{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QYMWILLLFNVSRRI27HUZ4JTQHU","short_pith_number":"pith:QYMWILLL","canonical_record":{"source":{"id":"2605.13517","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T13:35:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"441d62555c829aede8009bc3e8dee6882634f159ddd147f17f276ac0fe80ea9e","abstract_canon_sha256":"910fd1d6fe463497dab3b91f103ddd2f9230533bb55babdd1400f62a323d9caa"},"schema_version":"1.0"},"canonical_sha256":"8619642d6b2b6b28c51af9e99e26703d3f7542bf9aa607f1475451ae8eeb261c","source":{"kind":"arxiv","id":"2605.13517","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13517","created_at":"2026-05-18T02:44:24Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13517v1","created_at":"2026-05-18T02:44:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13517","created_at":"2026-05-18T02:44:24Z"},{"alias_kind":"pith_short_12","alias_value":"QYMWILLLFNVS","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"QYMWILLLFNVSRRI2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"QYMWILLL","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QYMWILLLFNVSRRI27HUZ4JTQHU","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13517","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T13:35:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"441d62555c829aede8009bc3e8dee6882634f159ddd147f17f276ac0fe80ea9e","abstract_canon_sha256":"910fd1d6fe463497dab3b91f103ddd2f9230533bb55babdd1400f62a323d9caa"},"schema_version":"1.0"},"canonical_sha256":"8619642d6b2b6b28c51af9e99e26703d3f7542bf9aa607f1475451ae8eeb261c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:24.427524Z","signature_b64":"npgS6l2dg1WDAlc9napWfC0j9RcvsM6TTR6n6PLqrR+Y1hOiw/fK2S+u9DvMptxJjeewQ1lhRGrIQGGqDmWiAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8619642d6b2b6b28c51af9e99e26703d3f7542bf9aa607f1475451ae8eeb261c","last_reissued_at":"2026-05-18T02:44:24.427031Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:24.427031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13517","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":"2026-05-18T02:44:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZCOU/LKGd6BRRylX2G0R61tH5HfbnCUeiPWwXnKMdCMhemSNTprc4Sj+S1DHkmL3gcPseTazFFjhcBO7671QBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T21:06:09.875800Z"},"content_sha256":"c7d8b0d7a37187e4881cdcd477371a91d1fcf076e172731db241e3a5bb4cc5f8","schema_version":"1.0","event_id":"sha256:c7d8b0d7a37187e4881cdcd477371a91d1fcf076e172731db241e3a5bb4cc5f8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QYMWILLLFNVSRRI27HUZ4JTQHU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margin","license":"http://creativecommons.org/licenses/by/4.0/","headline":"ArcVQ-VAE adds a spherical angular-margin prior to VQ-VAE codebooks to increase utilization and dispersion.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jaeyung Kim, Youngjoon Yoo","submitted_at":"2026-05-13T13:35:16Z","abstract_excerpt":"Vector Quantized Variational Autoencoder (VQ-VAE) has become a fundamental framework for learning discrete representations in image modeling. However, VQ-VAE models must tokenize entire images using a finite set of codebook vectors, and this capacity limitation restricts their ability to capture rich and diverse representations. In this paper, we propose ArcCosine Additive Margin VQ-VAE (ArcVQ-VAE), a novel vector quantization framework that introduces a spherical angular-margin prior (SAMP) for the codebook of a conventional VQ-VAE. The proposed SAMP consists of Ball-Bounded Norm Regularizati"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The proposed SAMP consists of Ball-Bounded Norm Regularization... and ArcCosine Additive Margin Loss... This formulation promotes more discriminative and uniformly dispersed latent representations within the constrained space, thereby improving effective latent-space coverage and leading to improved codebook utilization.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the combination of time-dependent ball constraint and arc-cosine margin will reliably increase angular separability and utilization without harming training stability or reconstruction quality on the target datasets.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ArcVQ-VAE constrains VQ-VAE codebook vectors inside a time-dependent ball and adds angular margin loss to increase separability and codebook utilization.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"ArcVQ-VAE adds a spherical angular-margin prior to VQ-VAE codebooks to increase utilization and dispersion.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ca5047cb16a09534a4b8dec77d0a8b5f1beb6c5ce2965d20dd2a54b391bb53f8"},"source":{"id":"2605.13517","kind":"arxiv","version":1},"verdict":{"id":"156b36ee-cfdc-46d9-967c-285d79d6a76b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:05:48.915274Z","strongest_claim":"The proposed SAMP consists of Ball-Bounded Norm Regularization... and ArcCosine Additive Margin Loss... This formulation promotes more discriminative and uniformly dispersed latent representations within the constrained space, thereby improving effective latent-space coverage and leading to improved codebook utilization.","one_line_summary":"ArcVQ-VAE constrains VQ-VAE codebook vectors inside a time-dependent ball and adds angular margin loss to increase separability and codebook utilization.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the combination of time-dependent ball constraint and arc-cosine margin will reliably increase angular separability and utilization without harming training stability or reconstruction quality on the target datasets.","pith_extraction_headline":"ArcVQ-VAE adds a spherical angular-margin prior to VQ-VAE codebooks to increase utilization and dispersion."},"references":{"count":15,"sample":[{"doi":"","year":null,"title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","work_id":"1fe8c7c8-aff7-4b94-9096-e549d7e60789","ref_index":1,"cited_arxiv_id":"1308.3432","is_internal_anchor":true},{"doi":"","year":null,"title":"Hyper- spherical variational auto-encoders","work_id":"7164f439-c1a9-40af-8fd3-1df0d25bd03f","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"Fast decoding in se- quence models using discrete latent variables","work_id":"02e45462-cbbb-4c93-b2f8-83b5a42e882c","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2000,"title":"Crafting papers on machine learning","work_id":"d344ba9d-7725-491b-9cdd-eba5d0253623","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Unitok: A unified tokenizer for visual generation and understanding","work_id":"31d5c278-398d-4fee-8130-a864fb6b3717","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":15,"snapshot_sha256":"0e0eb4a237620c1ee7d3686bdf37a2c29fc4c0b4faf5f421aab50591aebe7482","internal_anchors":2},"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":"156b36ee-cfdc-46d9-967c-285d79d6a76b"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WqXlilaqq0PVAIlUyIIEmZ6dkUqXpuZqk+4tFgKBVKBFs0xRP1lk2QRJGN+0lBLQNxAv8NUJ4o+rEUW7PB2DAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T21:06:09.876295Z"},"content_sha256":"6b99c5928a6a34677cf92bb98f1efb69f36a0f405efcda7f526274a5f794ca39","schema_version":"1.0","event_id":"sha256:6b99c5928a6a34677cf92bb98f1efb69f36a0f405efcda7f526274a5f794ca39"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QYMWILLLFNVSRRI27HUZ4JTQHU/bundle.json","state_url":"https://pith.science/pith/QYMWILLLFNVSRRI27HUZ4JTQHU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QYMWILLLFNVSRRI27HUZ4JTQHU/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":"2026-06-27T21:06:09Z","links":{"resolver":"https://pith.science/pith/QYMWILLLFNVSRRI27HUZ4JTQHU","bundle":"https://pith.science/pith/QYMWILLLFNVSRRI27HUZ4JTQHU/bundle.json","state":"https://pith.science/pith/QYMWILLLFNVSRRI27HUZ4JTQHU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QYMWILLLFNVSRRI27HUZ4JTQHU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QYMWILLLFNVSRRI27HUZ4JTQHU","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":"910fd1d6fe463497dab3b91f103ddd2f9230533bb55babdd1400f62a323d9caa","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T13:35:16Z","title_canon_sha256":"441d62555c829aede8009bc3e8dee6882634f159ddd147f17f276ac0fe80ea9e"},"schema_version":"1.0","source":{"id":"2605.13517","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13517","created_at":"2026-05-18T02:44:24Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13517v1","created_at":"2026-05-18T02:44:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13517","created_at":"2026-05-18T02:44:24Z"},{"alias_kind":"pith_short_12","alias_value":"QYMWILLLFNVS","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"QYMWILLLFNVSRRI2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"QYMWILLL","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:6b99c5928a6a34677cf92bb98f1efb69f36a0f405efcda7f526274a5f794ca39","target":"graph","created_at":"2026-05-18T02:44:24Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"The proposed SAMP consists of Ball-Bounded Norm Regularization... and ArcCosine Additive Margin Loss... This formulation promotes more discriminative and uniformly dispersed latent representations within the constrained space, thereby improving effective latent-space coverage and leading to improved codebook utilization."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the combination of time-dependent ball constraint and arc-cosine margin will reliably increase angular separability and utilization without harming training stability or reconstruction quality on the target datasets."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"ArcVQ-VAE constrains VQ-VAE codebook vectors inside a time-dependent ball and adds angular margin loss to increase separability and codebook utilization."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"ArcVQ-VAE adds a spherical angular-margin prior to VQ-VAE codebooks to increase utilization and dispersion."}],"snapshot_sha256":"ca5047cb16a09534a4b8dec77d0a8b5f1beb6c5ce2965d20dd2a54b391bb53f8"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Vector Quantized Variational Autoencoder (VQ-VAE) has become a fundamental framework for learning discrete representations in image modeling. However, VQ-VAE models must tokenize entire images using a finite set of codebook vectors, and this capacity limitation restricts their ability to capture rich and diverse representations. In this paper, we propose ArcCosine Additive Margin VQ-VAE (ArcVQ-VAE), a novel vector quantization framework that introduces a spherical angular-margin prior (SAMP) for the codebook of a conventional VQ-VAE. The proposed SAMP consists of Ball-Bounded Norm Regularizati","authors_text":"Jaeyung Kim, Youngjoon Yoo","cross_cats":["cs.AI","cs.LG"],"headline":"ArcVQ-VAE adds a spherical angular-margin prior to VQ-VAE codebooks to increase utilization and dispersion.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T13:35:16Z","title":"ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margin"},"references":{"count":15,"internal_anchors":2,"resolved_work":15,"sample":[{"cited_arxiv_id":"1308.3432","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","work_id":"1fe8c7c8-aff7-4b94-9096-e549d7e60789","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Hyper- spherical variational auto-encoders","work_id":"7164f439-c1a9-40af-8fd3-1df0d25bd03f","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Fast decoding in se- quence models using discrete latent variables","work_id":"02e45462-cbbb-4c93-b2f8-83b5a42e882c","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Crafting papers on machine learning","work_id":"d344ba9d-7725-491b-9cdd-eba5d0253623","year":2000},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Unitok: A unified tokenizer for visual generation and understanding","work_id":"31d5c278-398d-4fee-8130-a864fb6b3717","year":null}],"snapshot_sha256":"0e0eb4a237620c1ee7d3686bdf37a2c29fc4c0b4faf5f421aab50591aebe7482"},"source":{"id":"2605.13517","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:05:48.915274Z","id":"156b36ee-cfdc-46d9-967c-285d79d6a76b","model_set":{"reader":"grok-4.3"},"one_line_summary":"ArcVQ-VAE constrains VQ-VAE codebook vectors inside a time-dependent ball and adds angular margin loss to increase separability and codebook utilization.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"ArcVQ-VAE adds a spherical angular-margin prior to VQ-VAE codebooks to increase utilization and dispersion.","strongest_claim":"The proposed SAMP consists of Ball-Bounded Norm Regularization... and ArcCosine Additive Margin Loss... This formulation promotes more discriminative and uniformly dispersed latent representations within the constrained space, thereby improving effective latent-space coverage and leading to improved codebook utilization.","weakest_assumption":"That the combination of time-dependent ball constraint and arc-cosine margin will reliably increase angular separability and utilization without harming training stability or reconstruction quality on the target datasets."}},"verdict_id":"156b36ee-cfdc-46d9-967c-285d79d6a76b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c7d8b0d7a37187e4881cdcd477371a91d1fcf076e172731db241e3a5bb4cc5f8","target":"record","created_at":"2026-05-18T02:44:24Z","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":"910fd1d6fe463497dab3b91f103ddd2f9230533bb55babdd1400f62a323d9caa","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T13:35:16Z","title_canon_sha256":"441d62555c829aede8009bc3e8dee6882634f159ddd147f17f276ac0fe80ea9e"},"schema_version":"1.0","source":{"id":"2605.13517","kind":"arxiv","version":1}},"canonical_sha256":"8619642d6b2b6b28c51af9e99e26703d3f7542bf9aa607f1475451ae8eeb261c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8619642d6b2b6b28c51af9e99e26703d3f7542bf9aa607f1475451ae8eeb261c","first_computed_at":"2026-05-18T02:44:24.427031Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:24.427031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"npgS6l2dg1WDAlc9napWfC0j9RcvsM6TTR6n6PLqrR+Y1hOiw/fK2S+u9DvMptxJjeewQ1lhRGrIQGGqDmWiAA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:24.427524Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13517","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7d8b0d7a37187e4881cdcd477371a91d1fcf076e172731db241e3a5bb4cc5f8","sha256:6b99c5928a6a34677cf92bb98f1efb69f36a0f405efcda7f526274a5f794ca39"],"state_sha256":"3ddcd4cf5fa14ab12d099404b40983c4db44b00bea63c4c1f610f9a1496ec480"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n223Qg7hYoopFOjfnpGSWD3q0NUHYDpIrAilg34efgPO/JFfLeS5AskUhuBmhNOeg/WXJi4aFrGp7BgE7Zr4Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T21:06:09.878761Z","bundle_sha256":"fe09009395e55ff90a24d5ce9e8fad5ce25dc15fe338beb4ee71b276871f8182"}}