{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GEW2PGJTQRCWRSHEMZPV75BDOM","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":"4d27993b800fd1646807712c381144db75c3c13d2cf5b5383890f9e239f2273f","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-09-18T06:38:48Z","title_canon_sha256":"93145486d00cf5bb25f3c434dee02441ccef1c447a4c7a55bc5ab10b710a4385"},"schema_version":"1.0","source":{"id":"2409.11729","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.11729","created_at":"2026-07-05T09:08:36Z"},{"alias_kind":"arxiv_version","alias_value":"2409.11729v1","created_at":"2026-07-05T09:08:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11729","created_at":"2026-07-05T09:08:36Z"},{"alias_kind":"pith_short_12","alias_value":"GEW2PGJTQRCW","created_at":"2026-07-05T09:08:36Z"},{"alias_kind":"pith_short_16","alias_value":"GEW2PGJTQRCWRSHE","created_at":"2026-07-05T09:08:36Z"},{"alias_kind":"pith_short_8","alias_value":"GEW2PGJT","created_at":"2026-07-05T09:08:36Z"}],"graph_snapshots":[{"event_id":"sha256:26b7a19f004ecb42420aeff853e6d6bc5c30088679b366af78c8229a011f9a35","target":"graph","created_at":"2026-07-05T09:08:36Z","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/2409.11729/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current audio-visual representation learning can capture rough object categories (e.g., ``animals'' and ``instruments''), but it lacks the ability to recognize fine-grained details, such as specific categories like ``dogs'' and ``flutes'' within animals and instruments. To address this issue, we introduce DETECLAP, a method to enhance audio-visual representation learning with object information. Our key idea is to introduce an audio-visual label prediction loss to the existing Contrastive Audio-Visual Masked AutoEncoder to enhance its object awareness. To avoid costly manual annotations, we pr","authors_text":"Hokuto Munakata, Masayoshi Kondo, Shota Nakada, Taichi Nishimura, Tatsuya Komatsu","cross_cats":["cs.CV","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-09-18T06:38:48Z","title":"DETECLAP: Enhancing Audio-Visual Representation Learning with Object Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11729","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:dbf53976845c260fbda1b517ddca8ac7b5ce8b3190d57009c0ff03812956e3ed","target":"record","created_at":"2026-07-05T09:08:36Z","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":"4d27993b800fd1646807712c381144db75c3c13d2cf5b5383890f9e239f2273f","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-09-18T06:38:48Z","title_canon_sha256":"93145486d00cf5bb25f3c434dee02441ccef1c447a4c7a55bc5ab10b710a4385"},"schema_version":"1.0","source":{"id":"2409.11729","kind":"arxiv","version":1}},"canonical_sha256":"312da79933844568c8e4665f5ff4237327a278402f6400f4458665a8db97e02b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"312da79933844568c8e4665f5ff4237327a278402f6400f4458665a8db97e02b","first_computed_at":"2026-07-05T09:08:36.733863Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:08:36.733863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rW30akGp7fepbsr89R0qDAgseNaHIP3OjVPzDrJpIDt42Q44S14qzkPp0UBbOcnWx+LZHCp/KbVxKf2xlJJQCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:08:36.734373Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.11729","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbf53976845c260fbda1b517ddca8ac7b5ce8b3190d57009c0ff03812956e3ed","sha256:26b7a19f004ecb42420aeff853e6d6bc5c30088679b366af78c8229a011f9a35"],"state_sha256":"5b7d91244d0253cb4bd9e811e972516a9ca38d97d11b1652f94a28dcd591e4b6"}