{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:XV7NMD2OO6XQQ5GJ25TMXYHS3Q","short_pith_number":"pith:XV7NMD2O","canonical_record":{"source":{"id":"2211.01223","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-11-02T16:02:45Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"fe6241eef79c6a9d2d8dce9b1933bb59134f3f5d0e3d39a701ed148258988db1","abstract_canon_sha256":"3cf43441a4bcb8d7dac32d8f4fde6725b571afa4ef374cb317906aea039f73cd"},"schema_version":"1.0"},"canonical_sha256":"bd7ed60f4e77af0874c9d766cbe0f2dc15607b41f6d657e73715f10a843628d5","source":{"kind":"arxiv","id":"2211.01223","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.01223","created_at":"2026-07-05T05:13:10Z"},{"alias_kind":"arxiv_version","alias_value":"2211.01223v2","created_at":"2026-07-05T05:13:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.01223","created_at":"2026-07-05T05:13:10Z"},{"alias_kind":"pith_short_12","alias_value":"XV7NMD2OO6XQ","created_at":"2026-07-05T05:13:10Z"},{"alias_kind":"pith_short_16","alias_value":"XV7NMD2OO6XQQ5GJ","created_at":"2026-07-05T05:13:10Z"},{"alias_kind":"pith_short_8","alias_value":"XV7NMD2O","created_at":"2026-07-05T05:13:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:XV7NMD2OO6XQQ5GJ25TMXYHS3Q","target":"record","payload":{"canonical_record":{"source":{"id":"2211.01223","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-11-02T16:02:45Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"fe6241eef79c6a9d2d8dce9b1933bb59134f3f5d0e3d39a701ed148258988db1","abstract_canon_sha256":"3cf43441a4bcb8d7dac32d8f4fde6725b571afa4ef374cb317906aea039f73cd"},"schema_version":"1.0"},"canonical_sha256":"bd7ed60f4e77af0874c9d766cbe0f2dc15607b41f6d657e73715f10a843628d5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:10.918694Z","signature_b64":"uRx01VOmLEAxHjvYnTqyUq4jmA8N7ZsiMWJ10a/aZypFlnrIe+CAfcws2MvUrNi3dwNtgNxJLtl3n89rdvG8Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd7ed60f4e77af0874c9d766cbe0f2dc15607b41f6d657e73715f10a843628d5","last_reissued_at":"2026-07-05T05:13:10.918357Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:10.918357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.01223","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":"2026-07-05T05:13:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2j/m//jDENh2zztfcDFxrd53uRYek3QIt4Xj4iO/Ggh0dpGf7Yjfabi8iGLlcu4bs2kzzgsMwEGi3unf2qU1Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T13:34:13.014807Z"},"content_sha256":"855b31f149a96adb8b74406084403de481644de1d62b87d9144d7974609bea56","schema_version":"1.0","event_id":"sha256:855b31f149a96adb8b74406084403de481644de1d62b87d9144d7974609bea56"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:XV7NMD2OO6XQQ5GJ25TMXYHS3Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Audio Language Modeling using Perceptually-Guided Discrete Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Adam Polyak, Alexandre D\\'efossez, Felix Kreuk, Gabriel Synnaeve, Jade Copet, Yaniv Taigman, Yossi Adi","submitted_at":"2022-11-02T16:02:45Z","abstract_excerpt":"In this work, we study the task of Audio Language Modeling, in which we aim at learning probabilistic models for audio that can be used for generation and completion. We use a state-of-the-art perceptually-guided audio compression model, to encode audio to discrete representations. Next, we train a transformer-based causal language model using these representations. At inference time, we perform audio auto-completion by encoding an audio prompt as a discrete sequence, feeding it to the audio language model, sampling from the model, and synthesizing the corresponding time-domain signal. We eval"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.01223","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/2211.01223/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":"2026-07-05T05:13:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"grPQRV3GKCWy4de08hYt43Rz6AEWlh/pbVlkXLPquWw7lLhXcaoPa1+B7QLM2VZBedS1UTSHFUSQcHZLrxPxAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T13:34:13.015186Z"},"content_sha256":"0838eb79defc10f14adc119bcfa34c8f71c079fc5eb214af7a2f494ffb2e33fa","schema_version":"1.0","event_id":"sha256:0838eb79defc10f14adc119bcfa34c8f71c079fc5eb214af7a2f494ffb2e33fa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XV7NMD2OO6XQQ5GJ25TMXYHS3Q/bundle.json","state_url":"https://pith.science/pith/XV7NMD2OO6XQQ5GJ25TMXYHS3Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XV7NMD2OO6XQQ5GJ25TMXYHS3Q/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":"2026-07-05T13:34:13Z","links":{"resolver":"https://pith.science/pith/XV7NMD2OO6XQQ5GJ25TMXYHS3Q","bundle":"https://pith.science/pith/XV7NMD2OO6XQQ5GJ25TMXYHS3Q/bundle.json","state":"https://pith.science/pith/XV7NMD2OO6XQQ5GJ25TMXYHS3Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XV7NMD2OO6XQQ5GJ25TMXYHS3Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XV7NMD2OO6XQQ5GJ25TMXYHS3Q","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":"3cf43441a4bcb8d7dac32d8f4fde6725b571afa4ef374cb317906aea039f73cd","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-11-02T16:02:45Z","title_canon_sha256":"fe6241eef79c6a9d2d8dce9b1933bb59134f3f5d0e3d39a701ed148258988db1"},"schema_version":"1.0","source":{"id":"2211.01223","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.01223","created_at":"2026-07-05T05:13:10Z"},{"alias_kind":"arxiv_version","alias_value":"2211.01223v2","created_at":"2026-07-05T05:13:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.01223","created_at":"2026-07-05T05:13:10Z"},{"alias_kind":"pith_short_12","alias_value":"XV7NMD2OO6XQ","created_at":"2026-07-05T05:13:10Z"},{"alias_kind":"pith_short_16","alias_value":"XV7NMD2OO6XQQ5GJ","created_at":"2026-07-05T05:13:10Z"},{"alias_kind":"pith_short_8","alias_value":"XV7NMD2O","created_at":"2026-07-05T05:13:10Z"}],"graph_snapshots":[{"event_id":"sha256:0838eb79defc10f14adc119bcfa34c8f71c079fc5eb214af7a2f494ffb2e33fa","target":"graph","created_at":"2026-07-05T05:13:10Z","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/2211.01223/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we study the task of Audio Language Modeling, in which we aim at learning probabilistic models for audio that can be used for generation and completion. We use a state-of-the-art perceptually-guided audio compression model, to encode audio to discrete representations. Next, we train a transformer-based causal language model using these representations. At inference time, we perform audio auto-completion by encoding an audio prompt as a discrete sequence, feeding it to the audio language model, sampling from the model, and synthesizing the corresponding time-domain signal. We eval","authors_text":"Adam Polyak, Alexandre D\\'efossez, Felix Kreuk, Gabriel Synnaeve, Jade Copet, Yaniv Taigman, Yossi Adi","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-11-02T16:02:45Z","title":"Audio Language Modeling using Perceptually-Guided Discrete Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.01223","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":"sha256:855b31f149a96adb8b74406084403de481644de1d62b87d9144d7974609bea56","target":"record","created_at":"2026-07-05T05:13:10Z","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":"3cf43441a4bcb8d7dac32d8f4fde6725b571afa4ef374cb317906aea039f73cd","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-11-02T16:02:45Z","title_canon_sha256":"fe6241eef79c6a9d2d8dce9b1933bb59134f3f5d0e3d39a701ed148258988db1"},"schema_version":"1.0","source":{"id":"2211.01223","kind":"arxiv","version":2}},"canonical_sha256":"bd7ed60f4e77af0874c9d766cbe0f2dc15607b41f6d657e73715f10a843628d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd7ed60f4e77af0874c9d766cbe0f2dc15607b41f6d657e73715f10a843628d5","first_computed_at":"2026-07-05T05:13:10.918357Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:13:10.918357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uRx01VOmLEAxHjvYnTqyUq4jmA8N7ZsiMWJ10a/aZypFlnrIe+CAfcws2MvUrNi3dwNtgNxJLtl3n89rdvG8Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:13:10.918694Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.01223","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:855b31f149a96adb8b74406084403de481644de1d62b87d9144d7974609bea56","sha256:0838eb79defc10f14adc119bcfa34c8f71c079fc5eb214af7a2f494ffb2e33fa"],"state_sha256":"b8424c9117d4bafd752187016f76d78c89f192e53ece9adeb2efeee6df414926"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7dNfRSMNzm5Vk3hCtzmR4z6BmWPP+w34BBDyBbt0fJ+HUocujyxLhhDK3JBFZB/EBQZ5kHOKlN04k9snuPYEAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T13:34:13.017997Z","bundle_sha256":"5c600bc2b4cb9507eebc26964a1285484c8d30e0c08d5e8b2fa14a18f6c870f1"}}