{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XS2QFMVU4EUNEJVC5PE2UD6SFS","short_pith_number":"pith:XS2QFMVU","canonical_record":{"source":{"id":"2505.23494","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T14:43:48Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"2e74fe5d851a0e5060fbc685f49ad5d49237ee0f46eebfaf1c47a3de4ba07ab9","abstract_canon_sha256":"d21b1e7ab64b6a07260d26e8f522e21b483b9ae14843c482150e07a9f61d025f"},"schema_version":"1.0"},"canonical_sha256":"bcb502b2b4e128d226a2ebc9aa0fd22cad365dba112364839623598e7faa8593","source":{"kind":"arxiv","id":"2505.23494","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23494","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23494v1","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23494","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"pith_short_12","alias_value":"XS2QFMVU4EUN","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"pith_short_16","alias_value":"XS2QFMVU4EUNEJVC","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"pith_short_8","alias_value":"XS2QFMVU","created_at":"2026-07-05T11:12:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XS2QFMVU4EUNEJVC5PE2UD6SFS","target":"record","payload":{"canonical_record":{"source":{"id":"2505.23494","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T14:43:48Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"2e74fe5d851a0e5060fbc685f49ad5d49237ee0f46eebfaf1c47a3de4ba07ab9","abstract_canon_sha256":"d21b1e7ab64b6a07260d26e8f522e21b483b9ae14843c482150e07a9f61d025f"},"schema_version":"1.0"},"canonical_sha256":"bcb502b2b4e128d226a2ebc9aa0fd22cad365dba112364839623598e7faa8593","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:02.948791Z","signature_b64":"1NKYVqbMASmhod51DDsmWDA/02K/P65bDGDXxsPq6dwAf+q0NCUlmwy9t9mXv9OZZ6KumW55iu2pFtOIpvUABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcb502b2b4e128d226a2ebc9aa0fd22cad365dba112364839623598e7faa8593","last_reissued_at":"2026-07-05T11:12:02.948275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:02.948275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.23494","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":"2026-07-05T11:12:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rg0qW0SO7iWYX2fyzTWMYWZ3X6FYAu//3nzHW1k2D7ZlYW0T3GVVjNqg7yfujs2L0FUGIDWtqtMVFfSUeGnFDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:40:02.871740Z"},"content_sha256":"f79f1012be2a97cef52dd984fad1ae29b19e7cb83c624c506986e37775326939","schema_version":"1.0","event_id":"sha256:f79f1012be2a97cef52dd984fad1ae29b19e7cb83c624c506986e37775326939"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XS2QFMVU4EUNEJVC5PE2UD6SFS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Spoken Language Modeling with Duration-Penalized Self-Supervised Units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Herman Kamper, Nicol Visser","submitted_at":"2025-05-29T14:43:48Z","abstract_excerpt":"Spoken language models (SLMs) operate on acoustic units obtained by discretizing self-supervised speech representations. Although the characteristics of these units directly affect performance, the interaction between codebook size and unit coarseness (i.e., duration) remains unexplored. We investigate SLM performance as we vary codebook size and unit coarseness using the simple duration-penalized dynamic programming (DPDP) method. New analyses are performed across different linguistic levels. At the phone and word levels, coarseness provides little benefit, as long as the codebook size is cho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23494","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/2505.23494/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":"2026-07-05T11:12:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p6nr4LSGmT1EGFFqRGUvrsQc39LAEE/q4nu8kNGFbVvT0bHc4iKevt+AgZ4fS034TZ/W/p8BVbFMC69hC4vNBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:40:02.872246Z"},"content_sha256":"7cd812f3a65ef20af43f8c62b0aab3c8dd88ce3e789e101fee3c67e6a6193a31","schema_version":"1.0","event_id":"sha256:7cd812f3a65ef20af43f8c62b0aab3c8dd88ce3e789e101fee3c67e6a6193a31"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XS2QFMVU4EUNEJVC5PE2UD6SFS/bundle.json","state_url":"https://pith.science/pith/XS2QFMVU4EUNEJVC5PE2UD6SFS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XS2QFMVU4EUNEJVC5PE2UD6SFS/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":"2026-08-08T07:40:02Z","links":{"resolver":"https://pith.science/pith/XS2QFMVU4EUNEJVC5PE2UD6SFS","bundle":"https://pith.science/pith/XS2QFMVU4EUNEJVC5PE2UD6SFS/bundle.json","state":"https://pith.science/pith/XS2QFMVU4EUNEJVC5PE2UD6SFS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XS2QFMVU4EUNEJVC5PE2UD6SFS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XS2QFMVU4EUNEJVC5PE2UD6SFS","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":"d21b1e7ab64b6a07260d26e8f522e21b483b9ae14843c482150e07a9f61d025f","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T14:43:48Z","title_canon_sha256":"2e74fe5d851a0e5060fbc685f49ad5d49237ee0f46eebfaf1c47a3de4ba07ab9"},"schema_version":"1.0","source":{"id":"2505.23494","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23494","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23494v1","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23494","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"pith_short_12","alias_value":"XS2QFMVU4EUN","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"pith_short_16","alias_value":"XS2QFMVU4EUNEJVC","created_at":"2026-07-05T11:12:02Z"},{"alias_kind":"pith_short_8","alias_value":"XS2QFMVU","created_at":"2026-07-05T11:12:02Z"}],"graph_snapshots":[{"event_id":"sha256:7cd812f3a65ef20af43f8c62b0aab3c8dd88ce3e789e101fee3c67e6a6193a31","target":"graph","created_at":"2026-07-05T11:12:02Z","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/2505.23494/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spoken language models (SLMs) operate on acoustic units obtained by discretizing self-supervised speech representations. Although the characteristics of these units directly affect performance, the interaction between codebook size and unit coarseness (i.e., duration) remains unexplored. We investigate SLM performance as we vary codebook size and unit coarseness using the simple duration-penalized dynamic programming (DPDP) method. New analyses are performed across different linguistic levels. At the phone and word levels, coarseness provides little benefit, as long as the codebook size is cho","authors_text":"Herman Kamper, Nicol Visser","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T14:43:48Z","title":"Spoken Language Modeling with Duration-Penalized Self-Supervised Units"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23494","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:f79f1012be2a97cef52dd984fad1ae29b19e7cb83c624c506986e37775326939","target":"record","created_at":"2026-07-05T11:12:02Z","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":"d21b1e7ab64b6a07260d26e8f522e21b483b9ae14843c482150e07a9f61d025f","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T14:43:48Z","title_canon_sha256":"2e74fe5d851a0e5060fbc685f49ad5d49237ee0f46eebfaf1c47a3de4ba07ab9"},"schema_version":"1.0","source":{"id":"2505.23494","kind":"arxiv","version":1}},"canonical_sha256":"bcb502b2b4e128d226a2ebc9aa0fd22cad365dba112364839623598e7faa8593","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bcb502b2b4e128d226a2ebc9aa0fd22cad365dba112364839623598e7faa8593","first_computed_at":"2026-07-05T11:12:02.948275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:02.948275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1NKYVqbMASmhod51DDsmWDA/02K/P65bDGDXxsPq6dwAf+q0NCUlmwy9t9mXv9OZZ6KumW55iu2pFtOIpvUABA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:02.948791Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23494","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f79f1012be2a97cef52dd984fad1ae29b19e7cb83c624c506986e37775326939","sha256:7cd812f3a65ef20af43f8c62b0aab3c8dd88ce3e789e101fee3c67e6a6193a31"],"state_sha256":"1b3b87eb1d132305aab78356877b20e7f218b5a9489b2aa247a7ada2bde94ce2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rmMWdOaRNeUb7ojqOUqOOWjwX+qfTrhG57pQwDWo7R5Qcb2ftLie6O4k9By5QBIxj5ydEfF+3XEd3NKmFnNzDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T07:40:02.875608Z","bundle_sha256":"8d9b0772909d2f5cbaee7c442fb8fed5d18a6b744cc3e1ff49d55c2c417e481f"}}