{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Z6QLZN2ZMMJSXIW63JMHQ7A5RH","short_pith_number":"pith:Z6QLZN2Z","schema_version":"1.0","canonical_sha256":"cfa0bcb75963132ba2deda58787c1d89f647d803df0b28b04af31f4920431bbe","source":{"kind":"arxiv","id":"2505.05335","version":2},"attestation_state":"computed","paper":{"title":"FLAM: Frame-Wise Language-Audio Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Aaron Courville, Cheng-Zhi Anna Huang, Christos Tsirigotis, Justin Salamon, Ke Chen, Oriol Nieto, Prem Seetharaman, Yusong Wu","submitted_at":"2025-05-08T15:27:43Z","abstract_excerpt":"Recent multi-modal audio-language models (ALMs) excel at text-audio retrieval but struggle with frame-wise audio understanding. Prior works use temporal-aware labels or unsupervised training to improve frame-wise capabilities, but they still lack fine-grained labeling capability to pinpoint when an event occurs. While traditional sound event detection models can precisely localize events, they are limited to pre-defined categories, making them ineffective for real-world scenarios with out-of-distribution events. In this work, we introduce FLAM, an open-vocabulary contrastive audio-language mod"},"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":"2505.05335","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-08T15:27:43Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"5e13722af23f9d276cf14e41859cb498ccbae34e2021f568b768f93cecd5c6e5","abstract_canon_sha256":"561d6fdd5f8a990afa9f641d4f828461e73813c0fb371c107a925556331d99d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:45.303610Z","signature_b64":"lQKmV96I1zTUZJJ5okrsuLtoMRAR+mcqb0UuXjdZKWjD9LO9QN4w/vRVzw3OAUxA/cV/ohS9hYIadBV7Ft6yCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfa0bcb75963132ba2deda58787c1d89f647d803df0b28b04af31f4920431bbe","last_reissued_at":"2026-07-05T11:17:45.303062Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:45.303062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FLAM: Frame-Wise Language-Audio Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Aaron Courville, Cheng-Zhi Anna Huang, Christos Tsirigotis, Justin Salamon, Ke Chen, Oriol Nieto, Prem Seetharaman, Yusong Wu","submitted_at":"2025-05-08T15:27:43Z","abstract_excerpt":"Recent multi-modal audio-language models (ALMs) excel at text-audio retrieval but struggle with frame-wise audio understanding. Prior works use temporal-aware labels or unsupervised training to improve frame-wise capabilities, but they still lack fine-grained labeling capability to pinpoint when an event occurs. While traditional sound event detection models can precisely localize events, they are limited to pre-defined categories, making them ineffective for real-world scenarios with out-of-distribution events. In this work, we introduce FLAM, an open-vocabulary contrastive audio-language mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05335","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/2505.05335/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":"2505.05335","created_at":"2026-07-05T11:17:45.303120+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.05335v2","created_at":"2026-07-05T11:17:45.303120+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05335","created_at":"2026-07-05T11:17:45.303120+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z6QLZN2ZMMJS","created_at":"2026-07-05T11:17:45.303120+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z6QLZN2ZMMJSXIW6","created_at":"2026-07-05T11:17:45.303120+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z6QLZN2Z","created_at":"2026-07-05T11:17:45.303120+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.07829","citing_title":"Auditory Intelligence: Understanding the World Through Sound","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z6QLZN2ZMMJSXIW63JMHQ7A5RH","json":"https://pith.science/pith/Z6QLZN2ZMMJSXIW63JMHQ7A5RH.json","graph_json":"https://pith.science/api/pith-number/Z6QLZN2ZMMJSXIW63JMHQ7A5RH/graph.json","events_json":"https://pith.science/api/pith-number/Z6QLZN2ZMMJSXIW63JMHQ7A5RH/events.json","paper":"https://pith.science/paper/Z6QLZN2Z"},"agent_actions":{"view_html":"https://pith.science/pith/Z6QLZN2ZMMJSXIW63JMHQ7A5RH","download_json":"https://pith.science/pith/Z6QLZN2ZMMJSXIW63JMHQ7A5RH.json","view_paper":"https://pith.science/paper/Z6QLZN2Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.05335&json=true","fetch_graph":"https://pith.science/api/pith-number/Z6QLZN2ZMMJSXIW63JMHQ7A5RH/graph.json","fetch_events":"https://pith.science/api/pith-number/Z6QLZN2ZMMJSXIW63JMHQ7A5RH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z6QLZN2ZMMJSXIW63JMHQ7A5RH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z6QLZN2ZMMJSXIW63JMHQ7A5RH/action/storage_attestation","attest_author":"https://pith.science/pith/Z6QLZN2ZMMJSXIW63JMHQ7A5RH/action/author_attestation","sign_citation":"https://pith.science/pith/Z6QLZN2ZMMJSXIW63JMHQ7A5RH/action/citation_signature","submit_replication":"https://pith.science/pith/Z6QLZN2ZMMJSXIW63JMHQ7A5RH/action/replication_record"}},"created_at":"2026-07-05T11:17:45.303120+00:00","updated_at":"2026-07-05T11:17:45.303120+00:00"}