{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TJ6Q2DYUBNTHYWKFIQJ53HCUWR","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":"7444bc1788410c950270fa14c9b87482fa005660c3613f506af33f2261b88c7e","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-12T14:30:39Z","title_canon_sha256":"9e5e1fcb75171cfea7aafc6616f393645103b63e13383bf2415e2caf29345dad"},"schema_version":"1.0","source":{"id":"2505.07609","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07609","created_at":"2026-07-05T11:01:50Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07609v1","created_at":"2026-07-05T11:01:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07609","created_at":"2026-07-05T11:01:50Z"},{"alias_kind":"pith_short_12","alias_value":"TJ6Q2DYUBNTH","created_at":"2026-07-05T11:01:50Z"},{"alias_kind":"pith_short_16","alias_value":"TJ6Q2DYUBNTHYWKF","created_at":"2026-07-05T11:01:50Z"},{"alias_kind":"pith_short_8","alias_value":"TJ6Q2DYU","created_at":"2026-07-05T11:01:50Z"}],"graph_snapshots":[{"event_id":"sha256:b57071ce6ba790f6595ca8419feb3f976d33cfcf088a1f874cf45c069a40362c","target":"graph","created_at":"2026-07-05T11:01:50Z","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/2505.07609/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning to associate audio with textual descriptions is valuable for a range of tasks, including pretraining, zero-shot classification, audio retrieval, audio captioning, and text-conditioned audio generation. Existing contrastive language-audio pretrained models are typically trained using global, clip-level descriptions, which provide only weak temporal supervision. We hypothesize that CLAP-like language-audio models - particularly, if they are expected to produce frame-level embeddings - can benefit from a stronger temporal supervision. To confirm our hypothesis, we curate a novel dataset ","authors_text":"Florian Schmid, Gerhard Widmer, Paul Primus","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-12T14:30:39Z","title":"TACOS: Temporally-aligned Audio CaptiOnS for Language-Audio Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07609","kind":"arxiv","version":1},"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":"sha256:43b67d0ec941ce02f78f4d368361e1e986773fc5eeec4984ad46e10548d542fe","target":"record","created_at":"2026-07-05T11:01:50Z","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":"7444bc1788410c950270fa14c9b87482fa005660c3613f506af33f2261b88c7e","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-12T14:30:39Z","title_canon_sha256":"9e5e1fcb75171cfea7aafc6616f393645103b63e13383bf2415e2caf29345dad"},"schema_version":"1.0","source":{"id":"2505.07609","kind":"arxiv","version":1}},"canonical_sha256":"9a7d0d0f140b667c59454413dd9c54b46e7ef2cfe24ab3f189b9d42ce6eba737","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a7d0d0f140b667c59454413dd9c54b46e7ef2cfe24ab3f189b9d42ce6eba737","first_computed_at":"2026-07-05T11:01:50.591699Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:50.591699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ix0fIFsU2KEgV06T0A7S41m5qYa8nkjTev5p0Emz77NGStFi39rEaW5unaphZeze/t1ORVGS4mcoi296oPtbBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:50.592265Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.07609","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43b67d0ec941ce02f78f4d368361e1e986773fc5eeec4984ad46e10548d542fe","sha256:b57071ce6ba790f6595ca8419feb3f976d33cfcf088a1f874cf45c069a40362c"],"state_sha256":"95f8d568fff4b0ca0974cc136c8ee38ffadfaeb9c24accf6cce8be0407d3f942"}