{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OUWPIWLB77YT63OD6DGQPMUNHD","short_pith_number":"pith:OUWPIWLB","canonical_record":{"source":{"id":"2412.05951","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-08T14:14:30Z","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"title_canon_sha256":"664a696190c8009ffa041c86b5da83571384c9d9067dd1491d4ee44accdc92d6","abstract_canon_sha256":"50a14c6a9a7fba45957b029fa87d07236e33e10fc76a4a00785f8761581f0558"},"schema_version":"1.0"},"canonical_sha256":"752cf45961fff13f6dc3f0cd07b28d38ee95b47b79376e8379c3b5b52ab8c4fc","source":{"kind":"arxiv","id":"2412.05951","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.05951","created_at":"2026-07-05T09:46:12Z"},{"alias_kind":"arxiv_version","alias_value":"2412.05951v1","created_at":"2026-07-05T09:46:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05951","created_at":"2026-07-05T09:46:12Z"},{"alias_kind":"pith_short_12","alias_value":"OUWPIWLB77YT","created_at":"2026-07-05T09:46:12Z"},{"alias_kind":"pith_short_16","alias_value":"OUWPIWLB77YT63OD","created_at":"2026-07-05T09:46:12Z"},{"alias_kind":"pith_short_8","alias_value":"OUWPIWLB","created_at":"2026-07-05T09:46:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OUWPIWLB77YT63OD6DGQPMUNHD","target":"record","payload":{"canonical_record":{"source":{"id":"2412.05951","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-08T14:14:30Z","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"title_canon_sha256":"664a696190c8009ffa041c86b5da83571384c9d9067dd1491d4ee44accdc92d6","abstract_canon_sha256":"50a14c6a9a7fba45957b029fa87d07236e33e10fc76a4a00785f8761581f0558"},"schema_version":"1.0"},"canonical_sha256":"752cf45961fff13f6dc3f0cd07b28d38ee95b47b79376e8379c3b5b52ab8c4fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:12.098947Z","signature_b64":"mSW6cnnQp2LNrSYuqFvgbuY3PdmBHbX/I7PYGQxmMxNZU93MzfIBKZxHs55LzVDa0F7yPYbo6GRdQr2gt6tHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"752cf45961fff13f6dc3f0cd07b28d38ee95b47b79376e8379c3b5b52ab8c4fc","last_reissued_at":"2026-07-05T09:46:12.098589Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:12.098589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.05951","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:46:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E1YMQZMAYxKuysKjgjFbO/alyk7ZtZdiaiC1E9CRz+Qd7oLyUFagcrgPmZ6MNZYMleSf1ympEhKdEG5nILwGAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T06:20:44.425520Z"},"content_sha256":"d4eb9d0e8e7d9b8346598343a8c52ca4844bfed5dd1390174739761bca81ac69","schema_version":"1.0","event_id":"sha256:d4eb9d0e8e7d9b8346598343a8c52ca4844bfed5dd1390174739761bca81ac69"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OUWPIWLB77YT63OD6DGQPMUNHD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When Vision Models Meet Parameter Efficient Look-Aside Adapters Without Large-Scale Audio Pretraining","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jinkwan Jang, Juan Yeo, Kyubyung Chae, Seongkyu Mun, Taesup Kim","submitted_at":"2024-12-08T14:14:30Z","abstract_excerpt":"Recent studies show that pretrained vision models can boost performance in audio downstream tasks. To enhance the performance further, an additional pretraining stage with large scale audio data is typically required to infuse audio specific knowledge into the vision model. However, such approaches require extensive audio data and a carefully designed objective function. In this work, we propose bypassing the pretraining stage by directly fine-tuning the vision model with our Look Aside Adapter (LoAA) designed for efficient audio understanding. Audio spectrum data is represented across two het"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05951","kind":"arxiv","version":1},"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/2412.05951/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":"2026-07-05T09:46:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wWBlpmKX3vsTvP1mrPy6RC+HN4oTjErmqpHQ4erlPvrirPRgHHw9BeG1ZsWoPqyL1X+0S0yMBS98SQswLpJlBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T06:20:44.426202Z"},"content_sha256":"2cbe0b0ee901ff332757358f9138afa0884664802170ea1f0a4e7c83e7e27c05","schema_version":"1.0","event_id":"sha256:2cbe0b0ee901ff332757358f9138afa0884664802170ea1f0a4e7c83e7e27c05"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OUWPIWLB77YT63OD6DGQPMUNHD/bundle.json","state_url":"https://pith.science/pith/OUWPIWLB77YT63OD6DGQPMUNHD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OUWPIWLB77YT63OD6DGQPMUNHD/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":"2026-08-14T06:20:44Z","links":{"resolver":"https://pith.science/pith/OUWPIWLB77YT63OD6DGQPMUNHD","bundle":"https://pith.science/pith/OUWPIWLB77YT63OD6DGQPMUNHD/bundle.json","state":"https://pith.science/pith/OUWPIWLB77YT63OD6DGQPMUNHD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OUWPIWLB77YT63OD6DGQPMUNHD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OUWPIWLB77YT63OD6DGQPMUNHD","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":"50a14c6a9a7fba45957b029fa87d07236e33e10fc76a4a00785f8761581f0558","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-08T14:14:30Z","title_canon_sha256":"664a696190c8009ffa041c86b5da83571384c9d9067dd1491d4ee44accdc92d6"},"schema_version":"1.0","source":{"id":"2412.05951","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.05951","created_at":"2026-07-05T09:46:12Z"},{"alias_kind":"arxiv_version","alias_value":"2412.05951v1","created_at":"2026-07-05T09:46:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05951","created_at":"2026-07-05T09:46:12Z"},{"alias_kind":"pith_short_12","alias_value":"OUWPIWLB77YT","created_at":"2026-07-05T09:46:12Z"},{"alias_kind":"pith_short_16","alias_value":"OUWPIWLB77YT63OD","created_at":"2026-07-05T09:46:12Z"},{"alias_kind":"pith_short_8","alias_value":"OUWPIWLB","created_at":"2026-07-05T09:46:12Z"}],"graph_snapshots":[{"event_id":"sha256:2cbe0b0ee901ff332757358f9138afa0884664802170ea1f0a4e7c83e7e27c05","target":"graph","created_at":"2026-07-05T09:46:12Z","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/2412.05951/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies show that pretrained vision models can boost performance in audio downstream tasks. To enhance the performance further, an additional pretraining stage with large scale audio data is typically required to infuse audio specific knowledge into the vision model. However, such approaches require extensive audio data and a carefully designed objective function. In this work, we propose bypassing the pretraining stage by directly fine-tuning the vision model with our Look Aside Adapter (LoAA) designed for efficient audio understanding. Audio spectrum data is represented across two het","authors_text":"Jinkwan Jang, Juan Yeo, Kyubyung Chae, Seongkyu Mun, Taesup Kim","cross_cats":["cs.CV","cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-08T14:14:30Z","title":"When Vision Models Meet Parameter Efficient Look-Aside Adapters Without Large-Scale Audio Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05951","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:d4eb9d0e8e7d9b8346598343a8c52ca4844bfed5dd1390174739761bca81ac69","target":"record","created_at":"2026-07-05T09:46:12Z","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":"50a14c6a9a7fba45957b029fa87d07236e33e10fc76a4a00785f8761581f0558","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-08T14:14:30Z","title_canon_sha256":"664a696190c8009ffa041c86b5da83571384c9d9067dd1491d4ee44accdc92d6"},"schema_version":"1.0","source":{"id":"2412.05951","kind":"arxiv","version":1}},"canonical_sha256":"752cf45961fff13f6dc3f0cd07b28d38ee95b47b79376e8379c3b5b52ab8c4fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"752cf45961fff13f6dc3f0cd07b28d38ee95b47b79376e8379c3b5b52ab8c4fc","first_computed_at":"2026-07-05T09:46:12.098589Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:46:12.098589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mSW6cnnQp2LNrSYuqFvgbuY3PdmBHbX/I7PYGQxmMxNZU93MzfIBKZxHs55LzVDa0F7yPYbo6GRdQr2gt6tHBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:46:12.098947Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.05951","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4eb9d0e8e7d9b8346598343a8c52ca4844bfed5dd1390174739761bca81ac69","sha256:2cbe0b0ee901ff332757358f9138afa0884664802170ea1f0a4e7c83e7e27c05"],"state_sha256":"392321b28d4740209619f0571fb14f8799d6fcdbef168d94037e59c192f6610f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"od7kq+aq7wIPVgfZmotMuZa9jFv/FGjFR2pvjeXyPGPAQzRrMl54OHz+lSjnOklKuCmt6hmvn+OCUGzz2If0Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T06:20:44.432270Z","bundle_sha256":"14180b701ad703af0731cbfb515bfee376224d6d71fc7b65028a9cb1c6db822a"}}