{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AOMELPD6UMSIFSCWMDTC3ZFMBJ","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":"5cc51fc713113b1bb66e5a75605136180c087cb8ad0e222b58f00f091b4a6942","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-08T22:44:04Z","title_canon_sha256":"816f133c5a845f7dd2edd7029aa8cc0b8be0ae2a178a42a7c38b14ac2a7e9370"},"schema_version":"1.0","source":{"id":"2606.10231","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10231","created_at":"2026-06-10T01:09:00Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10231v1","created_at":"2026-06-10T01:09:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10231","created_at":"2026-06-10T01:09:00Z"},{"alias_kind":"pith_short_12","alias_value":"AOMELPD6UMSI","created_at":"2026-06-10T01:09:00Z"},{"alias_kind":"pith_short_16","alias_value":"AOMELPD6UMSIFSCW","created_at":"2026-06-10T01:09:00Z"},{"alias_kind":"pith_short_8","alias_value":"AOMELPD6","created_at":"2026-06-10T01:09:00Z"}],"graph_snapshots":[{"event_id":"sha256:a0f88fe7d69fccd1898246a3d4473fd0199bdb74efc6860f4cd278d19638e02f","target":"graph","created_at":"2026-06-10T01:09:00Z","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/2606.10231/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent speech-aware large language models (Speech-LLMs) rely on a pre-trained speech encoder to convert audio into semantic-rich representations consumable by LLM. In this work, instead, we explore: can an LLM learn to read Mel spectrogram directly without a dedicated speech encoder? We propose Mel-LLM, an encoder-free Speech-LLM that feeds lightly pre-processed Mel spectrogram patches directly into the LLM through a linear projection, allowing the LLM to learn speech-text alignment purely through its own parameters. We conduct extensive experiments on both automatic speech recognition (ASR) a","authors_text":"Bo Ren, Jinyu Li, Ruchao Fan, Xiaofei Wang, Yao Qian, Yiming Wang, Yufei Xia, Yuxuan Hu","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-08T22:44:04Z","title":"LLM can Read Spectrogram: Encoder-free Speech-Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10231","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":"sha256:63f0c1b791f2b2089b8229d884ee6f0935ed48b9bcd38a12f2c1df19b366b444","target":"record","created_at":"2026-06-10T01:09:00Z","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":"5cc51fc713113b1bb66e5a75605136180c087cb8ad0e222b58f00f091b4a6942","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-08T22:44:04Z","title_canon_sha256":"816f133c5a845f7dd2edd7029aa8cc0b8be0ae2a178a42a7c38b14ac2a7e9370"},"schema_version":"1.0","source":{"id":"2606.10231","kind":"arxiv","version":1}},"canonical_sha256":"039845bc7ea32482c85660e62de4ac0a70c8816f027b9a928bec7debe640691d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"039845bc7ea32482c85660e62de4ac0a70c8816f027b9a928bec7debe640691d","first_computed_at":"2026-06-10T01:09:00.780338Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:09:00.780338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MLyHP1c7P1A5mAk0DsmzubB4Y1erGeXV2Jur93ryn/m8lPh8liG7mmFD9Fd/KplS5l0x1USXOaZUqkxpu30mDQ==","signature_status":"signed_v1","signed_at":"2026-06-10T01:09:00.781191Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10231","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63f0c1b791f2b2089b8229d884ee6f0935ed48b9bcd38a12f2c1df19b366b444","sha256:a0f88fe7d69fccd1898246a3d4473fd0199bdb74efc6860f4cd278d19638e02f"],"state_sha256":"40218d67d5758044eff1c1c28a06747dc3c1faf7964502116c0a79936c96bc38"}