{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BWW4FPF2ZLEEG6LZBULPRE4FSH","short_pith_number":"pith:BWW4FPF2","canonical_record":{"source":{"id":"2509.00503","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-30T13:50:58Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"cfe45ef5645bc0017cb25db87bdd8e91be9afcc14584bcff21051d1f8b745a37","abstract_canon_sha256":"c56eb4189ab8e3559c291fda31cc8094a8f78302b1dd1b4a763fc2f8a368edc2"},"schema_version":"1.0"},"canonical_sha256":"0dadc2bcbacac84379790d16f8938591f035e8d160773e2ab99eec996a46508c","source":{"kind":"arxiv","id":"2509.00503","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00503","created_at":"2026-07-05T12:02:17Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00503v1","created_at":"2026-07-05T12:02:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00503","created_at":"2026-07-05T12:02:17Z"},{"alias_kind":"pith_short_12","alias_value":"BWW4FPF2ZLEE","created_at":"2026-07-05T12:02:17Z"},{"alias_kind":"pith_short_16","alias_value":"BWW4FPF2ZLEEG6LZ","created_at":"2026-07-05T12:02:17Z"},{"alias_kind":"pith_short_8","alias_value":"BWW4FPF2","created_at":"2026-07-05T12:02:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BWW4FPF2ZLEEG6LZBULPRE4FSH","target":"record","payload":{"canonical_record":{"source":{"id":"2509.00503","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-30T13:50:58Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"cfe45ef5645bc0017cb25db87bdd8e91be9afcc14584bcff21051d1f8b745a37","abstract_canon_sha256":"c56eb4189ab8e3559c291fda31cc8094a8f78302b1dd1b4a763fc2f8a368edc2"},"schema_version":"1.0"},"canonical_sha256":"0dadc2bcbacac84379790d16f8938591f035e8d160773e2ab99eec996a46508c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:17.335393Z","signature_b64":"z7DxX8PmgRAWtLxM94/p5rTwdNl8FKsQ/WWQ4FyBjsorauDKCu0e++GD93e0Ce2zk1ibG/tGc0gUjACnS+FnAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0dadc2bcbacac84379790d16f8938591f035e8d160773e2ab99eec996a46508c","last_reissued_at":"2026-07-05T12:02:17.334942Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:17.334942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.00503","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":"2026-07-05T12:02:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"By1GSZt/AaTzBkcWgQLjcwrnbNxhf8WeCKUZledWGs1hA7x1gQ5lkGQqT9dK+NDha3/DtESszLAlzzqWSyr5CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:52:45.627980Z"},"content_sha256":"155fd00878d719277076c90a38deeb3ff2a392b203fff9591daf02bb2a9dbcaa","schema_version":"1.0","event_id":"sha256:155fd00878d719277076c90a38deeb3ff2a392b203fff9591daf02bb2a9dbcaa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BWW4FPF2ZLEEG6LZBULPRE4FSH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Entropy-based Coarse and Compressed Semantic Speech Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Guangyan Zhang, Jialong Zuo, Jingyu Li, Minghui Fang, Shengpeng Ji, Xiaoqi Jiao, Yiwen Guo, Zhou Zhao","submitted_at":"2025-08-30T13:50:58Z","abstract_excerpt":"Discrete speech representation learning has recently attracted increasing interest in both acoustic and semantic modeling. Existing approaches typically encode 16 kHz waveforms into discrete tokens at a rate of 25 or 50 tokens per second. However, given that speech generally conveys only 2 to 5 words per second, such fine-grained tokenization introduces redundancy and hinders efficiency in downstream training and inference. Moreover, semantic speech representations at this frequency primarily capture phonetic-level information, while semantic understanding may not require such detailed token-l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00503","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/2509.00503/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":"2026-07-05T12:02:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hmjhd6KpM0N90q1q6pS2jDN8RJ5inx/pC/DoJoXrWVCuwLozlEE+Gm5UxPJ1PS9gWRPl90NDUy+4p/70whrvDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:52:45.628537Z"},"content_sha256":"8d5482656171e11c26fa0b81de3fba877d72e6a542960a1e9ca89f2380466d1b","schema_version":"1.0","event_id":"sha256:8d5482656171e11c26fa0b81de3fba877d72e6a542960a1e9ca89f2380466d1b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BWW4FPF2ZLEEG6LZBULPRE4FSH/bundle.json","state_url":"https://pith.science/pith/BWW4FPF2ZLEEG6LZBULPRE4FSH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BWW4FPF2ZLEEG6LZBULPRE4FSH/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":"2026-08-05T23:52:45Z","links":{"resolver":"https://pith.science/pith/BWW4FPF2ZLEEG6LZBULPRE4FSH","bundle":"https://pith.science/pith/BWW4FPF2ZLEEG6LZBULPRE4FSH/bundle.json","state":"https://pith.science/pith/BWW4FPF2ZLEEG6LZBULPRE4FSH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BWW4FPF2ZLEEG6LZBULPRE4FSH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BWW4FPF2ZLEEG6LZBULPRE4FSH","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":"c56eb4189ab8e3559c291fda31cc8094a8f78302b1dd1b4a763fc2f8a368edc2","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-30T13:50:58Z","title_canon_sha256":"cfe45ef5645bc0017cb25db87bdd8e91be9afcc14584bcff21051d1f8b745a37"},"schema_version":"1.0","source":{"id":"2509.00503","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00503","created_at":"2026-07-05T12:02:17Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00503v1","created_at":"2026-07-05T12:02:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00503","created_at":"2026-07-05T12:02:17Z"},{"alias_kind":"pith_short_12","alias_value":"BWW4FPF2ZLEE","created_at":"2026-07-05T12:02:17Z"},{"alias_kind":"pith_short_16","alias_value":"BWW4FPF2ZLEEG6LZ","created_at":"2026-07-05T12:02:17Z"},{"alias_kind":"pith_short_8","alias_value":"BWW4FPF2","created_at":"2026-07-05T12:02:17Z"}],"graph_snapshots":[{"event_id":"sha256:8d5482656171e11c26fa0b81de3fba877d72e6a542960a1e9ca89f2380466d1b","target":"graph","created_at":"2026-07-05T12:02:17Z","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/2509.00503/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Discrete speech representation learning has recently attracted increasing interest in both acoustic and semantic modeling. Existing approaches typically encode 16 kHz waveforms into discrete tokens at a rate of 25 or 50 tokens per second. However, given that speech generally conveys only 2 to 5 words per second, such fine-grained tokenization introduces redundancy and hinders efficiency in downstream training and inference. Moreover, semantic speech representations at this frequency primarily capture phonetic-level information, while semantic understanding may not require such detailed token-l","authors_text":"Guangyan Zhang, Jialong Zuo, Jingyu Li, Minghui Fang, Shengpeng Ji, Xiaoqi Jiao, Yiwen Guo, Zhou Zhao","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-30T13:50:58Z","title":"Entropy-based Coarse and Compressed Semantic Speech Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00503","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":"sha256:155fd00878d719277076c90a38deeb3ff2a392b203fff9591daf02bb2a9dbcaa","target":"record","created_at":"2026-07-05T12:02:17Z","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":"c56eb4189ab8e3559c291fda31cc8094a8f78302b1dd1b4a763fc2f8a368edc2","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-30T13:50:58Z","title_canon_sha256":"cfe45ef5645bc0017cb25db87bdd8e91be9afcc14584bcff21051d1f8b745a37"},"schema_version":"1.0","source":{"id":"2509.00503","kind":"arxiv","version":1}},"canonical_sha256":"0dadc2bcbacac84379790d16f8938591f035e8d160773e2ab99eec996a46508c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0dadc2bcbacac84379790d16f8938591f035e8d160773e2ab99eec996a46508c","first_computed_at":"2026-07-05T12:02:17.334942Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:02:17.334942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z7DxX8PmgRAWtLxM94/p5rTwdNl8FKsQ/WWQ4FyBjsorauDKCu0e++GD93e0Ce2zk1ibG/tGc0gUjACnS+FnAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:02:17.335393Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.00503","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:155fd00878d719277076c90a38deeb3ff2a392b203fff9591daf02bb2a9dbcaa","sha256:8d5482656171e11c26fa0b81de3fba877d72e6a542960a1e9ca89f2380466d1b"],"state_sha256":"57645673c1ec996bba238692a05336862fe87813493dad8a4a8eae7e8ffb9f8b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9+LJWl4Ts7iwsvK7z67RqSJ5Ouc/yNqpzmGzziuxAKC2uKvPtySo7/m3jSBCMOGxdwbM91ofX0qRHv3R0Y8uBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T23:52:45.633297Z","bundle_sha256":"360ed5b8cffd841eb68459c2cb9845e22d84fc3e64a22034c6c3b23bedcd3c40"}}