{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6MFPXYHPD3OBM7CWYI6VIK5G5K","short_pith_number":"pith:6MFPXYHP","canonical_record":{"source":{"id":"2406.04930","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-07T13:35:44Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"37360c3d41d39e8d3d0b67b5dd1181859efb291b6f7d7707e97696b7b0e6a46a","abstract_canon_sha256":"b3821765e3c8a1eaf3f5136860b72a1995d03be70790a78e9c7eb375fcd5096b"},"schema_version":"1.0"},"canonical_sha256":"f30afbe0ef1edc167c56c23d542ba6ea9eb2ce258277455fa94b848f4ee29563","source":{"kind":"arxiv","id":"2406.04930","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04930","created_at":"2026-07-05T08:28:51Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04930v1","created_at":"2026-07-05T08:28:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04930","created_at":"2026-07-05T08:28:51Z"},{"alias_kind":"pith_short_12","alias_value":"6MFPXYHPD3OB","created_at":"2026-07-05T08:28:51Z"},{"alias_kind":"pith_short_16","alias_value":"6MFPXYHPD3OBM7CW","created_at":"2026-07-05T08:28:51Z"},{"alias_kind":"pith_short_8","alias_value":"6MFPXYHP","created_at":"2026-07-05T08:28:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6MFPXYHPD3OBM7CWYI6VIK5G5K","target":"record","payload":{"canonical_record":{"source":{"id":"2406.04930","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-07T13:35:44Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"37360c3d41d39e8d3d0b67b5dd1181859efb291b6f7d7707e97696b7b0e6a46a","abstract_canon_sha256":"b3821765e3c8a1eaf3f5136860b72a1995d03be70790a78e9c7eb375fcd5096b"},"schema_version":"1.0"},"canonical_sha256":"f30afbe0ef1edc167c56c23d542ba6ea9eb2ce258277455fa94b848f4ee29563","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:51.004396Z","signature_b64":"gnZ3iOvtCYRlPsaj8UHglCYN1xKkwH6rLkna0WVmk79vGpHnOtnzscSH2BWAq4MDPHTZsCfILsMXDG0kJrksAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f30afbe0ef1edc167c56c23d542ba6ea9eb2ce258277455fa94b848f4ee29563","last_reissued_at":"2026-07-05T08:28:51.003958Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:51.003958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.04930","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":"2026-07-05T08:28:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ijH1I0CUl5NFsFCWAq2VYlj12v5J/RlUI7c/CZFvWar6N7ZFWzjWof2SuK6JLFXXRvRHlWAVj8fzQTDpvG3sCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:50:09.079544Z"},"content_sha256":"61d86325838d66aaa8a14a642dfdebe0a7c352684a7d6ebc0520888640ad7e6c","schema_version":"1.0","event_id":"sha256:61d86325838d66aaa8a14a642dfdebe0a7c352684a7d6ebc0520888640ad7e6c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6MFPXYHPD3OBM7CWYI6VIK5G5K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MA-AVT: Modality Alignment for Parameter-Efficient Audio-Visual Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Diana Marculescu, Shentong Mo, Tanvir Mahmud, Yapeng Tian","submitted_at":"2024-06-07T13:35:44Z","abstract_excerpt":"Recent advances in pre-trained vision transformers have shown promise in parameter-efficient audio-visual learning without audio pre-training. However, few studies have investigated effective methods for aligning multimodal features in parameter-efficient audio-visual transformers. In this paper, we propose MA-AVT, a new parameter-efficient audio-visual transformer employing deep modality alignment for corresponding multimodal semantic features. Specifically, we introduce joint unimodal and multimodal token learning for aligning the two modalities with a frozen modality-shared transformer. Thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04930","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/2406.04930/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":"2026-07-05T08:28:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y6L8Mtolahic80n5eUV0XQ9uK7/E/JrXTaTZpCnNEuDSE7An/3gya0FPvGaXqZJsmA0qdMhyA9TzeH/FkfpdDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:50:09.080424Z"},"content_sha256":"f40c3fbab4a36e6933df8e56eeb1f1691492621481887d530ea11f86af5b6916","schema_version":"1.0","event_id":"sha256:f40c3fbab4a36e6933df8e56eeb1f1691492621481887d530ea11f86af5b6916"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6MFPXYHPD3OBM7CWYI6VIK5G5K/bundle.json","state_url":"https://pith.science/pith/6MFPXYHPD3OBM7CWYI6VIK5G5K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6MFPXYHPD3OBM7CWYI6VIK5G5K/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":"2026-08-07T16:50:09Z","links":{"resolver":"https://pith.science/pith/6MFPXYHPD3OBM7CWYI6VIK5G5K","bundle":"https://pith.science/pith/6MFPXYHPD3OBM7CWYI6VIK5G5K/bundle.json","state":"https://pith.science/pith/6MFPXYHPD3OBM7CWYI6VIK5G5K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6MFPXYHPD3OBM7CWYI6VIK5G5K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6MFPXYHPD3OBM7CWYI6VIK5G5K","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":"b3821765e3c8a1eaf3f5136860b72a1995d03be70790a78e9c7eb375fcd5096b","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-07T13:35:44Z","title_canon_sha256":"37360c3d41d39e8d3d0b67b5dd1181859efb291b6f7d7707e97696b7b0e6a46a"},"schema_version":"1.0","source":{"id":"2406.04930","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04930","created_at":"2026-07-05T08:28:51Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04930v1","created_at":"2026-07-05T08:28:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04930","created_at":"2026-07-05T08:28:51Z"},{"alias_kind":"pith_short_12","alias_value":"6MFPXYHPD3OB","created_at":"2026-07-05T08:28:51Z"},{"alias_kind":"pith_short_16","alias_value":"6MFPXYHPD3OBM7CW","created_at":"2026-07-05T08:28:51Z"},{"alias_kind":"pith_short_8","alias_value":"6MFPXYHP","created_at":"2026-07-05T08:28:51Z"}],"graph_snapshots":[{"event_id":"sha256:f40c3fbab4a36e6933df8e56eeb1f1691492621481887d530ea11f86af5b6916","target":"graph","created_at":"2026-07-05T08:28:51Z","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/2406.04930/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in pre-trained vision transformers have shown promise in parameter-efficient audio-visual learning without audio pre-training. However, few studies have investigated effective methods for aligning multimodal features in parameter-efficient audio-visual transformers. In this paper, we propose MA-AVT, a new parameter-efficient audio-visual transformer employing deep modality alignment for corresponding multimodal semantic features. Specifically, we introduce joint unimodal and multimodal token learning for aligning the two modalities with a frozen modality-shared transformer. Thi","authors_text":"Diana Marculescu, Shentong Mo, Tanvir Mahmud, Yapeng Tian","cross_cats":["cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-07T13:35:44Z","title":"MA-AVT: Modality Alignment for Parameter-Efficient Audio-Visual Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04930","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":"sha256:61d86325838d66aaa8a14a642dfdebe0a7c352684a7d6ebc0520888640ad7e6c","target":"record","created_at":"2026-07-05T08:28:51Z","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":"b3821765e3c8a1eaf3f5136860b72a1995d03be70790a78e9c7eb375fcd5096b","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-07T13:35:44Z","title_canon_sha256":"37360c3d41d39e8d3d0b67b5dd1181859efb291b6f7d7707e97696b7b0e6a46a"},"schema_version":"1.0","source":{"id":"2406.04930","kind":"arxiv","version":1}},"canonical_sha256":"f30afbe0ef1edc167c56c23d542ba6ea9eb2ce258277455fa94b848f4ee29563","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f30afbe0ef1edc167c56c23d542ba6ea9eb2ce258277455fa94b848f4ee29563","first_computed_at":"2026-07-05T08:28:51.003958Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:51.003958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gnZ3iOvtCYRlPsaj8UHglCYN1xKkwH6rLkna0WVmk79vGpHnOtnzscSH2BWAq4MDPHTZsCfILsMXDG0kJrksAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:51.004396Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.04930","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61d86325838d66aaa8a14a642dfdebe0a7c352684a7d6ebc0520888640ad7e6c","sha256:f40c3fbab4a36e6933df8e56eeb1f1691492621481887d530ea11f86af5b6916"],"state_sha256":"9a2fa949b8c77db5443340e42ec0a77f8228e3491dd2ec0349c019fe631ef452"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5LaClN/cs85VcBR9G4NHnz586/O1t27ht/y4MxUrDfe8yOvrcuLy8hlH2TA+8ZcxCb89D7CL/toV/NYF2I9eAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T16:50:09.086034Z","bundle_sha256":"0e1c67f2484960740a0c03447f6f3817e6da6598a2d6f7ecf403e341af3fc369"}}