{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VVYXRIY2NUCXUTPCQ7ME5RRVGU","short_pith_number":"pith:VVYXRIY2","schema_version":"1.0","canonical_sha256":"ad7178a31a6d057a4de287d84ec635353dece56bb7ad6f110d479a2c4099ceff","source":{"kind":"arxiv","id":"2310.08753","version":4},"attestation_state":"computed","paper":{"title":"CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ashish Seth, Chandra Kiran Evuru, Dinesh Manocha, Oriol Nieto, Ramani Duraiswami, Sonal Kumar, S. Ramaneswaran, Sreyan Ghosh, S. Sakshi, Utkarsh Tyagi","submitted_at":"2023-10-12T22:43:38Z","abstract_excerpt":"A fundamental characteristic of audio is its compositional nature. Audio-language models (ALMs) trained using a contrastive approach (e.g., CLAP) that learns a shared representation between audio and language modalities have improved performance in many downstream applications, including zero-shot audio classification, audio retrieval, etc. However, the ability of these models to effectively perform compositional reasoning remains largely unexplored and necessitates additional research. In this paper, we propose CompA, a collection of two expert-annotated benchmarks with a majority of real-wor"},"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":"2310.08753","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-10-12T22:43:38Z","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"title_canon_sha256":"e534c66879c583335c80871090cf779fa7e5acf811f6d9da21d0e69b90824756","abstract_canon_sha256":"46d8e57caeca17fdb5074b8280fe8063968f33f348ac85abe2a0f10dae789433"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:25.059190Z","signature_b64":"4dirKDsrip7gwkHKJPpQ7rLSBokH3N34c97NaL3QCMleEYarElUVTwp5ff6MLlMvEd+YfqWXrxVu7CkEdrCXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad7178a31a6d057a4de287d84ec635353dece56bb7ad6f110d479a2c4099ceff","last_reissued_at":"2026-07-05T08:50:25.058754Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:25.058754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ashish Seth, Chandra Kiran Evuru, Dinesh Manocha, Oriol Nieto, Ramani Duraiswami, Sonal Kumar, S. Ramaneswaran, Sreyan Ghosh, S. Sakshi, Utkarsh Tyagi","submitted_at":"2023-10-12T22:43:38Z","abstract_excerpt":"A fundamental characteristic of audio is its compositional nature. Audio-language models (ALMs) trained using a contrastive approach (e.g., CLAP) that learns a shared representation between audio and language modalities have improved performance in many downstream applications, including zero-shot audio classification, audio retrieval, etc. However, the ability of these models to effectively perform compositional reasoning remains largely unexplored and necessitates additional research. In this paper, we propose CompA, a collection of two expert-annotated benchmarks with a majority of real-wor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08753","kind":"arxiv","version":4},"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/2310.08753/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":"2310.08753","created_at":"2026-07-05T08:50:25.058819+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.08753v4","created_at":"2026-07-05T08:50:25.058819+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08753","created_at":"2026-07-05T08:50:25.058819+00:00"},{"alias_kind":"pith_short_12","alias_value":"VVYXRIY2NUCX","created_at":"2026-07-05T08:50:25.058819+00:00"},{"alias_kind":"pith_short_16","alias_value":"VVYXRIY2NUCXUTPC","created_at":"2026-07-05T08:50:25.058819+00:00"},{"alias_kind":"pith_short_8","alias_value":"VVYXRIY2","created_at":"2026-07-05T08:50:25.058819+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25391","citing_title":"From Sounds to Scenes: A Benchmark for Evaluating Context-Aware Auditory Scene Understanding in Large Audio Language Models","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00247","citing_title":"Adaptive Perturbation Selection for Contrastive Audio Decoding","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VVYXRIY2NUCXUTPCQ7ME5RRVGU","json":"https://pith.science/pith/VVYXRIY2NUCXUTPCQ7ME5RRVGU.json","graph_json":"https://pith.science/api/pith-number/VVYXRIY2NUCXUTPCQ7ME5RRVGU/graph.json","events_json":"https://pith.science/api/pith-number/VVYXRIY2NUCXUTPCQ7ME5RRVGU/events.json","paper":"https://pith.science/paper/VVYXRIY2"},"agent_actions":{"view_html":"https://pith.science/pith/VVYXRIY2NUCXUTPCQ7ME5RRVGU","download_json":"https://pith.science/pith/VVYXRIY2NUCXUTPCQ7ME5RRVGU.json","view_paper":"https://pith.science/paper/VVYXRIY2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.08753&json=true","fetch_graph":"https://pith.science/api/pith-number/VVYXRIY2NUCXUTPCQ7ME5RRVGU/graph.json","fetch_events":"https://pith.science/api/pith-number/VVYXRIY2NUCXUTPCQ7ME5RRVGU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VVYXRIY2NUCXUTPCQ7ME5RRVGU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VVYXRIY2NUCXUTPCQ7ME5RRVGU/action/storage_attestation","attest_author":"https://pith.science/pith/VVYXRIY2NUCXUTPCQ7ME5RRVGU/action/author_attestation","sign_citation":"https://pith.science/pith/VVYXRIY2NUCXUTPCQ7ME5RRVGU/action/citation_signature","submit_replication":"https://pith.science/pith/VVYXRIY2NUCXUTPCQ7ME5RRVGU/action/replication_record"}},"created_at":"2026-07-05T08:50:25.058819+00:00","updated_at":"2026-07-05T08:50:25.058819+00:00"}