{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:UYBVMRVFJBFVCGNBWMPAWXS2KE","short_pith_number":"pith:UYBVMRVF","canonical_record":{"source":{"id":"2605.15413","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T20:57:15Z","cross_cats_sorted":[],"title_canon_sha256":"7e7b75926d1ea4522798d8adfe560b6d520f07bc8b45b1761ef3b75fd6f0f744","abstract_canon_sha256":"2a49b079418a93f3424ec125972eee8d6d1fc01a7eb9d5bcaa43878bfbeccf16"},"schema_version":"1.0"},"canonical_sha256":"a6035646a5484b5119a1b31e0b5e5a51057ca475398611b6d32a8e45996674eb","source":{"kind":"arxiv","id":"2605.15413","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15413","created_at":"2026-05-20T00:00:57Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15413v1","created_at":"2026-05-20T00:00:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15413","created_at":"2026-05-20T00:00:57Z"},{"alias_kind":"pith_short_12","alias_value":"UYBVMRVFJBFV","created_at":"2026-05-20T00:00:57Z"},{"alias_kind":"pith_short_16","alias_value":"UYBVMRVFJBFVCGNB","created_at":"2026-05-20T00:00:57Z"},{"alias_kind":"pith_short_8","alias_value":"UYBVMRVF","created_at":"2026-05-20T00:00:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:UYBVMRVFJBFVCGNBWMPAWXS2KE","target":"record","payload":{"canonical_record":{"source":{"id":"2605.15413","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T20:57:15Z","cross_cats_sorted":[],"title_canon_sha256":"7e7b75926d1ea4522798d8adfe560b6d520f07bc8b45b1761ef3b75fd6f0f744","abstract_canon_sha256":"2a49b079418a93f3424ec125972eee8d6d1fc01a7eb9d5bcaa43878bfbeccf16"},"schema_version":"1.0"},"canonical_sha256":"a6035646a5484b5119a1b31e0b5e5a51057ca475398611b6d32a8e45996674eb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:57.338644Z","signature_b64":"QPIrXLBrp5PFH7w0WdVse1zCUUCf/5ZCtsHQPAdn8X8M+toZaQpVgR5/5YDzqvlrWJsbcS4QxH3Erd2nIGDPDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6035646a5484b5119a1b31e0b5e5a51057ca475398611b6d32a8e45996674eb","last_reissued_at":"2026-05-20T00:00:57.337812Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:57.337812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.15413","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":"2026-05-20T00:00:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NfZOH0DvCl6GJrtvbOQIIXql1UGu3c+Vo38I0TwQN5vgpTLeN4KV0yMKQ/RirF+NW1F4KQwy0kIMNU1u0ZfwDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:33:19.614038Z"},"content_sha256":"c049418a1768eb392eb00f157e7d3b6e5f216dda606ea1b43e25ef055e45161e","schema_version":"1.0","event_id":"sha256:c049418a1768eb392eb00f157e7d3b6e5f216dda606ea1b43e25ef055e45161e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:UYBVMRVFJBFVCGNBWMPAWXS2KE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transformer Scalability Crisis: The First Comprehensive Empirical Analysis of Performance Walls in Modern Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Benchmark of 118 transformers shows performance walls where success drops to zero at 2048 tokens.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Faezeh Ghaderi, Mahdi Naser Moghadasi","submitted_at":"2026-05-14T20:57:15Z","abstract_excerpt":"Despite the remarkable success of transformer architectures in natural language processing, their scalability limitations remain poorly understood through systematic empirical analysis. This paper presents the first comprehensive large-scale evaluation of 118 transformer models across seven distinct architectural categories, revealing fundamental performance walls that manifest as hard deployment constraints. Our systematic benchmarking methodology uncovers a critical scalability crisis: while 88.1% of models successfully process sequences up to 512 tokens, this drops dramatically to 44.9% at "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our findings challenge prevailing scaling assumptions and provide the first quantitative evidence that the theoretical O(n2) attention complexity translates into measurable performance walls.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The 118 models across seven architectural categories and the chosen sequence lengths from 128 to 2048 tokens are representative enough to reveal fundamental, generalizable performance walls in modern transformers rather than artifacts of specific model selection or hardware.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Empirical tests on 118 transformers show success falling from 88.1% at 512 tokens to 0% at 2048 tokens, with compressed models achieving 649.2 tokens/sec/M parameters versus 12.5 for large generative ones.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Benchmark of 118 transformers shows performance walls where success drops to zero at 2048 tokens.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"25e1e95877a8926d6b7d1c24cd969f555cfff547c4bc651b8ddcfe0a7770e1e1"},"source":{"id":"2605.15413","kind":"arxiv","version":1},"verdict":{"id":"a69acfcd-f8c7-4c2e-ae76-6cf30b39adbd","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T16:06:40.953973Z","strongest_claim":"Our findings challenge prevailing scaling assumptions and provide the first quantitative evidence that the theoretical O(n2) attention complexity translates into measurable performance walls.","one_line_summary":"Empirical tests on 118 transformers show success falling from 88.1% at 512 tokens to 0% at 2048 tokens, with compressed models achieving 649.2 tokens/sec/M parameters versus 12.5 for large generative ones.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The 118 models across seven architectural categories and the chosen sequence lengths from 128 to 2048 tokens are representative enough to reveal fundamental, generalizable performance walls in modern transformers rather than artifacts of specific model selection or hardware.","pith_extraction_headline":"Benchmark of 118 transformers shows performance walls where success drops to zero at 2048 tokens."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15413/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T16:31:18.262548Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"cited_work_retraction","ran_at":"2026-05-19T16:23:37.921123Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T16:15:56.771576Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T15:50:44.746822Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.149710Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.709268Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"53c6e90e73cb5d454f6755185f48742f09f311eedcef84b4d64388d1462e9f8c"},"references":{"count":64,"sample":[{"doi":"","year":2017,"title":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, ”Attention is all you need,” inAdvances in neural information processing systems, 2017, pp. 5998–6","work_id":"15a38721-1e5f-4def-a98f-a83840807dd2","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, ”BERT: Pre- training of deep bidirectional transformers for language understanding,” inProceedings of the 2019 Conference of the North American Chapte","work_id":"fb52ee0f-a8bf-4931-a84b-26b6ff9ecd08","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Brown et al., ”Language models are few-shot learners,” inAdvances in neural information processing systems, vol","work_id":"0e4f8c81-b7b7-411f-8253-c83d84bd78bd","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Dosovitskiy et al., ”An image is worth 16x16 words: Transformers for image recognition at scale,” inInternational Conference on Learning Representations, 2021","work_id":"ccd07a27-e078-4907-b999-2cbb4ef358e6","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2004,"title":"Longformer: The Long-Document Transformer","work_id":"abea7a44-6668-4de7-aab6-f53a6e5aa088","ref_index":5,"cited_arxiv_id":"2004.05150","is_internal_anchor":true}],"resolved_work":64,"snapshot_sha256":"97db72c9472cad122516098b2158b6c6c7db5ab6289f147dc39828c0ce12ad71","internal_anchors":24},"formal_canon":{"evidence_count":2,"snapshot_sha256":"2d2cb22f0372bc4fc888194707c64b5fc84d3bddfb1dad000904a64e813b204f"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"a69acfcd-f8c7-4c2e-ae76-6cf30b39adbd"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:00:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PZKJ7k0Oc+4LfTG4yFAmtpTpN0FPK+8yzZLuwheKv+Z5jQW/gdLGgC37gFEnF7D0NL0e5v2YP7MgUvTlty+dBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:33:19.615457Z"},"content_sha256":"6eb379b348544cb47319843130dba5566d8c58338967464b136247bb442d4b36","schema_version":"1.0","event_id":"sha256:6eb379b348544cb47319843130dba5566d8c58338967464b136247bb442d4b36"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UYBVMRVFJBFVCGNBWMPAWXS2KE/bundle.json","state_url":"https://pith.science/pith/UYBVMRVFJBFVCGNBWMPAWXS2KE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UYBVMRVFJBFVCGNBWMPAWXS2KE/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":"2026-05-25T19:33:19Z","links":{"resolver":"https://pith.science/pith/UYBVMRVFJBFVCGNBWMPAWXS2KE","bundle":"https://pith.science/pith/UYBVMRVFJBFVCGNBWMPAWXS2KE/bundle.json","state":"https://pith.science/pith/UYBVMRVFJBFVCGNBWMPAWXS2KE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UYBVMRVFJBFVCGNBWMPAWXS2KE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UYBVMRVFJBFVCGNBWMPAWXS2KE","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":"2a49b079418a93f3424ec125972eee8d6d1fc01a7eb9d5bcaa43878bfbeccf16","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T20:57:15Z","title_canon_sha256":"7e7b75926d1ea4522798d8adfe560b6d520f07bc8b45b1761ef3b75fd6f0f744"},"schema_version":"1.0","source":{"id":"2605.15413","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15413","created_at":"2026-05-20T00:00:57Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15413v1","created_at":"2026-05-20T00:00:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15413","created_at":"2026-05-20T00:00:57Z"},{"alias_kind":"pith_short_12","alias_value":"UYBVMRVFJBFV","created_at":"2026-05-20T00:00:57Z"},{"alias_kind":"pith_short_16","alias_value":"UYBVMRVFJBFVCGNB","created_at":"2026-05-20T00:00:57Z"},{"alias_kind":"pith_short_8","alias_value":"UYBVMRVF","created_at":"2026-05-20T00:00:57Z"}],"graph_snapshots":[{"event_id":"sha256:6eb379b348544cb47319843130dba5566d8c58338967464b136247bb442d4b36","target":"graph","created_at":"2026-05-20T00:00:57Z","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":"Our findings challenge prevailing scaling assumptions and provide the first quantitative evidence that the theoretical O(n2) attention complexity translates into measurable performance walls."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The 118 models across seven architectural categories and the chosen sequence lengths from 128 to 2048 tokens are representative enough to reveal fundamental, generalizable performance walls in modern transformers rather than artifacts of specific model selection or hardware."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Empirical tests on 118 transformers show success falling from 88.1% at 512 tokens to 0% at 2048 tokens, with compressed models achieving 649.2 tokens/sec/M parameters versus 12.5 for large generative ones."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Benchmark of 118 transformers shows performance walls where success drops to zero at 2048 tokens."}],"snapshot_sha256":"25e1e95877a8926d6b7d1c24cd969f555cfff547c4bc651b8ddcfe0a7770e1e1"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"2d2cb22f0372bc4fc888194707c64b5fc84d3bddfb1dad000904a64e813b204f"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T16:31:18.262548Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"cited_work_retraction","ran_at":"2026-05-19T16:23:37.921123Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T16:15:56.771576Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"citation_quote_validity","ran_at":"2026-05-19T15:50:44.746822Z","status":"skipped","version":"0.1.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.149710Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.709268Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.15413/integrity.json","findings":[],"snapshot_sha256":"53c6e90e73cb5d454f6755185f48742f09f311eedcef84b4d64388d1462e9f8c","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the remarkable success of transformer architectures in natural language processing, their scalability limitations remain poorly understood through systematic empirical analysis. This paper presents the first comprehensive large-scale evaluation of 118 transformer models across seven distinct architectural categories, revealing fundamental performance walls that manifest as hard deployment constraints. Our systematic benchmarking methodology uncovers a critical scalability crisis: while 88.1% of models successfully process sequences up to 512 tokens, this drops dramatically to 44.9% at ","authors_text":"Faezeh Ghaderi, Mahdi Naser Moghadasi","cross_cats":[],"headline":"Benchmark of 118 transformers shows performance walls where success drops to zero at 2048 tokens.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T20:57:15Z","title":"Transformer Scalability Crisis: The First Comprehensive Empirical Analysis of Performance Walls in Modern Language Models"},"references":{"count":64,"internal_anchors":24,"resolved_work":64,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, ”Attention is all you need,” inAdvances in neural information processing systems, 2017, pp. 5998–6","work_id":"15a38721-1e5f-4def-a98f-a83840807dd2","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, ”BERT: Pre- training of deep bidirectional transformers for language understanding,” inProceedings of the 2019 Conference of the North American Chapte","work_id":"fb52ee0f-a8bf-4931-a84b-26b6ff9ecd08","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Brown et al., ”Language models are few-shot learners,” inAdvances in neural information processing systems, vol","work_id":"0e4f8c81-b7b7-411f-8253-c83d84bd78bd","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Dosovitskiy et al., ”An image is worth 16x16 words: Transformers for image recognition at scale,” inInternational Conference on Learning Representations, 2021","work_id":"ccd07a27-e078-4907-b999-2cbb4ef358e6","year":2021},{"cited_arxiv_id":"2004.05150","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Longformer: The Long-Document Transformer","work_id":"abea7a44-6668-4de7-aab6-f53a6e5aa088","year":2004}],"snapshot_sha256":"97db72c9472cad122516098b2158b6c6c7db5ab6289f147dc39828c0ce12ad71"},"source":{"id":"2605.15413","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T16:06:40.953973Z","id":"a69acfcd-f8c7-4c2e-ae76-6cf30b39adbd","model_set":{"reader":"grok-4.3"},"one_line_summary":"Empirical tests on 118 transformers show success falling from 88.1% at 512 tokens to 0% at 2048 tokens, with compressed models achieving 649.2 tokens/sec/M parameters versus 12.5 for large generative ones.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Benchmark of 118 transformers shows performance walls where success drops to zero at 2048 tokens.","strongest_claim":"Our findings challenge prevailing scaling assumptions and provide the first quantitative evidence that the theoretical O(n2) attention complexity translates into measurable performance walls.","weakest_assumption":"The 118 models across seven architectural categories and the chosen sequence lengths from 128 to 2048 tokens are representative enough to reveal fundamental, generalizable performance walls in modern transformers rather than artifacts of specific model selection or hardware."}},"verdict_id":"a69acfcd-f8c7-4c2e-ae76-6cf30b39adbd"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c049418a1768eb392eb00f157e7d3b6e5f216dda606ea1b43e25ef055e45161e","target":"record","created_at":"2026-05-20T00:00:57Z","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":"2a49b079418a93f3424ec125972eee8d6d1fc01a7eb9d5bcaa43878bfbeccf16","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T20:57:15Z","title_canon_sha256":"7e7b75926d1ea4522798d8adfe560b6d520f07bc8b45b1761ef3b75fd6f0f744"},"schema_version":"1.0","source":{"id":"2605.15413","kind":"arxiv","version":1}},"canonical_sha256":"a6035646a5484b5119a1b31e0b5e5a51057ca475398611b6d32a8e45996674eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6035646a5484b5119a1b31e0b5e5a51057ca475398611b6d32a8e45996674eb","first_computed_at":"2026-05-20T00:00:57.337812Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:57.337812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QPIrXLBrp5PFH7w0WdVse1zCUUCf/5ZCtsHQPAdn8X8M+toZaQpVgR5/5YDzqvlrWJsbcS4QxH3Erd2nIGDPDQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:57.338644Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15413","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c049418a1768eb392eb00f157e7d3b6e5f216dda606ea1b43e25ef055e45161e","sha256:6eb379b348544cb47319843130dba5566d8c58338967464b136247bb442d4b36"],"state_sha256":"624011eb06a83f5daff3c32b5d3d5b9c3180dde4751a55792f2fe1f2fec5bc3f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zBP3CDD8uURJKd03Q/jlzQu2ou+XyZmeG1b2viERphYUxwYJ4G3Lr+HhXD8iT/THY9ZU/xy/a7Lee6nt9zAKAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T19:33:19.621189Z","bundle_sha256":"eb806108af7baf4c2ed325fe7e9681c61392665cacaf3ee5877ecd3b339bb379"}}