{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SADJ7CUAFIRLSIXB2FJF7A4HQD","short_pith_number":"pith:SADJ7CUA","canonical_record":{"source":{"id":"2410.16505","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-21T20:55:33Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"63b70a85a9b18c139068c989086f661685ce4a318f20df51534c972d9c0c84eb","abstract_canon_sha256":"045128d19f9f3d268acfb5d6df7c8325db306a55d0ee8c1b47967cd78a42a3fe"},"schema_version":"1.0"},"canonical_sha256":"90069f8a802a22b922e1d1525f838780e2f31a28039ccf2fec85bb7852020add","source":{"kind":"arxiv","id":"2410.16505","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16505","created_at":"2026-07-05T10:17:12Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16505v2","created_at":"2026-07-05T10:17:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16505","created_at":"2026-07-05T10:17:12Z"},{"alias_kind":"pith_short_12","alias_value":"SADJ7CUAFIRL","created_at":"2026-07-05T10:17:12Z"},{"alias_kind":"pith_short_16","alias_value":"SADJ7CUAFIRLSIXB","created_at":"2026-07-05T10:17:12Z"},{"alias_kind":"pith_short_8","alias_value":"SADJ7CUA","created_at":"2026-07-05T10:17:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SADJ7CUAFIRLSIXB2FJF7A4HQD","target":"record","payload":{"canonical_record":{"source":{"id":"2410.16505","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-21T20:55:33Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"63b70a85a9b18c139068c989086f661685ce4a318f20df51534c972d9c0c84eb","abstract_canon_sha256":"045128d19f9f3d268acfb5d6df7c8325db306a55d0ee8c1b47967cd78a42a3fe"},"schema_version":"1.0"},"canonical_sha256":"90069f8a802a22b922e1d1525f838780e2f31a28039ccf2fec85bb7852020add","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:12.590794Z","signature_b64":"cjLXZQisIrt+LAS3ugbYHOZHTimkWmS45eUr7wq0KWFBKjpvyAGp9T3kZPDwma2/Dvi0JVNjTw6KP4d/tEDlCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90069f8a802a22b922e1d1525f838780e2f31a28039ccf2fec85bb7852020add","last_reissued_at":"2026-07-05T10:17:12.590309Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:12.590309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.16505","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:17:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+JmCb+h2I5Zny3/uNArhPLe3SyiwyDmDw9VfWkZTQN2ikATIlA6Kn0U8tz9mcBwieydqS51jnLwJEBsmpRLXAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T15:13:35.471636Z"},"content_sha256":"97b0ea281efc39456bff2d4fa82278b121cb9a37483f8e8ba9f145946d270d27","schema_version":"1.0","event_id":"sha256:97b0ea281efc39456bff2d4fa82278b121cb9a37483f8e8ba9f145946d270d27"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SADJ7CUAFIRLSIXB2FJF7A4HQD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do Audio-Language Models Understand Linguistic Variations?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ashish Seth, Dinesh Manocha, Hemant Kumar Giri, Nishit Anand, Ramaneswaran Selvakumar, Sonal Kumar, Sreyan Ghosh","submitted_at":"2024-10-21T20:55:33Z","abstract_excerpt":"Open-vocabulary audio language models (ALMs), like Contrastive Language Audio Pretraining (CLAP), represent a promising new paradigm for audio-text retrieval using natural language queries. In this paper, for the first time, we perform controlled experiments on various benchmarks to show that existing ALMs struggle to generalize to linguistic variations in textual queries. To address this issue, we propose RobustCLAP, a novel and compute-efficient technique to learn audio-language representations agnostic to linguistic variations. Specifically, we reformulate the contrastive loss used in CLAP "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16505","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/2410.16505/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:17:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3l4V2Fpdkhhv373HyckhVPqgZJlMT1rsRCsAoFOdshFl8HzdQ5LZ9gI1r9kfXsqE7WM1uFpd+Amk9OdB6aaqAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T15:13:35.472997Z"},"content_sha256":"6903a51504d6ad7b3f82f7bdad176bbf2b80b2ab2d1cd0b157d0785781294a52","schema_version":"1.0","event_id":"sha256:6903a51504d6ad7b3f82f7bdad176bbf2b80b2ab2d1cd0b157d0785781294a52"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SADJ7CUAFIRLSIXB2FJF7A4HQD/bundle.json","state_url":"https://pith.science/pith/SADJ7CUAFIRLSIXB2FJF7A4HQD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SADJ7CUAFIRLSIXB2FJF7A4HQD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-19T15:13:35Z","links":{"resolver":"https://pith.science/pith/SADJ7CUAFIRLSIXB2FJF7A4HQD","bundle":"https://pith.science/pith/SADJ7CUAFIRLSIXB2FJF7A4HQD/bundle.json","state":"https://pith.science/pith/SADJ7CUAFIRLSIXB2FJF7A4HQD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SADJ7CUAFIRLSIXB2FJF7A4HQD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SADJ7CUAFIRLSIXB2FJF7A4HQD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"045128d19f9f3d268acfb5d6df7c8325db306a55d0ee8c1b47967cd78a42a3fe","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-21T20:55:33Z","title_canon_sha256":"63b70a85a9b18c139068c989086f661685ce4a318f20df51534c972d9c0c84eb"},"schema_version":"1.0","source":{"id":"2410.16505","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16505","created_at":"2026-07-05T10:17:12Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16505v2","created_at":"2026-07-05T10:17:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16505","created_at":"2026-07-05T10:17:12Z"},{"alias_kind":"pith_short_12","alias_value":"SADJ7CUAFIRL","created_at":"2026-07-05T10:17:12Z"},{"alias_kind":"pith_short_16","alias_value":"SADJ7CUAFIRLSIXB","created_at":"2026-07-05T10:17:12Z"},{"alias_kind":"pith_short_8","alias_value":"SADJ7CUA","created_at":"2026-07-05T10:17:12Z"}],"graph_snapshots":[{"event_id":"sha256:6903a51504d6ad7b3f82f7bdad176bbf2b80b2ab2d1cd0b157d0785781294a52","target":"graph","created_at":"2026-07-05T10:17:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.16505/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open-vocabulary audio language models (ALMs), like Contrastive Language Audio Pretraining (CLAP), represent a promising new paradigm for audio-text retrieval using natural language queries. In this paper, for the first time, we perform controlled experiments on various benchmarks to show that existing ALMs struggle to generalize to linguistic variations in textual queries. To address this issue, we propose RobustCLAP, a novel and compute-efficient technique to learn audio-language representations agnostic to linguistic variations. Specifically, we reformulate the contrastive loss used in CLAP ","authors_text":"Ashish Seth, Dinesh Manocha, Hemant Kumar Giri, Nishit Anand, Ramaneswaran Selvakumar, Sonal Kumar, Sreyan Ghosh","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-21T20:55:33Z","title":"Do Audio-Language Models Understand Linguistic Variations?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16505","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:97b0ea281efc39456bff2d4fa82278b121cb9a37483f8e8ba9f145946d270d27","target":"record","created_at":"2026-07-05T10:17:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"045128d19f9f3d268acfb5d6df7c8325db306a55d0ee8c1b47967cd78a42a3fe","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-21T20:55:33Z","title_canon_sha256":"63b70a85a9b18c139068c989086f661685ce4a318f20df51534c972d9c0c84eb"},"schema_version":"1.0","source":{"id":"2410.16505","kind":"arxiv","version":2}},"canonical_sha256":"90069f8a802a22b922e1d1525f838780e2f31a28039ccf2fec85bb7852020add","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90069f8a802a22b922e1d1525f838780e2f31a28039ccf2fec85bb7852020add","first_computed_at":"2026-07-05T10:17:12.590309Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:12.590309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cjLXZQisIrt+LAS3ugbYHOZHTimkWmS45eUr7wq0KWFBKjpvyAGp9T3kZPDwma2/Dvi0JVNjTw6KP4d/tEDlCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:12.590794Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.16505","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97b0ea281efc39456bff2d4fa82278b121cb9a37483f8e8ba9f145946d270d27","sha256:6903a51504d6ad7b3f82f7bdad176bbf2b80b2ab2d1cd0b157d0785781294a52"],"state_sha256":"10fa501bd34ff519b86e23406c0ceb990bc2423a657760e91e62cf105b0c4cd3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r50siNWC37Lz+O8TJAveQHKyj2RYRQNt3tNu821QiY3JUsZA/25rdlbyXL6QNvWAveL6U/hEnE9vP+GB6E+2Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T15:13:35.481126Z","bundle_sha256":"21b374e546959787cbbd0d43bdf695070ea58dfd364f30f14545dea986afab95"}}