{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:V6BSAQE7N6TLEQK6WAB4UTGSIU","short_pith_number":"pith:V6BSAQE7","canonical_record":{"source":{"id":"2105.00335","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-05-01T19:38:30Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","eess.AS"],"title_canon_sha256":"e35ec82931dff9258c67de14d44683d27c8e8fa8dd6a0c49991c5bb877df0f02","abstract_canon_sha256":"0247acd0494331de121a3ed3bf5a03419ad721b43204df9cd9619388c6a7e32c"},"schema_version":"1.0"},"canonical_sha256":"af8320409f6fa6b2415eb003ca4cd24506f9bbe4f13a204447f6d7dbc722dd26","source":{"kind":"arxiv","id":"2105.00335","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.00335","created_at":"2026-07-05T11:01:20Z"},{"alias_kind":"arxiv_version","alias_value":"2105.00335v2","created_at":"2026-07-05T11:01:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.00335","created_at":"2026-07-05T11:01:20Z"},{"alias_kind":"pith_short_12","alias_value":"V6BSAQE7N6TL","created_at":"2026-07-05T11:01:20Z"},{"alias_kind":"pith_short_16","alias_value":"V6BSAQE7N6TLEQK6","created_at":"2026-07-05T11:01:20Z"},{"alias_kind":"pith_short_8","alias_value":"V6BSAQE7","created_at":"2026-07-05T11:01:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:V6BSAQE7N6TLEQK6WAB4UTGSIU","target":"record","payload":{"canonical_record":{"source":{"id":"2105.00335","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-05-01T19:38:30Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","eess.AS"],"title_canon_sha256":"e35ec82931dff9258c67de14d44683d27c8e8fa8dd6a0c49991c5bb877df0f02","abstract_canon_sha256":"0247acd0494331de121a3ed3bf5a03419ad721b43204df9cd9619388c6a7e32c"},"schema_version":"1.0"},"canonical_sha256":"af8320409f6fa6b2415eb003ca4cd24506f9bbe4f13a204447f6d7dbc722dd26","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:20.698410Z","signature_b64":"4hebPWiN1bkMqcgdlYHas8vqEDQazGpvoijvDuIgMIw5R4iNBYeQcQrRs5oIk0PD/MMgRWYEivmoFGg1RI8uBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af8320409f6fa6b2415eb003ca4cd24506f9bbe4f13a204447f6d7dbc722dd26","last_reissued_at":"2026-07-05T11:01:20.697959Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:20.697959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.00335","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":"2026-07-05T11:01:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C1X3+ZUuP7TShkJF8j+DPzA9DfeaeVpBJkdeUsPg2K3IL4FoqfLVI9u43MYTsJ4NTfb7DV7Qjf63QNXJuaZzBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:52:50.775135Z"},"content_sha256":"e31e07d4b053b2d9bd1a409c2a1b65fa43c970b82074de303d76b07e79a7d2e6","schema_version":"1.0","event_id":"sha256:e31e07d4b053b2d9bd1a409c2a1b65fa43c970b82074de303d76b07e79a7d2e6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:V6BSAQE7N6TLEQK6WAB4UTGSIU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Audio Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jonathan Berger, Prateek Verma","submitted_at":"2021-05-01T19:38:30Z","abstract_excerpt":"Over the past two decades, CNN architectures have produced compelling models of sound perception and cognition, learning hierarchical organizations of features. Analogous to successes in computer vision, audio feature classification can be optimized for a particular task of interest, over a wide variety of datasets and labels. In fact similar architectures designed for image understanding have proven effective for acoustic scene analysis. Here we propose applying Transformer based architectures without convolutional layers to raw audio signals. On a standard dataset of Free Sound 50K,comprisin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.00335","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/2105.00335/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":"2026-07-05T11:01:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HbM/gXQ4KAxWkMsAEkcz5N6LzAks9TP4BPJJozeCV/7EoV8lAlOP8lcN2pUxhsYs0OqotOxSX47DNtR5H7mZBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:52:50.775632Z"},"content_sha256":"dcaba524ed570ab02f15f17ab6fbd9beec3040cfdee8dc492c662b9fe2f90a14","schema_version":"1.0","event_id":"sha256:dcaba524ed570ab02f15f17ab6fbd9beec3040cfdee8dc492c662b9fe2f90a14"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V6BSAQE7N6TLEQK6WAB4UTGSIU/bundle.json","state_url":"https://pith.science/pith/V6BSAQE7N6TLEQK6WAB4UTGSIU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V6BSAQE7N6TLEQK6WAB4UTGSIU/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":"2026-08-08T11:52:50Z","links":{"resolver":"https://pith.science/pith/V6BSAQE7N6TLEQK6WAB4UTGSIU","bundle":"https://pith.science/pith/V6BSAQE7N6TLEQK6WAB4UTGSIU/bundle.json","state":"https://pith.science/pith/V6BSAQE7N6TLEQK6WAB4UTGSIU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V6BSAQE7N6TLEQK6WAB4UTGSIU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:V6BSAQE7N6TLEQK6WAB4UTGSIU","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":"0247acd0494331de121a3ed3bf5a03419ad721b43204df9cd9619388c6a7e32c","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-05-01T19:38:30Z","title_canon_sha256":"e35ec82931dff9258c67de14d44683d27c8e8fa8dd6a0c49991c5bb877df0f02"},"schema_version":"1.0","source":{"id":"2105.00335","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.00335","created_at":"2026-07-05T11:01:20Z"},{"alias_kind":"arxiv_version","alias_value":"2105.00335v2","created_at":"2026-07-05T11:01:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.00335","created_at":"2026-07-05T11:01:20Z"},{"alias_kind":"pith_short_12","alias_value":"V6BSAQE7N6TL","created_at":"2026-07-05T11:01:20Z"},{"alias_kind":"pith_short_16","alias_value":"V6BSAQE7N6TLEQK6","created_at":"2026-07-05T11:01:20Z"},{"alias_kind":"pith_short_8","alias_value":"V6BSAQE7","created_at":"2026-07-05T11:01:20Z"}],"graph_snapshots":[{"event_id":"sha256:dcaba524ed570ab02f15f17ab6fbd9beec3040cfdee8dc492c662b9fe2f90a14","target":"graph","created_at":"2026-07-05T11:01:20Z","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/2105.00335/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Over the past two decades, CNN architectures have produced compelling models of sound perception and cognition, learning hierarchical organizations of features. Analogous to successes in computer vision, audio feature classification can be optimized for a particular task of interest, over a wide variety of datasets and labels. In fact similar architectures designed for image understanding have proven effective for acoustic scene analysis. Here we propose applying Transformer based architectures without convolutional layers to raw audio signals. On a standard dataset of Free Sound 50K,comprisin","authors_text":"Jonathan Berger, Prateek Verma","cross_cats":["cs.AI","cs.LG","cs.MM","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-05-01T19:38:30Z","title":"Audio Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.00335","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:e31e07d4b053b2d9bd1a409c2a1b65fa43c970b82074de303d76b07e79a7d2e6","target":"record","created_at":"2026-07-05T11:01:20Z","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":"0247acd0494331de121a3ed3bf5a03419ad721b43204df9cd9619388c6a7e32c","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-05-01T19:38:30Z","title_canon_sha256":"e35ec82931dff9258c67de14d44683d27c8e8fa8dd6a0c49991c5bb877df0f02"},"schema_version":"1.0","source":{"id":"2105.00335","kind":"arxiv","version":2}},"canonical_sha256":"af8320409f6fa6b2415eb003ca4cd24506f9bbe4f13a204447f6d7dbc722dd26","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af8320409f6fa6b2415eb003ca4cd24506f9bbe4f13a204447f6d7dbc722dd26","first_computed_at":"2026-07-05T11:01:20.697959Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:20.697959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4hebPWiN1bkMqcgdlYHas8vqEDQazGpvoijvDuIgMIw5R4iNBYeQcQrRs5oIk0PD/MMgRWYEivmoFGg1RI8uBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:20.698410Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.00335","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e31e07d4b053b2d9bd1a409c2a1b65fa43c970b82074de303d76b07e79a7d2e6","sha256:dcaba524ed570ab02f15f17ab6fbd9beec3040cfdee8dc492c662b9fe2f90a14"],"state_sha256":"d17fe5dfb83027954b055df24b383eeccff5f352ced63e86b3502cd29ddb8035"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zPJvFOfdaCgW+vx+7ENdU5kKQJL9wFP2ZkNv4j8I3SpQTTUX877RanmS2zU4SzGGdEyyesXSXIi16FpbXR1JCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:52:50.779383Z","bundle_sha256":"2cb21d3c4f7a2b7535b56061bde627a801446223461b1dadbf075b8fc1680fbd"}}