{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZREWQPRXZO7OZUHJPXDYIVHAAD","short_pith_number":"pith:ZREWQPRX","schema_version":"1.0","canonical_sha256":"cc49683e37cbbeecd0e97dc78454e000f3b3925c0a7bb0a49c226ed13fd0a610","source":{"kind":"arxiv","id":"2607.10387","version":1},"attestation_state":"computed","paper":{"title":"GigaChat Audio: Time-aware Large Audio Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Aleksandr Kutsakov, Alexandr Maximenko, Fyodor Minkin, Georgii Gospodinov, Mariia Sadovina, Oleg Kutuzov, Pavel Bogomolov","submitted_at":"2026-07-11T16:34:25Z","abstract_excerpt":"Temporal grounding in long recordings remains challenging for audio-conditioned LLMs. We present a time-aware audio LLM that answers questions with explicit timestamps over up to 120 minutes of input. Our approach interleaves periodic time markers with continuous audio tokens using large-scale synthetic supervision from a cascaded pipeline. Our model achieves strong temporal-grounding accuracy on short and long benchmarks and supports time-anchored fragment descriptions and summaries. Extensive ablations examine how time representation, marker frequency, tokenization, and duration-mixture desi"},"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":"2607.10387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-07-11T16:34:25Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"fd6874c91cff3aee42ba6e75936818e077b7b5bb5a5db6681a8074274cbcfb77","abstract_canon_sha256":"8ab448102717d57fceafc8277e5614a8104a8ceb2151b31d95870dd4a59d7d3b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:21:13.539843Z","signature_b64":"SltQgfT7lUp76HAoO2fvWzBNZiUT446ZXI+uZ2fZOwyb3fr12GrcidZlIarZwDUFtGWzpGJ6xWUBF9u5NKL+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc49683e37cbbeecd0e97dc78454e000f3b3925c0a7bb0a49c226ed13fd0a610","last_reissued_at":"2026-07-14T01:21:13.538997Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:21:13.538997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GigaChat Audio: Time-aware Large Audio Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Aleksandr Kutsakov, Alexandr Maximenko, Fyodor Minkin, Georgii Gospodinov, Mariia Sadovina, Oleg Kutuzov, Pavel Bogomolov","submitted_at":"2026-07-11T16:34:25Z","abstract_excerpt":"Temporal grounding in long recordings remains challenging for audio-conditioned LLMs. We present a time-aware audio LLM that answers questions with explicit timestamps over up to 120 minutes of input. Our approach interleaves periodic time markers with continuous audio tokens using large-scale synthetic supervision from a cascaded pipeline. Our model achieves strong temporal-grounding accuracy on short and long benchmarks and supports time-anchored fragment descriptions and summaries. Extensive ablations examine how time representation, marker frequency, tokenization, and duration-mixture desi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10387","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/2607.10387/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":"2607.10387","created_at":"2026-07-14T01:21:13.539441+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.10387v1","created_at":"2026-07-14T01:21:13.539441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10387","created_at":"2026-07-14T01:21:13.539441+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZREWQPRXZO7O","created_at":"2026-07-14T01:21:13.539441+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZREWQPRXZO7OZUHJ","created_at":"2026-07-14T01:21:13.539441+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZREWQPRX","created_at":"2026-07-14T01:21:13.539441+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/ZREWQPRXZO7OZUHJPXDYIVHAAD","json":"https://pith.science/pith/ZREWQPRXZO7OZUHJPXDYIVHAAD.json","graph_json":"https://pith.science/api/pith-number/ZREWQPRXZO7OZUHJPXDYIVHAAD/graph.json","events_json":"https://pith.science/api/pith-number/ZREWQPRXZO7OZUHJPXDYIVHAAD/events.json","paper":"https://pith.science/paper/ZREWQPRX"},"agent_actions":{"view_html":"https://pith.science/pith/ZREWQPRXZO7OZUHJPXDYIVHAAD","download_json":"https://pith.science/pith/ZREWQPRXZO7OZUHJPXDYIVHAAD.json","view_paper":"https://pith.science/paper/ZREWQPRX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.10387&json=true","fetch_graph":"https://pith.science/api/pith-number/ZREWQPRXZO7OZUHJPXDYIVHAAD/graph.json","fetch_events":"https://pith.science/api/pith-number/ZREWQPRXZO7OZUHJPXDYIVHAAD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZREWQPRXZO7OZUHJPXDYIVHAAD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZREWQPRXZO7OZUHJPXDYIVHAAD/action/storage_attestation","attest_author":"https://pith.science/pith/ZREWQPRXZO7OZUHJPXDYIVHAAD/action/author_attestation","sign_citation":"https://pith.science/pith/ZREWQPRXZO7OZUHJPXDYIVHAAD/action/citation_signature","submit_replication":"https://pith.science/pith/ZREWQPRXZO7OZUHJPXDYIVHAAD/action/replication_record"}},"created_at":"2026-07-14T01:21:13.539441+00:00","updated_at":"2026-07-14T01:21:13.539441+00:00"}