{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CHJ2U3WQ647RG4E5PWKLXOJ5ET","short_pith_number":"pith:CHJ2U3WQ","canonical_record":{"source":{"id":"2606.10853","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-09T13:32:13Z","cross_cats_sorted":[],"title_canon_sha256":"0006a8ecaa035992f6f6d33557d631b2cf635a98bd040125e66f072598789fe0","abstract_canon_sha256":"8c96dafd6a45d41c7fc57b5e74793f56ca15f5f8167a0ce33b47c5ac3d5dc54b"},"schema_version":"1.0"},"canonical_sha256":"11d3aa6ed0f73f13709d7d94bbb93d24fa292c526c2c4e48a4e7b225fee8dd4b","source":{"kind":"arxiv","id":"2606.10853","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10853","created_at":"2026-06-10T01:10:43Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10853v1","created_at":"2026-06-10T01:10:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10853","created_at":"2026-06-10T01:10:43Z"},{"alias_kind":"pith_short_12","alias_value":"CHJ2U3WQ647R","created_at":"2026-06-10T01:10:43Z"},{"alias_kind":"pith_short_16","alias_value":"CHJ2U3WQ647RG4E5","created_at":"2026-06-10T01:10:43Z"},{"alias_kind":"pith_short_8","alias_value":"CHJ2U3WQ","created_at":"2026-06-10T01:10:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CHJ2U3WQ647RG4E5PWKLXOJ5ET","target":"record","payload":{"canonical_record":{"source":{"id":"2606.10853","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-09T13:32:13Z","cross_cats_sorted":[],"title_canon_sha256":"0006a8ecaa035992f6f6d33557d631b2cf635a98bd040125e66f072598789fe0","abstract_canon_sha256":"8c96dafd6a45d41c7fc57b5e74793f56ca15f5f8167a0ce33b47c5ac3d5dc54b"},"schema_version":"1.0"},"canonical_sha256":"11d3aa6ed0f73f13709d7d94bbb93d24fa292c526c2c4e48a4e7b225fee8dd4b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:43.995066Z","signature_b64":"k9Tyy/xTD0lYabRmGrSe0jzV2FdMo395GNxklnIhyxAVQC8Y8rSmPhhtUtP3Ft2y8o74ZyNYpZKSqT4s/00RDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11d3aa6ed0f73f13709d7d94bbb93d24fa292c526c2c4e48a4e7b225fee8dd4b","last_reissued_at":"2026-06-10T01:10:43.994211Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:43.994211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.10853","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":"2026-06-10T01:10:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7bc8K1rhP6L/vunfqT8l+wCc3MhKrs/auOr6ECUJOjV7E4ko+3NQofFKBPauDq0uQMWy3jTgrpr7asgpFUnWDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:37:23.602316Z"},"content_sha256":"5942b271b1f0707a1dfc9df54dab7f34205e3b6a14659462ebfc4afc877c5e33","schema_version":"1.0","event_id":"sha256:5942b271b1f0707a1dfc9df54dab7f34205e3b6a14659462ebfc4afc877c5e33"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CHJ2U3WQ647RG4E5PWKLXOJ5ET","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speech Encoder Fusion for LLM-based Automatic Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Hugo Van hamme, Jakob Poncelet","submitted_at":"2026-06-09T13:32:13Z","abstract_excerpt":"Speech-aware large language models (LLMs) can incorporate speech through pre-trained acoustic encoders that project speech features into the LLM embedding space. While the choice of the speech encoder critically influences performance, different encoders often exhibit complementary strengths, motivating their combination. In this work, we investigate whether fusing multiple pre-trained speech encoders can enhance speech-aware LLMs for automatic speech recognition (ASR). We explore several fusion strategies beyond simple feature concatenation, including learned combinations and Transformer-base"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10853","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/2606.10853/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":"2026-06-10T01:10:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6BvvgDDeHWH1Cm+3DZ6yYl0NEVPhxMecuT3kdQcXoOpkMKxqejIocE1Jabs44zY4oqJhl5tcyKyMEMiifYlaBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:37:23.602903Z"},"content_sha256":"3b8cab8eff71f661f0d03ca354b3da53166e7c6bf5fc09869ff1f7b054100cf7","schema_version":"1.0","event_id":"sha256:3b8cab8eff71f661f0d03ca354b3da53166e7c6bf5fc09869ff1f7b054100cf7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CHJ2U3WQ647RG4E5PWKLXOJ5ET/bundle.json","state_url":"https://pith.science/pith/CHJ2U3WQ647RG4E5PWKLXOJ5ET/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CHJ2U3WQ647RG4E5PWKLXOJ5ET/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":"2026-08-14T08:37:23Z","links":{"resolver":"https://pith.science/pith/CHJ2U3WQ647RG4E5PWKLXOJ5ET","bundle":"https://pith.science/pith/CHJ2U3WQ647RG4E5PWKLXOJ5ET/bundle.json","state":"https://pith.science/pith/CHJ2U3WQ647RG4E5PWKLXOJ5ET/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CHJ2U3WQ647RG4E5PWKLXOJ5ET/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CHJ2U3WQ647RG4E5PWKLXOJ5ET","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":"8c96dafd6a45d41c7fc57b5e74793f56ca15f5f8167a0ce33b47c5ac3d5dc54b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-09T13:32:13Z","title_canon_sha256":"0006a8ecaa035992f6f6d33557d631b2cf635a98bd040125e66f072598789fe0"},"schema_version":"1.0","source":{"id":"2606.10853","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10853","created_at":"2026-06-10T01:10:43Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10853v1","created_at":"2026-06-10T01:10:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10853","created_at":"2026-06-10T01:10:43Z"},{"alias_kind":"pith_short_12","alias_value":"CHJ2U3WQ647R","created_at":"2026-06-10T01:10:43Z"},{"alias_kind":"pith_short_16","alias_value":"CHJ2U3WQ647RG4E5","created_at":"2026-06-10T01:10:43Z"},{"alias_kind":"pith_short_8","alias_value":"CHJ2U3WQ","created_at":"2026-06-10T01:10:43Z"}],"graph_snapshots":[{"event_id":"sha256:3b8cab8eff71f661f0d03ca354b3da53166e7c6bf5fc09869ff1f7b054100cf7","target":"graph","created_at":"2026-06-10T01:10:43Z","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/2606.10853/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech-aware large language models (LLMs) can incorporate speech through pre-trained acoustic encoders that project speech features into the LLM embedding space. While the choice of the speech encoder critically influences performance, different encoders often exhibit complementary strengths, motivating their combination. In this work, we investigate whether fusing multiple pre-trained speech encoders can enhance speech-aware LLMs for automatic speech recognition (ASR). We explore several fusion strategies beyond simple feature concatenation, including learned combinations and Transformer-base","authors_text":"Hugo Van hamme, Jakob Poncelet","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-09T13:32:13Z","title":"Speech Encoder Fusion for LLM-based Automatic Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10853","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":"sha256:5942b271b1f0707a1dfc9df54dab7f34205e3b6a14659462ebfc4afc877c5e33","target":"record","created_at":"2026-06-10T01:10:43Z","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":"8c96dafd6a45d41c7fc57b5e74793f56ca15f5f8167a0ce33b47c5ac3d5dc54b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-09T13:32:13Z","title_canon_sha256":"0006a8ecaa035992f6f6d33557d631b2cf635a98bd040125e66f072598789fe0"},"schema_version":"1.0","source":{"id":"2606.10853","kind":"arxiv","version":1}},"canonical_sha256":"11d3aa6ed0f73f13709d7d94bbb93d24fa292c526c2c4e48a4e7b225fee8dd4b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11d3aa6ed0f73f13709d7d94bbb93d24fa292c526c2c4e48a4e7b225fee8dd4b","first_computed_at":"2026-06-10T01:10:43.994211Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:10:43.994211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k9Tyy/xTD0lYabRmGrSe0jzV2FdMo395GNxklnIhyxAVQC8Y8rSmPhhtUtP3Ft2y8o74ZyNYpZKSqT4s/00RDQ==","signature_status":"signed_v1","signed_at":"2026-06-10T01:10:43.995066Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10853","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5942b271b1f0707a1dfc9df54dab7f34205e3b6a14659462ebfc4afc877c5e33","sha256:3b8cab8eff71f661f0d03ca354b3da53166e7c6bf5fc09869ff1f7b054100cf7"],"state_sha256":"ccb3ddc2aad3709c60087210674093b1ccd0eacf8c6ddc3292016238fe54a9d6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i+jSv3WYqOMd3sw3uyhVoGMHWdyKJDeBNqnTwEaV7zdOa7QjPvLuJdWnqvjX/nOjTjpQ/ccrdcVRTUNTWgqFCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T08:37:23.609985Z","bundle_sha256":"c48f8a3b167b8ac93d16fc587c924f3ca27c94f9635e5ce8020ee90d21b3e9c2"}}