{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EMEXYGSXDHKI5SKQSPC6HON373","short_pith_number":"pith:EMEXYGSX","schema_version":"1.0","canonical_sha256":"23097c1a5719d48ec95093c5e3b9bbfecb3d206c14d42bf568f943c29eded5ec","source":{"kind":"arxiv","id":"2606.18273","version":1},"attestation_state":"computed","paper":{"title":"Continuous Audio Thinking for Large Audio Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Changho Choi, Dong-Jae Lee, Gyojin Han, Jongsuk Kim, Junmo Kim","submitted_at":"2026-06-05T11:38:30Z","abstract_excerpt":"Large audio language models (LALMs) have shown impressive capabilities on diverse audio understanding tasks, ranging from speech transcription to music analysis. However, because LALMs are typically trained to produce text-aligned responses, their hidden states are progressively shaped for text generation rather than for preserving acoustic information. As a result, the diverse acoustic content that audio carries, such as phonetic detail, prosody, sound events, affect, and pitch, is lost along the way and difficult to leverage in the response. We introduce Continuous Audio Thinking (CoAT), a f"},"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":"2606.18273","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-05T11:38:30Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"9410d125c8f9ba8df7f53db5b6be634405c3226ed46a831d7d39a4a5099dc9ed","abstract_canon_sha256":"b182b2bf867b3f2b0bc7f79ff83c050ae3998e04c0d7088e5cebb1e8be13a988"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:56.672361Z","signature_b64":"6BqYqZalnych500qsjLC9fJO+LMnboGOctfEC2dYSk2ossGVJPVUyUGuCFvM/xr2Vi04l/6/kCFOXKGxmumEDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23097c1a5719d48ec95093c5e3b9bbfecb3d206c14d42bf568f943c29eded5ec","last_reissued_at":"2026-06-19T16:10:56.671990Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:56.671990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continuous Audio Thinking for Large Audio Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Changho Choi, Dong-Jae Lee, Gyojin Han, Jongsuk Kim, Junmo Kim","submitted_at":"2026-06-05T11:38:30Z","abstract_excerpt":"Large audio language models (LALMs) have shown impressive capabilities on diverse audio understanding tasks, ranging from speech transcription to music analysis. However, because LALMs are typically trained to produce text-aligned responses, their hidden states are progressively shaped for text generation rather than for preserving acoustic information. As a result, the diverse acoustic content that audio carries, such as phonetic detail, prosody, sound events, affect, and pitch, is lost along the way and difficult to leverage in the response. We introduce Continuous Audio Thinking (CoAT), a f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18273","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/2606.18273/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":"2606.18273","created_at":"2026-06-19T16:10:56.672051+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18273v1","created_at":"2026-06-19T16:10:56.672051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18273","created_at":"2026-06-19T16:10:56.672051+00:00"},{"alias_kind":"pith_short_12","alias_value":"EMEXYGSXDHKI","created_at":"2026-06-19T16:10:56.672051+00:00"},{"alias_kind":"pith_short_16","alias_value":"EMEXYGSXDHKI5SKQ","created_at":"2026-06-19T16:10:56.672051+00:00"},{"alias_kind":"pith_short_8","alias_value":"EMEXYGSX","created_at":"2026-06-19T16:10:56.672051+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/EMEXYGSXDHKI5SKQSPC6HON373","json":"https://pith.science/pith/EMEXYGSXDHKI5SKQSPC6HON373.json","graph_json":"https://pith.science/api/pith-number/EMEXYGSXDHKI5SKQSPC6HON373/graph.json","events_json":"https://pith.science/api/pith-number/EMEXYGSXDHKI5SKQSPC6HON373/events.json","paper":"https://pith.science/paper/EMEXYGSX"},"agent_actions":{"view_html":"https://pith.science/pith/EMEXYGSXDHKI5SKQSPC6HON373","download_json":"https://pith.science/pith/EMEXYGSXDHKI5SKQSPC6HON373.json","view_paper":"https://pith.science/paper/EMEXYGSX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18273&json=true","fetch_graph":"https://pith.science/api/pith-number/EMEXYGSXDHKI5SKQSPC6HON373/graph.json","fetch_events":"https://pith.science/api/pith-number/EMEXYGSXDHKI5SKQSPC6HON373/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EMEXYGSXDHKI5SKQSPC6HON373/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EMEXYGSXDHKI5SKQSPC6HON373/action/storage_attestation","attest_author":"https://pith.science/pith/EMEXYGSXDHKI5SKQSPC6HON373/action/author_attestation","sign_citation":"https://pith.science/pith/EMEXYGSXDHKI5SKQSPC6HON373/action/citation_signature","submit_replication":"https://pith.science/pith/EMEXYGSXDHKI5SKQSPC6HON373/action/replication_record"}},"created_at":"2026-06-19T16:10:56.672051+00:00","updated_at":"2026-06-19T16:10:56.672051+00:00"}