{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EUE7I3AKB2F4U52ZJ5JRQD7OWR","short_pith_number":"pith:EUE7I3AK","schema_version":"1.0","canonical_sha256":"2509f46c0a0e8bca77594f53180feeb475fe6375cfc0c074fa11babe0e66722e","source":{"kind":"arxiv","id":"2305.16645","version":2},"attestation_state":"computed","paper":{"title":"Summarizing Stream Data for Memory-Constrained Online Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianyang Gu, Kai Wang, Wei Jiang, Yang You","submitted_at":"2023-05-26T05:31:51Z","abstract_excerpt":"Replay-based methods have proved their effectiveness on online continual learning by rehearsing past samples from an auxiliary memory. With many efforts made on improving training schemes based on the memory, however, the information carried by each sample in the memory remains under-investigated. Under circumstances with restricted storage space, the informativeness of the memory becomes critical for effective replay. Although some works design specific strategies to select representative samples, by only employing a small number of original images, the storage space is still not well utilize"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2305.16645","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-26T05:31:51Z","cross_cats_sorted":[],"title_canon_sha256":"4172ef7831f16429dd9dca93208747a67759e284d8a5778c6e90888d9c8c1adb","abstract_canon_sha256":"f87a729cfcda41f868d8bb5b0e955e3f591c6bc1dca25fe2f3d420dcd6aecbc0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:31:28.551415Z","signature_b64":"fWMCxVqsPTRsiiJRB5fxTBRVGHQXtntXSSAY5MPOS3bx9Tl+e6MsGkxXudBBlOcRZxM8Ur92tEM/G9Jm1uEmDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2509f46c0a0e8bca77594f53180feeb475fe6375cfc0c074fa11babe0e66722e","last_reissued_at":"2026-07-05T07:31:28.550940Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:31:28.550940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Summarizing Stream Data for Memory-Constrained Online Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianyang Gu, Kai Wang, Wei Jiang, Yang You","submitted_at":"2023-05-26T05:31:51Z","abstract_excerpt":"Replay-based methods have proved their effectiveness on online continual learning by rehearsing past samples from an auxiliary memory. With many efforts made on improving training schemes based on the memory, however, the information carried by each sample in the memory remains under-investigated. Under circumstances with restricted storage space, the informativeness of the memory becomes critical for effective replay. Although some works design specific strategies to select representative samples, by only employing a small number of original images, the storage space is still not well utilize"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16645","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/2305.16645/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2305.16645","created_at":"2026-07-05T07:31:28.550995+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.16645v2","created_at":"2026-07-05T07:31:28.550995+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16645","created_at":"2026-07-05T07:31:28.550995+00:00"},{"alias_kind":"pith_short_12","alias_value":"EUE7I3AKB2F4","created_at":"2026-07-05T07:31:28.550995+00:00"},{"alias_kind":"pith_short_16","alias_value":"EUE7I3AKB2F4U52Z","created_at":"2026-07-05T07:31:28.550995+00:00"},{"alias_kind":"pith_short_8","alias_value":"EUE7I3AK","created_at":"2026-07-05T07:31:28.550995+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12649","citing_title":"DIVER:Diving Deeper into Distilled Data via Expressive Semantic Recovery","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EUE7I3AKB2F4U52ZJ5JRQD7OWR","json":"https://pith.science/pith/EUE7I3AKB2F4U52ZJ5JRQD7OWR.json","graph_json":"https://pith.science/api/pith-number/EUE7I3AKB2F4U52ZJ5JRQD7OWR/graph.json","events_json":"https://pith.science/api/pith-number/EUE7I3AKB2F4U52ZJ5JRQD7OWR/events.json","paper":"https://pith.science/paper/EUE7I3AK"},"agent_actions":{"view_html":"https://pith.science/pith/EUE7I3AKB2F4U52ZJ5JRQD7OWR","download_json":"https://pith.science/pith/EUE7I3AKB2F4U52ZJ5JRQD7OWR.json","view_paper":"https://pith.science/paper/EUE7I3AK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.16645&json=true","fetch_graph":"https://pith.science/api/pith-number/EUE7I3AKB2F4U52ZJ5JRQD7OWR/graph.json","fetch_events":"https://pith.science/api/pith-number/EUE7I3AKB2F4U52ZJ5JRQD7OWR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EUE7I3AKB2F4U52ZJ5JRQD7OWR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EUE7I3AKB2F4U52ZJ5JRQD7OWR/action/storage_attestation","attest_author":"https://pith.science/pith/EUE7I3AKB2F4U52ZJ5JRQD7OWR/action/author_attestation","sign_citation":"https://pith.science/pith/EUE7I3AKB2F4U52ZJ5JRQD7OWR/action/citation_signature","submit_replication":"https://pith.science/pith/EUE7I3AKB2F4U52ZJ5JRQD7OWR/action/replication_record"}},"created_at":"2026-07-05T07:31:28.550995+00:00","updated_at":"2026-07-05T07:31:28.550995+00:00"}