{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QPNNBTJO3SHC7SZLOU7D7WKLQ6","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":"89e7f11056c082d8193e011768e1f4f7b8d527e1879da424079c84be51cba02d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-27T03:52:52Z","title_canon_sha256":"6a3605d04199e8d52c4010ff77e3545d025b55f915ff94706168e65a85cf521e"},"schema_version":"1.0","source":{"id":"2305.17356","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17356","created_at":"2026-07-05T06:14:26Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17356v1","created_at":"2026-07-05T06:14:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17356","created_at":"2026-07-05T06:14:26Z"},{"alias_kind":"pith_short_12","alias_value":"QPNNBTJO3SHC","created_at":"2026-07-05T06:14:26Z"},{"alias_kind":"pith_short_16","alias_value":"QPNNBTJO3SHC7SZL","created_at":"2026-07-05T06:14:26Z"},{"alias_kind":"pith_short_8","alias_value":"QPNNBTJO","created_at":"2026-07-05T06:14:26Z"}],"graph_snapshots":[{"event_id":"sha256:923aec3c26122d84070f8ccfbcecd35113a75abb78a5a184250288832f2183c7","target":"graph","created_at":"2026-07-05T06:14:26Z","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/2305.17356/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Transformer has become the de-facto standard for speech, modeling upon the fine-grained frame-level features remains an open challenge of capturing long-distance dependencies and distributing the attention weights. We propose \\textit{Progressive Down-Sampling} (PDS) which gradually compresses the acoustic features into coarser-grained units containing more complete semantic information, like text-level representation. In addition, we develop a representation fusion method to alleviate information loss that occurs inevitably during high compression. In this way, we compress the acoustic f","authors_text":"Anxiang Ma, Chengbo Jiao, Chen Xu, Chi Hu, Huizhen Wang, Jingbo Zhu, Tong Xiao, Xiaoqian Liu, Xin Zeng, Yuhao Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-27T03:52:52Z","title":"Bridging the Granularity Gap for Acoustic Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17356","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:d30ac7a2cbc84ee4732a57c7b6ea4bac5bd2e46798419aceb6363dc8fa6d443e","target":"record","created_at":"2026-07-05T06:14:26Z","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":"89e7f11056c082d8193e011768e1f4f7b8d527e1879da424079c84be51cba02d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-27T03:52:52Z","title_canon_sha256":"6a3605d04199e8d52c4010ff77e3545d025b55f915ff94706168e65a85cf521e"},"schema_version":"1.0","source":{"id":"2305.17356","kind":"arxiv","version":1}},"canonical_sha256":"83dad0cd2edc8e2fcb2b753e3fd94b87b7db5a0bf615965665c3be300ceacffa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83dad0cd2edc8e2fcb2b753e3fd94b87b7db5a0bf615965665c3be300ceacffa","first_computed_at":"2026-07-05T06:14:26.866082Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:26.866082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V6EgDxe9ujV+l5w3qwzaXprkpURLT49Xauk0sOSNeJtqAFuwZTeBjeco0xYMRMF49jLsuxrWWkAjDgVrZVKVBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:26.866562Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.17356","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d30ac7a2cbc84ee4732a57c7b6ea4bac5bd2e46798419aceb6363dc8fa6d443e","sha256:923aec3c26122d84070f8ccfbcecd35113a75abb78a5a184250288832f2183c7"],"state_sha256":"7fd592051489cb0861df7855ddc80f07d63d0f49d6c77a2cbf3482e645fd5295"}