9cb83985569e2db4b96230afde8430cb80ebaef92e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T09:41:22Z","title_canon_sha256":"63f8bdf39a55165b2f3b383530835c83716fa5be513276ad3d0670dc45adb809"},"schema_version":"1.0","source":{"id":"2605.28227","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28227","created_at":"2026-05-28T01:05:03Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28227v1","created_at":"2026-05-28T01:05:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28227","created_at":"2026-05-28T01:05:03Z"},{"alias_kind":"pith_short_12","alias_value":"24UUIQ3B76RW","created_at":"2026-05-28T01:05:03Z"},{"alias_kind":"pith_short_16","alias_value":"24UUIQ3B76RW5E65","created_at":"2026-05-28T01:05:03Z"},{"alias_kind":"pith_short_8","alias_value":"24UUIQ3B","created_at":"2026-05-28T01:05:03Z"}],"graph_snapshots":[{"event_id":"sha256:e94feb82abaf7caf8534b229ac17cde63dc959b944a22d6e7f792a2e37195d06","target":"graph","created_at":"2026-05-28T01:05:03Z","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/2605.28227/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech translation models are increasingly capable of preserving speech-specific information (e.g., speaker gender, prosody, and emphasis), yet evaluation metrics remain blind to such phenomena. We meta-evaluate both text- and speech-based quality estimation metrics on two contrastive datasets targeting gender agreement and prosody, and find that both fall short, even when given direct access to the speech signal. We then train SpeechCOMET, a family of quality estimation models with speech encoders, and evaluate a state-of-the-art SpeechLLM as a judge. Both match or exceed text-based COMET on ","authors_text":"Danni Liu, Jan Niehues, Maike Z\\\"ufle, Vil\\'em Zouhar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T09:41:22Z","title":"Why We Need Speech to Evaluate Speech Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28227","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":"sha256:681ce86564fa925f23cb26aa26a8b32119eba2943d5bbc17aa23eae5171d69b2","target":"record","created_at":"2026-05-28T01:05:03Z","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":"67c15c69356901bf91a2ce9cb83985569e2db4b96230afde8430cb80ebaef92e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T09:41:22Z","title_canon_sha256":"63f8bdf39a55165b2f3b383530835c83716fa5be513276ad3d0670dc45adb809"},"schema_version":"1.0","source":{"id":"2605.28227","kind":"arxiv","version":1}},"canonical_sha256":"d729444361ffa36e93dd87442b77e6d4430b63a08472435baf229847b445b48e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d729444361ffa36e93dd87442b77e6d4430b63a08472435baf229847b445b48e","first_computed_at":"2026-05-28T01:05:03.219873Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:05:03.219873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/tykXrmYUx7TZgt+PNpk7sB3iO8NBH0lZELCS3Zl5ih4aNUBHOMNWy0XK0gEYi3FROzBHNPXZYc9FAWzqjgjBw==","signature_status":"signed_v1","signed_at":"2026-05-28T01:05:03.220282Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28227","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:681ce86564fa925f23cb26aa26a8b32119eba2943d5bbc17aa23eae5171d69b2","sha256:e94feb82abaf7caf8534b229ac17cde63dc959b944a22d6e7f792a2e37195d06"],"state_sha256":"30022ed94d3a6d141eb2771d6da3158be715504e6f511801cf3dab14dc9a996f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iztSrygCQnnSdeuEx2LC7FjB0CLq906Q0F1M/OCk1v97wug4BFlAEM+OFIwssAHbDvnCDWT7R3SW6BeSBAr3DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T19:25:28.677127Z","bundle_sha256":"144063ac72b5ec334263d8876d6495ef0ff09fd8b7c94634219495a1342c1b64"}}