{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IDMPISQJAECXDYKAYZAVIXGPSJ","short_pith_number":"pith:IDMPISQJ","schema_version":"1.0","canonical_sha256":"40d8f44a09010571e140c641545ccf92771cdc15f18ae9a17e1976db877c4479","source":{"kind":"arxiv","id":"2301.08562","version":1},"attestation_state":"computed","paper":{"title":"Latent Autoregressive Source Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Andrea Santilli, Emanuele Rodol\\`a, Emilian Postolache, Giorgio Mariani, Luca Cosmo, Michele Mancusi","submitted_at":"2023-01-09T17:32:00Z","abstract_excerpt":"Autoregressive models have achieved impressive results over a wide range of domains in terms of generation quality and downstream task performance. In the continuous domain, a key factor behind this success is the usage of quantized latent spaces (e.g., obtained via VQ-VAE autoencoders), which allow for dimensionality reduction and faster inference times. However, using existing pre-trained models to perform new non-trivial tasks is difficult since it requires additional fine-tuning or extensive training to elicit prompting. This paper introduces LASS as a way to perform vector-quantized Laten"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2301.08562","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-09T17:32:00Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"c6ffbdcfb20abb870e2d10f69b65654b42a8dd0e77d9eacc91adedc40f3b2a5a","abstract_canon_sha256":"4e39b72fe95a3b8241cdeea5f3045ef677639a70489cb24fe5971850c17c2833"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:34:37.501001Z","signature_b64":"xX5VsQk0OTXHzuAlNRZg5xrSQfa1VE8GnYxz6Ru+Y7FINFa878azkpQHcmFI81gd5FriuH+JqLdASEVIQoeqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40d8f44a09010571e140c641545ccf92771cdc15f18ae9a17e1976db877c4479","last_reissued_at":"2026-07-05T05:34:37.500502Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:34:37.500502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latent Autoregressive Source Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Andrea Santilli, Emanuele Rodol\\`a, Emilian Postolache, Giorgio Mariani, Luca Cosmo, Michele Mancusi","submitted_at":"2023-01-09T17:32:00Z","abstract_excerpt":"Autoregressive models have achieved impressive results over a wide range of domains in terms of generation quality and downstream task performance. In the continuous domain, a key factor behind this success is the usage of quantized latent spaces (e.g., obtained via VQ-VAE autoencoders), which allow for dimensionality reduction and faster inference times. However, using existing pre-trained models to perform new non-trivial tasks is difficult since it requires additional fine-tuning or extensive training to elicit prompting. This paper introduces LASS as a way to perform vector-quantized Laten"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.08562","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/2301.08562/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2301.08562","created_at":"2026-07-05T05:34:37.500564+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.08562v1","created_at":"2026-07-05T05:34:37.500564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.08562","created_at":"2026-07-05T05:34:37.500564+00:00"},{"alias_kind":"pith_short_12","alias_value":"IDMPISQJAECX","created_at":"2026-07-05T05:34:37.500564+00:00"},{"alias_kind":"pith_short_16","alias_value":"IDMPISQJAECXDYKA","created_at":"2026-07-05T05:34:37.500564+00:00"},{"alias_kind":"pith_short_8","alias_value":"IDMPISQJ","created_at":"2026-07-05T05:34:37.500564+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IDMPISQJAECXDYKAYZAVIXGPSJ","json":"https://pith.science/pith/IDMPISQJAECXDYKAYZAVIXGPSJ.json","graph_json":"https://pith.science/api/pith-number/IDMPISQJAECXDYKAYZAVIXGPSJ/graph.json","events_json":"https://pith.science/api/pith-number/IDMPISQJAECXDYKAYZAVIXGPSJ/events.json","paper":"https://pith.science/paper/IDMPISQJ"},"agent_actions":{"view_html":"https://pith.science/pith/IDMPISQJAECXDYKAYZAVIXGPSJ","download_json":"https://pith.science/pith/IDMPISQJAECXDYKAYZAVIXGPSJ.json","view_paper":"https://pith.science/paper/IDMPISQJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.08562&json=true","fetch_graph":"https://pith.science/api/pith-number/IDMPISQJAECXDYKAYZAVIXGPSJ/graph.json","fetch_events":"https://pith.science/api/pith-number/IDMPISQJAECXDYKAYZAVIXGPSJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IDMPISQJAECXDYKAYZAVIXGPSJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IDMPISQJAECXDYKAYZAVIXGPSJ/action/storage_attestation","attest_author":"https://pith.science/pith/IDMPISQJAECXDYKAYZAVIXGPSJ/action/author_attestation","sign_citation":"https://pith.science/pith/IDMPISQJAECXDYKAYZAVIXGPSJ/action/citation_signature","submit_replication":"https://pith.science/pith/IDMPISQJAECXDYKAYZAVIXGPSJ/action/replication_record"}},"created_at":"2026-07-05T05:34:37.500564+00:00","updated_at":"2026-07-05T05:34:37.500564+00:00"}