{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6QNDLPEGSCEPOMXZOHJ6Y73O4K","short_pith_number":"pith:6QNDLPEG","canonical_record":{"source":{"id":"2407.18158","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-07-25T16:13:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ec783d55c7eb6f8a415cf70240179d61d56b3e723cf2b2602bbda09467e10ab1","abstract_canon_sha256":"16cf7b797a66915ea8be77a72fea5c78ee69ae9bcc281dbb4c3ad60f0f9e6a17"},"schema_version":"1.0"},"canonical_sha256":"f41a35bc869088f732f971d3ec7f6ee28dbad32e091efa0e05e5a863e1cbb543","source":{"kind":"arxiv","id":"2407.18158","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.18158","created_at":"2026-07-05T08:48:35Z"},{"alias_kind":"arxiv_version","alias_value":"2407.18158v1","created_at":"2026-07-05T08:48:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18158","created_at":"2026-07-05T08:48:35Z"},{"alias_kind":"pith_short_12","alias_value":"6QNDLPEGSCEP","created_at":"2026-07-05T08:48:35Z"},{"alias_kind":"pith_short_16","alias_value":"6QNDLPEGSCEPOMXZ","created_at":"2026-07-05T08:48:35Z"},{"alias_kind":"pith_short_8","alias_value":"6QNDLPEG","created_at":"2026-07-05T08:48:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6QNDLPEGSCEPOMXZOHJ6Y73O4K","target":"record","payload":{"canonical_record":{"source":{"id":"2407.18158","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-07-25T16:13:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ec783d55c7eb6f8a415cf70240179d61d56b3e723cf2b2602bbda09467e10ab1","abstract_canon_sha256":"16cf7b797a66915ea8be77a72fea5c78ee69ae9bcc281dbb4c3ad60f0f9e6a17"},"schema_version":"1.0"},"canonical_sha256":"f41a35bc869088f732f971d3ec7f6ee28dbad32e091efa0e05e5a863e1cbb543","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:35.477650Z","signature_b64":"Scvtz8kbeKpWvxGhHLsDsl2R4DaQbvADJirhCMkwvLTOy1em7QgQWgZHhe5xShpcGKrAqKfVWTvkk8E2K915BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f41a35bc869088f732f971d3ec7f6ee28dbad32e091efa0e05e5a863e1cbb543","last_reissued_at":"2026-07-05T08:48:35.477123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:35.477123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.18158","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":"2026-07-05T08:48:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iJ0wkabby8+Zk31rk+AyQnx7JaHJyUyV0lQp2MDUGNXXiPd7aB1u9sCsB0dA/kD2l5BptH6HvbxfUZ3WhPQdCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:48:43.208465Z"},"content_sha256":"a4bb8047885c8e325041dd4e1a14833b9e389b899f52f3503e519c8a92c78532","schema_version":"1.0","event_id":"sha256:a4bb8047885c8e325041dd4e1a14833b9e389b899f52f3503e519c8a92c78532"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6QNDLPEGSCEPOMXZOHJ6Y73O4K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Andrew Gordon Wilson, Brandon Amos, Marc Finzi, Micah Goldblum, Sanae Lotfi, Yilun Kuang","submitted_at":"2024-07-25T16:13:58Z","abstract_excerpt":"Large language models (LLMs) with billions of parameters excel at predicting the next token in a sequence. Recent work computes non-vacuous compression-based generalization bounds for LLMs, but these bounds are vacuous for large models at the billion-parameter scale. Moreover, these bounds are obtained through restrictive compression techniques, bounding compressed models that generate low-quality text. Additionally, the tightness of these existing bounds depends on the number of IID documents in a training set rather than the much larger number of non-IID constituent tokens, leaving untapped "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18158","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/2407.18158/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":"2026-07-05T08:48:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CknjsGJeVuSH1kp+LLRf+RFlQxBJYWn9S4F8X/nGR4hUOr4kJ121YyEr84PmrvLKzL7RvAPwaztvp+IOx5AuBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:48:43.209614Z"},"content_sha256":"4586158f2cad6140e2a912bae3f19c8752fe997cef35614167078334bb0138b0","schema_version":"1.0","event_id":"sha256:4586158f2cad6140e2a912bae3f19c8752fe997cef35614167078334bb0138b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6QNDLPEGSCEPOMXZOHJ6Y73O4K/bundle.json","state_url":"https://pith.science/pith/6QNDLPEGSCEPOMXZOHJ6Y73O4K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6QNDLPEGSCEPOMXZOHJ6Y73O4K/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":"2026-08-09T19:48:43Z","links":{"resolver":"https://pith.science/pith/6QNDLPEGSCEPOMXZOHJ6Y73O4K","bundle":"https://pith.science/pith/6QNDLPEGSCEPOMXZOHJ6Y73O4K/bundle.json","state":"https://pith.science/pith/6QNDLPEGSCEPOMXZOHJ6Y73O4K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6QNDLPEGSCEPOMXZOHJ6Y73O4K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6QNDLPEGSCEPOMXZOHJ6Y73O4K","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":"16cf7b797a66915ea8be77a72fea5c78ee69ae9bcc281dbb4c3ad60f0f9e6a17","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-07-25T16:13:58Z","title_canon_sha256":"ec783d55c7eb6f8a415cf70240179d61d56b3e723cf2b2602bbda09467e10ab1"},"schema_version":"1.0","source":{"id":"2407.18158","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.18158","created_at":"2026-07-05T08:48:35Z"},{"alias_kind":"arxiv_version","alias_value":"2407.18158v1","created_at":"2026-07-05T08:48:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18158","created_at":"2026-07-05T08:48:35Z"},{"alias_kind":"pith_short_12","alias_value":"6QNDLPEGSCEP","created_at":"2026-07-05T08:48:35Z"},{"alias_kind":"pith_short_16","alias_value":"6QNDLPEGSCEPOMXZ","created_at":"2026-07-05T08:48:35Z"},{"alias_kind":"pith_short_8","alias_value":"6QNDLPEG","created_at":"2026-07-05T08:48:35Z"}],"graph_snapshots":[{"event_id":"sha256:4586158f2cad6140e2a912bae3f19c8752fe997cef35614167078334bb0138b0","target":"graph","created_at":"2026-07-05T08:48:35Z","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/2407.18158/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) with billions of parameters excel at predicting the next token in a sequence. Recent work computes non-vacuous compression-based generalization bounds for LLMs, but these bounds are vacuous for large models at the billion-parameter scale. Moreover, these bounds are obtained through restrictive compression techniques, bounding compressed models that generate low-quality text. Additionally, the tightness of these existing bounds depends on the number of IID documents in a training set rather than the much larger number of non-IID constituent tokens, leaving untapped ","authors_text":"Andrew Gordon Wilson, Brandon Amos, Marc Finzi, Micah Goldblum, Sanae Lotfi, Yilun Kuang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-07-25T16:13:58Z","title":"Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18158","kind":"arxiv","version":1},"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:a4bb8047885c8e325041dd4e1a14833b9e389b899f52f3503e519c8a92c78532","target":"record","created_at":"2026-07-05T08:48:35Z","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":"16cf7b797a66915ea8be77a72fea5c78ee69ae9bcc281dbb4c3ad60f0f9e6a17","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-07-25T16:13:58Z","title_canon_sha256":"ec783d55c7eb6f8a415cf70240179d61d56b3e723cf2b2602bbda09467e10ab1"},"schema_version":"1.0","source":{"id":"2407.18158","kind":"arxiv","version":1}},"canonical_sha256":"f41a35bc869088f732f971d3ec7f6ee28dbad32e091efa0e05e5a863e1cbb543","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f41a35bc869088f732f971d3ec7f6ee28dbad32e091efa0e05e5a863e1cbb543","first_computed_at":"2026-07-05T08:48:35.477123Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:48:35.477123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Scvtz8kbeKpWvxGhHLsDsl2R4DaQbvADJirhCMkwvLTOy1em7QgQWgZHhe5xShpcGKrAqKfVWTvkk8E2K915BA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:48:35.477650Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.18158","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4bb8047885c8e325041dd4e1a14833b9e389b899f52f3503e519c8a92c78532","sha256:4586158f2cad6140e2a912bae3f19c8752fe997cef35614167078334bb0138b0"],"state_sha256":"12c83ce4ce41a41f7aaf78e21dc99053fce7554c976bd8997152dd472b26cd5f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dzmH7GX4BWyxyEMEOHppulHDybKjKvcPzpapI5YU+pqWU6UKsQkybkkuxdjvF182Q0GzXee2cAZ23aY87lXEDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T19:48:43.220011Z","bundle_sha256":"06e0e55a53aa9342c45268287f160fd60e4243de5cca2c71577f1c1107ddad54"}}