{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BEFQERO5LHCFQBA2YFUJCYKAMS","short_pith_number":"pith:BEFQERO5","schema_version":"1.0","canonical_sha256":"090b0245dd59c458041ac16891614064a3e0d21d3464e2e844ffd25787c17f0b","source":{"kind":"arxiv","id":"2509.26469","version":4},"attestation_state":"computed","paper":{"title":"DiVeQ: Differentiable Vector Quantization Using the Reparameterization Trick","license":"http://creativecommons.org/licenses/by/4.0/","headline":"DiVeQ makes vector quantization differentiable by reparameterizing it as an additive error vector.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arno Solin, Mohammad Hassan Vali, Tom B\\\"ackstr\\\"om","submitted_at":"2025-09-30T16:17:21Z","abstract_excerpt":"Vector quantization is common in deep models, yet its hard assignments block gradients and hinder end-to-end training. We propose DiVeQ, which treats quantization as adding an error vector that mimics the quantization distortion, keeping the forward pass hard while letting gradients flow. We also present a space-filling variant (SF-DiVeQ) that assigns input to a curve constructed by the lines connecting codewords, resulting in less quantization error and full codebook usage. Both methods train end-to-end without requiring auxiliary losses or temperature schedules. In VQ-VAE image compression, "},"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":true},"canonical_record":{"source":{"id":"2509.26469","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-30T16:17:21Z","cross_cats_sorted":[],"title_canon_sha256":"5bc33420f94caab4993bbc8ef26ed4c8e36eec909e4e4de5786e73294215c2a3","abstract_canon_sha256":"68a69dbb823b02c186d7d5d111ff4d7260b7e85b049a205c70c05bac37fdfd7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:38.245807Z","signature_b64":"/l07bFFmCbg2c/cQ1kg6zGkfgC6haef9nV/96AIKC6O6NHJqG++YwiY9M8AXNFHPz/+CuCHYAOl1tOYTv8gPBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"090b0245dd59c458041ac16891614064a3e0d21d3464e2e844ffd25787c17f0b","last_reissued_at":"2026-05-27T01:05:38.245132Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:38.245132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiVeQ: Differentiable Vector Quantization Using the Reparameterization Trick","license":"http://creativecommons.org/licenses/by/4.0/","headline":"DiVeQ makes vector quantization differentiable by reparameterizing it as an additive error vector.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arno Solin, Mohammad Hassan Vali, Tom B\\\"ackstr\\\"om","submitted_at":"2025-09-30T16:17:21Z","abstract_excerpt":"Vector quantization is common in deep models, yet its hard assignments block gradients and hinder end-to-end training. We propose DiVeQ, which treats quantization as adding an error vector that mimics the quantization distortion, keeping the forward pass hard while letting gradients flow. We also present a space-filling variant (SF-DiVeQ) that assigns input to a curve constructed by the lines connecting codewords, resulting in less quantization error and full codebook usage. Both methods train end-to-end without requiring auxiliary losses or temperature schedules. In VQ-VAE image compression, "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"In VQ-VAE image compression, VQGAN image generation, and DAC speech coding tasks across various data sets, our proposed methods improve reconstruction and sample quality over alternative quantization approaches.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That modeling quantization distortion as an additive error vector (and the space-filling curve assignment) produces gradients that are both stable and unbiased enough to replace auxiliary losses and temperature schedules without degrading the hard forward-pass behavior.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DiVeQ and SF-DiVeQ make vector quantization differentiable through error-vector reparameterization and space-filling curves, yielding better reconstruction in VQ-VAE, VQGAN, and DAC tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"DiVeQ makes vector quantization differentiable by reparameterizing it as an additive error vector.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"45f129a11702c01e06b9a39c42cc34b3ca90abfbb74a2d4827eacf5ee120cad0"},"source":{"id":"2509.26469","kind":"arxiv","version":4},"verdict":{"id":"bea943f8-8673-4a7f-a5b1-c4808b6df145","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-18T11:53:17.007194Z","strongest_claim":"In VQ-VAE image compression, VQGAN image generation, and DAC speech coding tasks across various data sets, our proposed methods improve reconstruction and sample quality over alternative quantization approaches.","one_line_summary":"DiVeQ and SF-DiVeQ make vector quantization differentiable through error-vector reparameterization and space-filling curves, yielding better reconstruction in VQ-VAE, VQGAN, and DAC tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That modeling quantization distortion as an additive error vector (and the space-filling curve assignment) produces gradients that are both stable and unbiased enough to replace auxiliary losses and temperature schedules without degrading the hard forward-pass behavior.","pith_extraction_headline":"DiVeQ makes vector quantization differentiable by reparameterizing it as an additive error vector."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2509.26469/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":2,"snapshot_sha256":"8e883833f512c9600f1ebc0eb73d006788d75bc76a8a761eb992d24a45ad7707"},"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":"2509.26469","created_at":"2026-05-27T01:05:38.245186+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.26469v4","created_at":"2026-05-27T01:05:38.245186+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.26469","created_at":"2026-05-27T01:05:38.245186+00:00"},{"alias_kind":"pith_short_12","alias_value":"BEFQERO5LHCF","created_at":"2026-05-27T01:05:38.245186+00:00"},{"alias_kind":"pith_short_16","alias_value":"BEFQERO5LHCFQBA2","created_at":"2026-05-27T01:05:38.245186+00:00"},{"alias_kind":"pith_short_8","alias_value":"BEFQERO5","created_at":"2026-05-27T01:05:38.245186+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BEFQERO5LHCFQBA2YFUJCYKAMS","json":"https://pith.science/pith/BEFQERO5LHCFQBA2YFUJCYKAMS.json","graph_json":"https://pith.science/api/pith-number/BEFQERO5LHCFQBA2YFUJCYKAMS/graph.json","events_json":"https://pith.science/api/pith-number/BEFQERO5LHCFQBA2YFUJCYKAMS/events.json","paper":"https://pith.science/paper/BEFQERO5"},"agent_actions":{"view_html":"https://pith.science/pith/BEFQERO5LHCFQBA2YFUJCYKAMS","download_json":"https://pith.science/pith/BEFQERO5LHCFQBA2YFUJCYKAMS.json","view_paper":"https://pith.science/paper/BEFQERO5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.26469&json=true","fetch_graph":"https://pith.science/api/pith-number/BEFQERO5LHCFQBA2YFUJCYKAMS/graph.json","fetch_events":"https://pith.science/api/pith-number/BEFQERO5LHCFQBA2YFUJCYKAMS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BEFQERO5LHCFQBA2YFUJCYKAMS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BEFQERO5LHCFQBA2YFUJCYKAMS/action/storage_attestation","attest_author":"https://pith.science/pith/BEFQERO5LHCFQBA2YFUJCYKAMS/action/author_attestation","sign_citation":"https://pith.science/pith/BEFQERO5LHCFQBA2YFUJCYKAMS/action/citation_signature","submit_replication":"https://pith.science/pith/BEFQERO5LHCFQBA2YFUJCYKAMS/action/replication_record"}},"created_at":"2026-05-27T01:05:38.245186+00:00","updated_at":"2026-05-27T01:05:38.245186+00:00"}