{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Q7SRYQU4HYV454B3ROORP7Z44S","short_pith_number":"pith:Q7SRYQU4","canonical_record":{"source":{"id":"2402.13429","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-02-20T23:45:37Z","cross_cats_sorted":["cs.LG","cs.OS"],"title_canon_sha256":"d0945f1febc4299c0631a6a37364032416675693cbd078d7742eb42937d8f103","abstract_canon_sha256":"deb185f9ec6cdd987fdcdc2e899a7de139a3bcecac2bb3cc9557826d13c12696"},"schema_version":"1.0"},"canonical_sha256":"87e51c429c3e2bcef03b8b9d17ff3ce4b8cac93e9cd384d62e162cddd21fd12f","source":{"kind":"arxiv","id":"2402.13429","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13429","created_at":"2026-07-05T07:54:08Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13429v1","created_at":"2026-07-05T07:54:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13429","created_at":"2026-07-05T07:54:08Z"},{"alias_kind":"pith_short_12","alias_value":"Q7SRYQU4HYV4","created_at":"2026-07-05T07:54:08Z"},{"alias_kind":"pith_short_16","alias_value":"Q7SRYQU4HYV454B3","created_at":"2026-07-05T07:54:08Z"},{"alias_kind":"pith_short_8","alias_value":"Q7SRYQU4","created_at":"2026-07-05T07:54:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Q7SRYQU4HYV454B3ROORP7Z44S","target":"record","payload":{"canonical_record":{"source":{"id":"2402.13429","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-02-20T23:45:37Z","cross_cats_sorted":["cs.LG","cs.OS"],"title_canon_sha256":"d0945f1febc4299c0631a6a37364032416675693cbd078d7742eb42937d8f103","abstract_canon_sha256":"deb185f9ec6cdd987fdcdc2e899a7de139a3bcecac2bb3cc9557826d13c12696"},"schema_version":"1.0"},"canonical_sha256":"87e51c429c3e2bcef03b8b9d17ff3ce4b8cac93e9cd384d62e162cddd21fd12f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:08.462220Z","signature_b64":"2PzdqfstveN5BVoiYNoR2t/CtwSUf0vCvkRm4TBeqZyyN6jyQZlceGyk6yiWTtYv8TUmxBL2pVZrupFseZ3ADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87e51c429c3e2bcef03b8b9d17ff3ce4b8cac93e9cd384d62e162cddd21fd12f","last_reissued_at":"2026-07-05T07:54:08.461745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:08.461745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.13429","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":"2026-07-05T07:54:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lMn0SNG7SG8ejXPxp60MVLJVqySOnKdUMzY0FJWllL7PsHhcdXR9AHqPu31qj8KyVgNmOEASzFdVAhciaIXHBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:15:21.585835Z"},"content_sha256":"68b53a1c48b63f5913510da302c203d33d63495069d634c5ecc1904fec62bc68","schema_version":"1.0","event_id":"sha256:68b53a1c48b63f5913510da302c203d33d63495069d634c5ecc1904fec62bc68"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Q7SRYQU4HYV454B3ROORP7Z44S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Everything You Always Wanted to Know About Storage Compressibility of Pre-Trained ML Models but Were Afraid to Ask","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.OS"],"primary_cat":"cs.DB","authors_text":"Ali Anwar, Ammar Ahmed, Yue Cheng, Zhaoyuan Su, Zirui Wang","submitted_at":"2024-02-20T23:45:37Z","abstract_excerpt":"As the number of pre-trained machine learning (ML) models is growing exponentially, data reduction tools are not catching up. Existing data reduction techniques are not specifically designed for pre-trained model (PTM) dataset files. This is largely due to a lack of understanding of the patterns and characteristics of these datasets, especially those relevant to data reduction and compressibility.\n  This paper presents the first, exhaustive analysis to date of PTM datasets on storage compressibility. Our analysis spans different types of data reduction and compression techniques, from hash-bas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13429","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/2402.13429/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":"2026-07-05T07:54:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qrBAbEJkiAJeX00Hwvdl+JyfIxL/UhErUcm6+FkMmhoOo+CdjusPwMiZxpb+rbhuDKHbz8kcSzHwSm/Ty1CxBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:15:21.586810Z"},"content_sha256":"dd612b488da551237b257d2dca7d42f877f1f82ab932f4c5b6dff168b2dcc776","schema_version":"1.0","event_id":"sha256:dd612b488da551237b257d2dca7d42f877f1f82ab932f4c5b6dff168b2dcc776"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q7SRYQU4HYV454B3ROORP7Z44S/bundle.json","state_url":"https://pith.science/pith/Q7SRYQU4HYV454B3ROORP7Z44S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q7SRYQU4HYV454B3ROORP7Z44S/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":"2026-08-05T03:15:21Z","links":{"resolver":"https://pith.science/pith/Q7SRYQU4HYV454B3ROORP7Z44S","bundle":"https://pith.science/pith/Q7SRYQU4HYV454B3ROORP7Z44S/bundle.json","state":"https://pith.science/pith/Q7SRYQU4HYV454B3ROORP7Z44S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q7SRYQU4HYV454B3ROORP7Z44S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q7SRYQU4HYV454B3ROORP7Z44S","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":"deb185f9ec6cdd987fdcdc2e899a7de139a3bcecac2bb3cc9557826d13c12696","cross_cats_sorted":["cs.LG","cs.OS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-02-20T23:45:37Z","title_canon_sha256":"d0945f1febc4299c0631a6a37364032416675693cbd078d7742eb42937d8f103"},"schema_version":"1.0","source":{"id":"2402.13429","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13429","created_at":"2026-07-05T07:54:08Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13429v1","created_at":"2026-07-05T07:54:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13429","created_at":"2026-07-05T07:54:08Z"},{"alias_kind":"pith_short_12","alias_value":"Q7SRYQU4HYV4","created_at":"2026-07-05T07:54:08Z"},{"alias_kind":"pith_short_16","alias_value":"Q7SRYQU4HYV454B3","created_at":"2026-07-05T07:54:08Z"},{"alias_kind":"pith_short_8","alias_value":"Q7SRYQU4","created_at":"2026-07-05T07:54:08Z"}],"graph_snapshots":[{"event_id":"sha256:dd612b488da551237b257d2dca7d42f877f1f82ab932f4c5b6dff168b2dcc776","target":"graph","created_at":"2026-07-05T07:54:08Z","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/2402.13429/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As the number of pre-trained machine learning (ML) models is growing exponentially, data reduction tools are not catching up. Existing data reduction techniques are not specifically designed for pre-trained model (PTM) dataset files. This is largely due to a lack of understanding of the patterns and characteristics of these datasets, especially those relevant to data reduction and compressibility.\n  This paper presents the first, exhaustive analysis to date of PTM datasets on storage compressibility. Our analysis spans different types of data reduction and compression techniques, from hash-bas","authors_text":"Ali Anwar, Ammar Ahmed, Yue Cheng, Zhaoyuan Su, Zirui Wang","cross_cats":["cs.LG","cs.OS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-02-20T23:45:37Z","title":"Everything You Always Wanted to Know About Storage Compressibility of Pre-Trained ML Models but Were Afraid to Ask"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13429","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":"sha256:68b53a1c48b63f5913510da302c203d33d63495069d634c5ecc1904fec62bc68","target":"record","created_at":"2026-07-05T07:54:08Z","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":"deb185f9ec6cdd987fdcdc2e899a7de139a3bcecac2bb3cc9557826d13c12696","cross_cats_sorted":["cs.LG","cs.OS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-02-20T23:45:37Z","title_canon_sha256":"d0945f1febc4299c0631a6a37364032416675693cbd078d7742eb42937d8f103"},"schema_version":"1.0","source":{"id":"2402.13429","kind":"arxiv","version":1}},"canonical_sha256":"87e51c429c3e2bcef03b8b9d17ff3ce4b8cac93e9cd384d62e162cddd21fd12f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87e51c429c3e2bcef03b8b9d17ff3ce4b8cac93e9cd384d62e162cddd21fd12f","first_computed_at":"2026-07-05T07:54:08.461745Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:54:08.461745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2PzdqfstveN5BVoiYNoR2t/CtwSUf0vCvkRm4TBeqZyyN6jyQZlceGyk6yiWTtYv8TUmxBL2pVZrupFseZ3ADg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:54:08.462220Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.13429","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68b53a1c48b63f5913510da302c203d33d63495069d634c5ecc1904fec62bc68","sha256:dd612b488da551237b257d2dca7d42f877f1f82ab932f4c5b6dff168b2dcc776"],"state_sha256":"5a107327443692d167388f26ca4f655643271b41fbbe04e784d7b674bc71a2c3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yy3r0YtrRkEUMmmromlgfRuFq5fo3rr+p7VC0U8BdP31lyQc1qO8rHCSdhn6dPW609VrR9SHizOxrX6Fh9KWCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T03:15:21.593380Z","bundle_sha256":"bafe561f234704f8e6266e809aee9764b6825b49faaa3429ccef7baa49edf058"}}