{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5N7GZGWKM6LNM2FUYZFPYPQTII","short_pith_number":"pith:5N7GZGWK","canonical_record":{"source":{"id":"2409.10788","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-16T23:51:42Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"5f4ec5c435ef02211a5c103c40ce84b85741efe41872075dc997ae8051420c65","abstract_canon_sha256":"2339a6b67fe179935934ed628e109766a1eb9ed113777e7dd359ad260361442a"},"schema_version":"1.0"},"canonical_sha256":"eb7e6c9aca6796d668b4c64afc3e13420b713204803906f7df98f359e2e961d2","source":{"kind":"arxiv","id":"2409.10788","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.10788","created_at":"2026-07-05T10:02:24Z"},{"alias_kind":"arxiv_version","alias_value":"2409.10788v2","created_at":"2026-07-05T10:02:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10788","created_at":"2026-07-05T10:02:24Z"},{"alias_kind":"pith_short_12","alias_value":"5N7GZGWKM6LN","created_at":"2026-07-05T10:02:24Z"},{"alias_kind":"pith_short_16","alias_value":"5N7GZGWKM6LNM2FU","created_at":"2026-07-05T10:02:24Z"},{"alias_kind":"pith_short_8","alias_value":"5N7GZGWK","created_at":"2026-07-05T10:02:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5N7GZGWKM6LNM2FUYZFPYPQTII","target":"record","payload":{"canonical_record":{"source":{"id":"2409.10788","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-16T23:51:42Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"5f4ec5c435ef02211a5c103c40ce84b85741efe41872075dc997ae8051420c65","abstract_canon_sha256":"2339a6b67fe179935934ed628e109766a1eb9ed113777e7dd359ad260361442a"},"schema_version":"1.0"},"canonical_sha256":"eb7e6c9aca6796d668b4c64afc3e13420b713204803906f7df98f359e2e961d2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:24.422383Z","signature_b64":"rtoqp0kS6TfxglfmBD2NU7Xlta6shw30F874GYAW+ACaAxqvnM3oxM3+/rn9uLKhDG2DYah5ZCXMJxO0lrLZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb7e6c9aca6796d668b4c64afc3e13420b713204803906f7df98f359e2e961d2","last_reissued_at":"2026-07-05T10:02:24.421936Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:24.421936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.10788","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:02:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8X5oo+6yqG+1UYqrPjounnDHyfBB0lh9aHnJ04mnUq3aG+u4YQC1aDwKamJhEukapTDvbrEtNELbEiXbYdhHCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T09:36:01.371406Z"},"content_sha256":"816ac08c1e793229211626df55f255f46afeca7af5357dc7aaf2f2e22d159225","schema_version":"1.0","event_id":"sha256:816ac08c1e793229211626df55f255f46afeca7af5357dc7aaf2f2e22d159225"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5N7GZGWKM6LNM2FUYZFPYPQTII","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring Prediction Targets in Masked Pre-Training for Speech Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Ahmed Hussen Abdelaziz, Alexander Rudnicky, Barry-John Theobald, He Bai, Li-Wei Chen, Shinji Watanabe, Takuya Higuchi, Tatiana Likhomanenko, Zakaria Aldeneh","submitted_at":"2024-09-16T23:51:42Z","abstract_excerpt":"Speech foundation models, such as HuBERT and its variants, are pre-trained on large amounts of unlabeled speech data and then used for a range of downstream tasks. These models use a masked prediction objective, where the model learns to predict information about masked input segments from the unmasked context. The choice of prediction targets in this framework impacts their performance on downstream tasks. For instance, models pre-trained with targets that capture prosody learn representations suited for speaker-related tasks, while those pre-trained with targets that capture phonetics learn "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10788","kind":"arxiv","version":2},"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/2409.10788/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":"2026-07-05T10:02:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OFPxSy+O5Op14SjCafjAgs3UFcYd+k90a7nyp11H5ZduvxLRq0YVOxxsDSnHYboUMLg3SPfdkzOLPdLqJ3hRBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T09:36:01.372470Z"},"content_sha256":"e18eb692dd03e16411c5bdee0938bf709bbe15949203e2a27ce63e8f7b711f36","schema_version":"1.0","event_id":"sha256:e18eb692dd03e16411c5bdee0938bf709bbe15949203e2a27ce63e8f7b711f36"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5N7GZGWKM6LNM2FUYZFPYPQTII/bundle.json","state_url":"https://pith.science/pith/5N7GZGWKM6LNM2FUYZFPYPQTII/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5N7GZGWKM6LNM2FUYZFPYPQTII/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":"2026-08-18T09:36:01Z","links":{"resolver":"https://pith.science/pith/5N7GZGWKM6LNM2FUYZFPYPQTII","bundle":"https://pith.science/pith/5N7GZGWKM6LNM2FUYZFPYPQTII/bundle.json","state":"https://pith.science/pith/5N7GZGWKM6LNM2FUYZFPYPQTII/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5N7GZGWKM6LNM2FUYZFPYPQTII/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5N7GZGWKM6LNM2FUYZFPYPQTII","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":"2339a6b67fe179935934ed628e109766a1eb9ed113777e7dd359ad260361442a","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-16T23:51:42Z","title_canon_sha256":"5f4ec5c435ef02211a5c103c40ce84b85741efe41872075dc997ae8051420c65"},"schema_version":"1.0","source":{"id":"2409.10788","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.10788","created_at":"2026-07-05T10:02:24Z"},{"alias_kind":"arxiv_version","alias_value":"2409.10788v2","created_at":"2026-07-05T10:02:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10788","created_at":"2026-07-05T10:02:24Z"},{"alias_kind":"pith_short_12","alias_value":"5N7GZGWKM6LN","created_at":"2026-07-05T10:02:24Z"},{"alias_kind":"pith_short_16","alias_value":"5N7GZGWKM6LNM2FU","created_at":"2026-07-05T10:02:24Z"},{"alias_kind":"pith_short_8","alias_value":"5N7GZGWK","created_at":"2026-07-05T10:02:24Z"}],"graph_snapshots":[{"event_id":"sha256:e18eb692dd03e16411c5bdee0938bf709bbe15949203e2a27ce63e8f7b711f36","target":"graph","created_at":"2026-07-05T10:02:24Z","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/2409.10788/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech foundation models, such as HuBERT and its variants, are pre-trained on large amounts of unlabeled speech data and then used for a range of downstream tasks. These models use a masked prediction objective, where the model learns to predict information about masked input segments from the unmasked context. The choice of prediction targets in this framework impacts their performance on downstream tasks. For instance, models pre-trained with targets that capture prosody learn representations suited for speaker-related tasks, while those pre-trained with targets that capture phonetics learn ","authors_text":"Ahmed Hussen Abdelaziz, Alexander Rudnicky, Barry-John Theobald, He Bai, Li-Wei Chen, Shinji Watanabe, Takuya Higuchi, Tatiana Likhomanenko, Zakaria Aldeneh","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-16T23:51:42Z","title":"Exploring Prediction Targets in Masked Pre-Training for Speech Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10788","kind":"arxiv","version":2},"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":"sha256:816ac08c1e793229211626df55f255f46afeca7af5357dc7aaf2f2e22d159225","target":"record","created_at":"2026-07-05T10:02:24Z","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":"2339a6b67fe179935934ed628e109766a1eb9ed113777e7dd359ad260361442a","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-16T23:51:42Z","title_canon_sha256":"5f4ec5c435ef02211a5c103c40ce84b85741efe41872075dc997ae8051420c65"},"schema_version":"1.0","source":{"id":"2409.10788","kind":"arxiv","version":2}},"canonical_sha256":"eb7e6c9aca6796d668b4c64afc3e13420b713204803906f7df98f359e2e961d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb7e6c9aca6796d668b4c64afc3e13420b713204803906f7df98f359e2e961d2","first_computed_at":"2026-07-05T10:02:24.421936Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:24.421936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rtoqp0kS6TfxglfmBD2NU7Xlta6shw30F874GYAW+ACaAxqvnM3oxM3+/rn9uLKhDG2DYah5ZCXMJxO0lrLZAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:24.422383Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.10788","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:816ac08c1e793229211626df55f255f46afeca7af5357dc7aaf2f2e22d159225","sha256:e18eb692dd03e16411c5bdee0938bf709bbe15949203e2a27ce63e8f7b711f36"],"state_sha256":"92bb1cc0e77d95ef18c922741c956a9edec4af1b11720d916c67772c492ae27d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LL8/+Kn4XVs3V5qD3dEsROYWgPZbsUR954KMyVPdRJXALA34eOB7Nf6RD/ay6bigKvKbdDJgJAFRR0DtBE1xBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T09:36:01.380884Z","bundle_sha256":"e8c2589fb5fad20fb0f93f86f9f3b4d09c2c48a5797cc6659c47184defd358ad"}}