{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XEBAFDJBTGZ4CH25SC5V3LHKUK","short_pith_number":"pith:XEBAFDJB","schema_version":"1.0","canonical_sha256":"b902028d2199b3c11f5d90bb5daceaa2840aab89621e9577377afff32ff32cca","source":{"kind":"arxiv","id":"2407.14875","version":1},"attestation_state":"computed","paper":{"title":"Seal: Advancing Speech Language Models to be Few-Shot Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiaolong Yang, Lingen Liu, Shuyu Lei, Xiang Guo, Yasen Jiao, Yushu Yang, Yuxiang Yang","submitted_at":"2024-07-20T13:28:12Z","abstract_excerpt":"Existing auto-regressive language models have demonstrated a remarkable capability to perform a new task with just a few examples in prompt, without requiring any additional training. In order to extend this capability to a multi-modal setting (i.e. speech and language), this paper introduces the Seal model, an abbreviation for speech language model. It incorporates a novel alignment method, in which Kullback-Leibler divergence loss is performed to train a projector that bridges a frozen speech encoder with a frozen language model decoder. The resulting Seal model exhibits robust performance a"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2407.14875","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-20T13:28:12Z","cross_cats_sorted":[],"title_canon_sha256":"630edc28a9f7698bf8956b5a5c8d29e0b98ec61bfbc300c1b0dfb0a9f545365b","abstract_canon_sha256":"0abd5d75d256121cc0d19e7776558edfe9776fad4fb76def78c773f705b164ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:35.358700Z","signature_b64":"sZ8qhP0rNLCdnrz+l5cU6OeZ4WJ7uqmLKzLito+KvmatvrANFUCP0Hp8yM/Eu5arP+gC177LKWaNggM23iX0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b902028d2199b3c11f5d90bb5daceaa2840aab89621e9577377afff32ff32cca","last_reissued_at":"2026-07-05T08:46:35.358180Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:35.358180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Seal: Advancing Speech Language Models to be Few-Shot Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiaolong Yang, Lingen Liu, Shuyu Lei, Xiang Guo, Yasen Jiao, Yushu Yang, Yuxiang Yang","submitted_at":"2024-07-20T13:28:12Z","abstract_excerpt":"Existing auto-regressive language models have demonstrated a remarkable capability to perform a new task with just a few examples in prompt, without requiring any additional training. In order to extend this capability to a multi-modal setting (i.e. speech and language), this paper introduces the Seal model, an abbreviation for speech language model. It incorporates a novel alignment method, in which Kullback-Leibler divergence loss is performed to train a projector that bridges a frozen speech encoder with a frozen language model decoder. The resulting Seal model exhibits robust performance a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14875","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/2407.14875/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2407.14875","created_at":"2026-07-05T08:46:35.358250+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.14875v1","created_at":"2026-07-05T08:46:35.358250+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14875","created_at":"2026-07-05T08:46:35.358250+00:00"},{"alias_kind":"pith_short_12","alias_value":"XEBAFDJBTGZ4","created_at":"2026-07-05T08:46:35.358250+00:00"},{"alias_kind":"pith_short_16","alias_value":"XEBAFDJBTGZ4CH25","created_at":"2026-07-05T08:46:35.358250+00:00"},{"alias_kind":"pith_short_8","alias_value":"XEBAFDJB","created_at":"2026-07-05T08:46:35.358250+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XEBAFDJBTGZ4CH25SC5V3LHKUK","json":"https://pith.science/pith/XEBAFDJBTGZ4CH25SC5V3LHKUK.json","graph_json":"https://pith.science/api/pith-number/XEBAFDJBTGZ4CH25SC5V3LHKUK/graph.json","events_json":"https://pith.science/api/pith-number/XEBAFDJBTGZ4CH25SC5V3LHKUK/events.json","paper":"https://pith.science/paper/XEBAFDJB"},"agent_actions":{"view_html":"https://pith.science/pith/XEBAFDJBTGZ4CH25SC5V3LHKUK","download_json":"https://pith.science/pith/XEBAFDJBTGZ4CH25SC5V3LHKUK.json","view_paper":"https://pith.science/paper/XEBAFDJB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.14875&json=true","fetch_graph":"https://pith.science/api/pith-number/XEBAFDJBTGZ4CH25SC5V3LHKUK/graph.json","fetch_events":"https://pith.science/api/pith-number/XEBAFDJBTGZ4CH25SC5V3LHKUK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XEBAFDJBTGZ4CH25SC5V3LHKUK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XEBAFDJBTGZ4CH25SC5V3LHKUK/action/storage_attestation","attest_author":"https://pith.science/pith/XEBAFDJBTGZ4CH25SC5V3LHKUK/action/author_attestation","sign_citation":"https://pith.science/pith/XEBAFDJBTGZ4CH25SC5V3LHKUK/action/citation_signature","submit_replication":"https://pith.science/pith/XEBAFDJBTGZ4CH25SC5V3LHKUK/action/replication_record"}},"created_at":"2026-07-05T08:46:35.358250+00:00","updated_at":"2026-07-05T08:46:35.358250+00:00"}