{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SR26QDJAZ7LZIOXL4WYI3BE6XA","short_pith_number":"pith:SR26QDJA","canonical_record":{"source":{"id":"2505.16563","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T11:53:48Z","cross_cats_sorted":[],"title_canon_sha256":"c317625dfeac6391ec7461f04f188ebf4e4a10813f02a0d0c367c188873c2c40","abstract_canon_sha256":"c24a72dfb73e22affef1b3ed8f51ed77d1059af010d9b1004fb502f984308a8e"},"schema_version":"1.0"},"canonical_sha256":"9475e80d20cfd7943aebe5b08d849eb8231849be895a5b5b49817593f94c0346","source":{"kind":"arxiv","id":"2505.16563","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16563","created_at":"2026-07-05T11:19:07Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16563v2","created_at":"2026-07-05T11:19:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16563","created_at":"2026-07-05T11:19:07Z"},{"alias_kind":"pith_short_12","alias_value":"SR26QDJAZ7LZ","created_at":"2026-07-05T11:19:07Z"},{"alias_kind":"pith_short_16","alias_value":"SR26QDJAZ7LZIOXL","created_at":"2026-07-05T11:19:07Z"},{"alias_kind":"pith_short_8","alias_value":"SR26QDJA","created_at":"2026-07-05T11:19:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SR26QDJAZ7LZIOXL4WYI3BE6XA","target":"record","payload":{"canonical_record":{"source":{"id":"2505.16563","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T11:53:48Z","cross_cats_sorted":[],"title_canon_sha256":"c317625dfeac6391ec7461f04f188ebf4e4a10813f02a0d0c367c188873c2c40","abstract_canon_sha256":"c24a72dfb73e22affef1b3ed8f51ed77d1059af010d9b1004fb502f984308a8e"},"schema_version":"1.0"},"canonical_sha256":"9475e80d20cfd7943aebe5b08d849eb8231849be895a5b5b49817593f94c0346","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:07.385154Z","signature_b64":"1ODWoTtGt+GkVbb7T90Lh2Di/AEPhU1Fs5mN9lT9pTOWO3P0gANukyO63ZKJowPTuFX8Dx3So/JsV9tmrJyHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9475e80d20cfd7943aebe5b08d849eb8231849be895a5b5b49817593f94c0346","last_reissued_at":"2026-07-05T11:19:07.384724Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:07.384724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.16563","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:19:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"THJ7aek2TvNqjpK+RJINB4dIRRVBlPut++5MsDPX5vd3bSvSOLSICl+YQh2fpQv2NRoJ+gn1JPiaNlWmknd5CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T17:13:53.027227Z"},"content_sha256":"981af2ac950180ca83179b73d9fb634474fff908ed2ab115c96126788254d14f","schema_version":"1.0","event_id":"sha256:981af2ac950180ca83179b73d9fb634474fff908ed2ab115c96126788254d14f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SR26QDJAZ7LZIOXL4WYI3BE6XA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Two-Stage Data Selection Framework for Data-Efficient Model Training on Edge Devices","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chen Gong, Fan Wu, Rui Xing, Zhenzhe Zheng","submitted_at":"2025-05-22T11:53:48Z","abstract_excerpt":"The demand for machine learning (ML) model training on edge devices is escalating due to data privacy and personalized service needs. However, we observe that current on-device model training is hampered by the under-utilization of on-device data, due to low training throughput, limited storage and diverse data importance. To improve data resource utilization, we propose a two-stage data selection framework {\\sf Titan} to select the most important data batch from streaming data for model training with guaranteed efficiency and effectiveness. Specifically, in the first stage, {\\sf Titan} filter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16563","kind":"arxiv","version":2},"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/2505.16563/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":"2026-07-05T11:19:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DM626vDbM+TeJBrfToED5xw+SrlWt5HPUZcsv7VpVDDsJEcEKMcbDZrtFSJClGkfk3v6y7rUpFKAE7PajgNbBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T17:13:53.028097Z"},"content_sha256":"6d1df140fadbe65acadd8e7e02df831b64b18adf9e66f1214d90e90cb00d2b7d","schema_version":"1.0","event_id":"sha256:6d1df140fadbe65acadd8e7e02df831b64b18adf9e66f1214d90e90cb00d2b7d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SR26QDJAZ7LZIOXL4WYI3BE6XA/bundle.json","state_url":"https://pith.science/pith/SR26QDJAZ7LZIOXL4WYI3BE6XA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SR26QDJAZ7LZIOXL4WYI3BE6XA/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":"2026-08-18T17:13:53Z","links":{"resolver":"https://pith.science/pith/SR26QDJAZ7LZIOXL4WYI3BE6XA","bundle":"https://pith.science/pith/SR26QDJAZ7LZIOXL4WYI3BE6XA/bundle.json","state":"https://pith.science/pith/SR26QDJAZ7LZIOXL4WYI3BE6XA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SR26QDJAZ7LZIOXL4WYI3BE6XA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SR26QDJAZ7LZIOXL4WYI3BE6XA","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":"c24a72dfb73e22affef1b3ed8f51ed77d1059af010d9b1004fb502f984308a8e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T11:53:48Z","title_canon_sha256":"c317625dfeac6391ec7461f04f188ebf4e4a10813f02a0d0c367c188873c2c40"},"schema_version":"1.0","source":{"id":"2505.16563","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16563","created_at":"2026-07-05T11:19:07Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16563v2","created_at":"2026-07-05T11:19:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16563","created_at":"2026-07-05T11:19:07Z"},{"alias_kind":"pith_short_12","alias_value":"SR26QDJAZ7LZ","created_at":"2026-07-05T11:19:07Z"},{"alias_kind":"pith_short_16","alias_value":"SR26QDJAZ7LZIOXL","created_at":"2026-07-05T11:19:07Z"},{"alias_kind":"pith_short_8","alias_value":"SR26QDJA","created_at":"2026-07-05T11:19:07Z"}],"graph_snapshots":[{"event_id":"sha256:6d1df140fadbe65acadd8e7e02df831b64b18adf9e66f1214d90e90cb00d2b7d","target":"graph","created_at":"2026-07-05T11:19:07Z","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/2505.16563/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The demand for machine learning (ML) model training on edge devices is escalating due to data privacy and personalized service needs. However, we observe that current on-device model training is hampered by the under-utilization of on-device data, due to low training throughput, limited storage and diverse data importance. To improve data resource utilization, we propose a two-stage data selection framework {\\sf Titan} to select the most important data batch from streaming data for model training with guaranteed efficiency and effectiveness. Specifically, in the first stage, {\\sf Titan} filter","authors_text":"Chen Gong, Fan Wu, Rui Xing, Zhenzhe Zheng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T11:53:48Z","title":"A Two-Stage Data Selection Framework for Data-Efficient Model Training on Edge Devices"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16563","kind":"arxiv","version":2},"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":"sha256:981af2ac950180ca83179b73d9fb634474fff908ed2ab115c96126788254d14f","target":"record","created_at":"2026-07-05T11:19:07Z","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":"c24a72dfb73e22affef1b3ed8f51ed77d1059af010d9b1004fb502f984308a8e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T11:53:48Z","title_canon_sha256":"c317625dfeac6391ec7461f04f188ebf4e4a10813f02a0d0c367c188873c2c40"},"schema_version":"1.0","source":{"id":"2505.16563","kind":"arxiv","version":2}},"canonical_sha256":"9475e80d20cfd7943aebe5b08d849eb8231849be895a5b5b49817593f94c0346","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9475e80d20cfd7943aebe5b08d849eb8231849be895a5b5b49817593f94c0346","first_computed_at":"2026-07-05T11:19:07.384724Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:07.384724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1ODWoTtGt+GkVbb7T90Lh2Di/AEPhU1Fs5mN9lT9pTOWO3P0gANukyO63ZKJowPTuFX8Dx3So/JsV9tmrJyHCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:07.385154Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.16563","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:981af2ac950180ca83179b73d9fb634474fff908ed2ab115c96126788254d14f","sha256:6d1df140fadbe65acadd8e7e02df831b64b18adf9e66f1214d90e90cb00d2b7d"],"state_sha256":"0c8f1e3aa5142462b630aade162b5b9f7fa6c92bd26e8f6e339721c7398455b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fd33K6jz+D6wGKJ+rdkwccEXgvUfe1rMzoRXAsekrsr+wh9FB6bzRDi+GVyTZHxxeoqP952DSf3JMQ5bIpAcDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T17:13:53.038519Z","bundle_sha256":"12bf258627666db21e9103fd7c6e5e36097d443ea2bd9177b1367ff13ad8e76b"}}