{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OTH6HTFOXDYDTH4BT3SQS7TYBZ","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":"80d29833da0575091b5216da5bdaca5981fb77b58b3ae2f0cf98c60ded802c75","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-17T12:38:45Z","title_canon_sha256":"a614bfc882da5ed3871347407f4847dcb196254faa0daaf1c864a56dcac4a1dc"},"schema_version":"1.0","source":{"id":"2602.15537","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.15537","created_at":"2026-06-19T16:10:35Z"},{"alias_kind":"arxiv_version","alias_value":"2602.15537v2","created_at":"2026-06-19T16:10:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.15537","created_at":"2026-06-19T16:10:35Z"},{"alias_kind":"pith_short_12","alias_value":"OTH6HTFOXDYD","created_at":"2026-06-19T16:10:35Z"},{"alias_kind":"pith_short_16","alias_value":"OTH6HTFOXDYDTH4B","created_at":"2026-06-19T16:10:35Z"},{"alias_kind":"pith_short_8","alias_value":"OTH6HTFO","created_at":"2026-06-19T16:10:35Z"}],"graph_snapshots":[{"event_id":"sha256:028d05dd1d57dc28a9342154779494e9dd5124182944312ea5595d399dca3bc0","target":"graph","created_at":"2026-06-19T16:10:35Z","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/2602.15537/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pure speech language models aim to learn language directly from raw audio without textual resources. A key challenge is that discrete tokens from self-supervised speech encoders result in excessively long sequences, motivating recent work on syllable-like units. However, methods like Sylber and SyllableLM rely on intricate multi-stage training pipelines. We propose ZeroSyl, a simple training-free method to extract syllable boundaries and embeddings directly from a frozen WavLM model. Using L2 norms of features in WavLM's intermediate layers, ZeroSyl achieves competitive syllable segmentation p","authors_text":"Danel Slabbert, Herman Kamper, Nicol Visser, Simon Malan","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-17T12:38:45Z","title":"ZeroSyl: Simple Zero-Resource Syllable Tokenization for Spoken Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.15537","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":"sha256:46b5d62d2e6de04b74d25d5c6d9862eb271192350378858c23b0e0bc46eca46e","target":"record","created_at":"2026-06-19T16:10:35Z","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":"80d29833da0575091b5216da5bdaca5981fb77b58b3ae2f0cf98c60ded802c75","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-17T12:38:45Z","title_canon_sha256":"a614bfc882da5ed3871347407f4847dcb196254faa0daaf1c864a56dcac4a1dc"},"schema_version":"1.0","source":{"id":"2602.15537","kind":"arxiv","version":2}},"canonical_sha256":"74cfe3ccaeb8f0399f819ee5097e780e605d0e6bfcb0e6a4ada97a3f90bc9951","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74cfe3ccaeb8f0399f819ee5097e780e605d0e6bfcb0e6a4ada97a3f90bc9951","first_computed_at":"2026-06-19T16:10:35.419204Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:10:35.419204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8YpGaN8GnpsKZDtswxmx9I29595/znFZ6AXq90Xwh1Y419Fc0lTd8d7AaCeW4R+Wzzu87v1b/H/3YjXxYalbAw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:10:35.419670Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.15537","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:46b5d62d2e6de04b74d25d5c6d9862eb271192350378858c23b0e0bc46eca46e","sha256:028d05dd1d57dc28a9342154779494e9dd5124182944312ea5595d399dca3bc0"],"state_sha256":"9e3f628689b46ae79d6bbab37a2054545985a701a34664a9f5bb097d8ad3816c"}