{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RMYEUJESASORVS27T36HY7LPS4","short_pith_number":"pith:RMYEUJES","canonical_record":{"source":{"id":"2412.01145","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-02T05:42:33Z","cross_cats_sorted":[],"title_canon_sha256":"543ba1f49c356c13104e6e9ca62943bcce8858f168ee5d53006fbb66209b9c2b","abstract_canon_sha256":"731ccc28532968efbffd64cca9238cb78de6347296c0486c133dec1872bd0729"},"schema_version":"1.0"},"canonical_sha256":"8b304a2492049d1acb5f9efc7c7d6f9714a7745de2eac4180595c9f9472fa536","source":{"kind":"arxiv","id":"2412.01145","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01145","created_at":"2026-07-05T11:31:41Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01145v2","created_at":"2026-07-05T11:31:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01145","created_at":"2026-07-05T11:31:41Z"},{"alias_kind":"pith_short_12","alias_value":"RMYEUJESASOR","created_at":"2026-07-05T11:31:41Z"},{"alias_kind":"pith_short_16","alias_value":"RMYEUJESASORVS27","created_at":"2026-07-05T11:31:41Z"},{"alias_kind":"pith_short_8","alias_value":"RMYEUJES","created_at":"2026-07-05T11:31:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RMYEUJESASORVS27T36HY7LPS4","target":"record","payload":{"canonical_record":{"source":{"id":"2412.01145","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-02T05:42:33Z","cross_cats_sorted":[],"title_canon_sha256":"543ba1f49c356c13104e6e9ca62943bcce8858f168ee5d53006fbb66209b9c2b","abstract_canon_sha256":"731ccc28532968efbffd64cca9238cb78de6347296c0486c133dec1872bd0729"},"schema_version":"1.0"},"canonical_sha256":"8b304a2492049d1acb5f9efc7c7d6f9714a7745de2eac4180595c9f9472fa536","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:41.688489Z","signature_b64":"qkmfunynWnEehAA6h0Va2G/5SqrvtcxqcYeo4QJR6zxgokNl2RpBs2s+KBDCrAGszu9SV2kU8c/qvtWTn9wgBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b304a2492049d1acb5f9efc7c7d6f9714a7745de2eac4180595c9f9472fa536","last_reissued_at":"2026-07-05T11:31:41.687983Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:41.687983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.01145","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:31:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cS58I8Ti/thYTldHDEAWxlrOb2eouSMhK81BDj67e+2G98OcPQSPUtVeN6Q0TiCeHw0lI8mL7rllzC9mDBujBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:47:24.984349Z"},"content_sha256":"9a24a1fe3f6d54c7ac08658f161f1ddb4ca5dcc3fb7fb80c6cefa70a0cc855ee","schema_version":"1.0","event_id":"sha256:9a24a1fe3f6d54c7ac08658f161f1ddb4ca5dcc3fb7fb80c6cefa70a0cc855ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RMYEUJESASORVS27T36HY7LPS4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AlignFormer: Modality Matching Can Achieve Better Zero-shot Instruction-Following Speech-LLM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Bo Ren, Jinyu Li, Ruchao Fan, Rui Zhao, Shujie Liu, Yuxuan Hu","submitted_at":"2024-12-02T05:42:33Z","abstract_excerpt":"Integrating speech into LLM (speech-LLM) has gaining increased attention recently. The mainstream solution is to connect a well-trained speech encoder and LLM with a neural adapter. However, the length mismatch between the speech and text sequences are not well handled, leading to imperfect modality matching between the speech and text. In this work, we propose a novel neural adapter, AlignFormer, to reduce the length gap between the two modalities. AlignFormer consists of CTC and dynamic-window QFormer layers, where the CTC alignment provides the dynamic window information for QFormer. The LL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01145","kind":"arxiv","version":2},"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/2412.01145/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":"2026-07-05T11:31:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r/QLC2kYtHC6buh23iZqTTfvVV+RfvN1ZT+BTZ6XDFfRBppsY+2sKTQVhRsC76BBHmyUEWLCDrlqU2V5hi49BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:47:24.984844Z"},"content_sha256":"44784f00801230e117d9f09ce2b0c838a0e209b302901932f95e297f3091b1d3","schema_version":"1.0","event_id":"sha256:44784f00801230e117d9f09ce2b0c838a0e209b302901932f95e297f3091b1d3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RMYEUJESASORVS27T36HY7LPS4/bundle.json","state_url":"https://pith.science/pith/RMYEUJESASORVS27T36HY7LPS4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RMYEUJESASORVS27T36HY7LPS4/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":"2026-08-07T19:47:24Z","links":{"resolver":"https://pith.science/pith/RMYEUJESASORVS27T36HY7LPS4","bundle":"https://pith.science/pith/RMYEUJESASORVS27T36HY7LPS4/bundle.json","state":"https://pith.science/pith/RMYEUJESASORVS27T36HY7LPS4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RMYEUJESASORVS27T36HY7LPS4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RMYEUJESASORVS27T36HY7LPS4","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":"731ccc28532968efbffd64cca9238cb78de6347296c0486c133dec1872bd0729","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-02T05:42:33Z","title_canon_sha256":"543ba1f49c356c13104e6e9ca62943bcce8858f168ee5d53006fbb66209b9c2b"},"schema_version":"1.0","source":{"id":"2412.01145","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01145","created_at":"2026-07-05T11:31:41Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01145v2","created_at":"2026-07-05T11:31:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01145","created_at":"2026-07-05T11:31:41Z"},{"alias_kind":"pith_short_12","alias_value":"RMYEUJESASOR","created_at":"2026-07-05T11:31:41Z"},{"alias_kind":"pith_short_16","alias_value":"RMYEUJESASORVS27","created_at":"2026-07-05T11:31:41Z"},{"alias_kind":"pith_short_8","alias_value":"RMYEUJES","created_at":"2026-07-05T11:31:41Z"}],"graph_snapshots":[{"event_id":"sha256:44784f00801230e117d9f09ce2b0c838a0e209b302901932f95e297f3091b1d3","target":"graph","created_at":"2026-07-05T11:31:41Z","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/2412.01145/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Integrating speech into LLM (speech-LLM) has gaining increased attention recently. The mainstream solution is to connect a well-trained speech encoder and LLM with a neural adapter. However, the length mismatch between the speech and text sequences are not well handled, leading to imperfect modality matching between the speech and text. In this work, we propose a novel neural adapter, AlignFormer, to reduce the length gap between the two modalities. AlignFormer consists of CTC and dynamic-window QFormer layers, where the CTC alignment provides the dynamic window information for QFormer. The LL","authors_text":"Bo Ren, Jinyu Li, Ruchao Fan, Rui Zhao, Shujie Liu, Yuxuan Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-02T05:42:33Z","title":"AlignFormer: Modality Matching Can Achieve Better Zero-shot Instruction-Following Speech-LLM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01145","kind":"arxiv","version":2},"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":"sha256:9a24a1fe3f6d54c7ac08658f161f1ddb4ca5dcc3fb7fb80c6cefa70a0cc855ee","target":"record","created_at":"2026-07-05T11:31:41Z","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":"731ccc28532968efbffd64cca9238cb78de6347296c0486c133dec1872bd0729","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-02T05:42:33Z","title_canon_sha256":"543ba1f49c356c13104e6e9ca62943bcce8858f168ee5d53006fbb66209b9c2b"},"schema_version":"1.0","source":{"id":"2412.01145","kind":"arxiv","version":2}},"canonical_sha256":"8b304a2492049d1acb5f9efc7c7d6f9714a7745de2eac4180595c9f9472fa536","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b304a2492049d1acb5f9efc7c7d6f9714a7745de2eac4180595c9f9472fa536","first_computed_at":"2026-07-05T11:31:41.687983Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:41.687983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qkmfunynWnEehAA6h0Va2G/5SqrvtcxqcYeo4QJR6zxgokNl2RpBs2s+KBDCrAGszu9SV2kU8c/qvtWTn9wgBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:41.688489Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.01145","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a24a1fe3f6d54c7ac08658f161f1ddb4ca5dcc3fb7fb80c6cefa70a0cc855ee","sha256:44784f00801230e117d9f09ce2b0c838a0e209b302901932f95e297f3091b1d3"],"state_sha256":"ba6b54de764dfe3f9aa09eecc888e9bfe213e9b58e226a1f320e613d95509b17"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ivoc4uhf6BVTL/a8jTrhcJXwsTNMEhgS7v50iqLfN3DWxHjWaYYP6+ba+MyLDVylImYzT6122WGl7Gvi6k2/Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:47:24.989998Z","bundle_sha256":"dc8df5313eb94fb7b92bc3fef539de63658e731288c5588e4ec5884a5d63d6f6"}}