{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:6Q767YNPLQTRDFK6WGU2JVTMXN","short_pith_number":"pith:6Q767YNP","canonical_record":{"source":{"id":"2201.01155","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-31T07:05:31Z","cross_cats_sorted":["cs.AI","cs.CV","cs.SE"],"title_canon_sha256":"15c973dc2af4aa3317b2db1d1deebca1e0944bf9741ce2d3a6f5560b2016f400","abstract_canon_sha256":"22c6c79ad1f26a93206a0c56f2549f54a5ee5e5095889dcbbb0b0a565e20aaeb"},"schema_version":"1.0"},"canonical_sha256":"f43fefe1af5c2711955eb1a9a4d66cbb4e7caa40031753e7d9a63af9582b0a0a","source":{"kind":"arxiv","id":"2201.01155","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.01155","created_at":"2026-07-05T03:45:17Z"},{"alias_kind":"arxiv_version","alias_value":"2201.01155v1","created_at":"2026-07-05T03:45:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.01155","created_at":"2026-07-05T03:45:17Z"},{"alias_kind":"pith_short_12","alias_value":"6Q767YNPLQTR","created_at":"2026-07-05T03:45:17Z"},{"alias_kind":"pith_short_16","alias_value":"6Q767YNPLQTRDFK6","created_at":"2026-07-05T03:45:17Z"},{"alias_kind":"pith_short_8","alias_value":"6Q767YNP","created_at":"2026-07-05T03:45:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:6Q767YNPLQTRDFK6WGU2JVTMXN","target":"record","payload":{"canonical_record":{"source":{"id":"2201.01155","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-31T07:05:31Z","cross_cats_sorted":["cs.AI","cs.CV","cs.SE"],"title_canon_sha256":"15c973dc2af4aa3317b2db1d1deebca1e0944bf9741ce2d3a6f5560b2016f400","abstract_canon_sha256":"22c6c79ad1f26a93206a0c56f2549f54a5ee5e5095889dcbbb0b0a565e20aaeb"},"schema_version":"1.0"},"canonical_sha256":"f43fefe1af5c2711955eb1a9a4d66cbb4e7caa40031753e7d9a63af9582b0a0a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:45:17.337095Z","signature_b64":"tzRDFmC70WbeunS99KGQcvIjFrxeC50MxJKyq+p54q++U13DVH0uBUfOXftRO0LPQUlfeIJO4RP9f0ImC43nCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f43fefe1af5c2711955eb1a9a4d66cbb4e7caa40031753e7d9a63af9582b0a0a","last_reissued_at":"2026-07-05T03:45:17.336678Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:45:17.336678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.01155","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":"2026-07-05T03:45:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f+sLskd/e2Iftkbez5BOkUmIvqGbT+P0ZQxWWOb7DUXasdhlVbjGw7Fowbiz/fLXk3YFq9G01R3W5gs/uer9Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:38:02.922858Z"},"content_sha256":"d28159458eb4fd0f9d5ab156bfb39412793ab45d859904173a3fd5cdcb0f8cf6","schema_version":"1.0","event_id":"sha256:d28159458eb4fd0f9d5ab156bfb39412793ab45d859904173a3fd5cdcb0f8cf6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:6Q767YNPLQTRDFK6WGU2JVTMXN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DeepVisualInsight: Time-Travelling Visualization for Spatio-Temporal Causality of Deep Classification Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.SE"],"primary_cat":"cs.LG","authors_text":"Chao Wang, Hong Mei, Jin Song Dong, Ruofan Liu, Xianglin Yang, Yun Lin, Zhenfeng He","submitted_at":"2021-12-31T07:05:31Z","abstract_excerpt":"Understanding how the predictions of deep learning models are formed during the training process is crucial to improve model performance and fix model defects, especially when we need to investigate nontrivial training strategies such as active learning, and track the root cause of unexpected training results such as performance degeneration.\n  In this work, we propose a time-travelling visual solution DeepVisualInsight (DVI), aiming to manifest the spatio-temporal causality while training a deep learning image classifier. The spatio-temporal causality demonstrates how the gradient-descent alg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.01155","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/2201.01155/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":"2026-07-05T03:45:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8UXSfU/FefLsViGwcMjTturoGuw8ah4ZwoQbE6Bn1D/+RqM6ECH4RHwpvKgtrUVvPbrBmRdYE8N6z2gOPaSCBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:38:02.923244Z"},"content_sha256":"cd6dff0a873fc4ef4feb11cc2e09424c0d5dc3417635b0f5f950009c9509b809","schema_version":"1.0","event_id":"sha256:cd6dff0a873fc4ef4feb11cc2e09424c0d5dc3417635b0f5f950009c9509b809"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6Q767YNPLQTRDFK6WGU2JVTMXN/bundle.json","state_url":"https://pith.science/pith/6Q767YNPLQTRDFK6WGU2JVTMXN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6Q767YNPLQTRDFK6WGU2JVTMXN/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":"2026-07-07T14:38:02Z","links":{"resolver":"https://pith.science/pith/6Q767YNPLQTRDFK6WGU2JVTMXN","bundle":"https://pith.science/pith/6Q767YNPLQTRDFK6WGU2JVTMXN/bundle.json","state":"https://pith.science/pith/6Q767YNPLQTRDFK6WGU2JVTMXN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6Q767YNPLQTRDFK6WGU2JVTMXN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6Q767YNPLQTRDFK6WGU2JVTMXN","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":"22c6c79ad1f26a93206a0c56f2549f54a5ee5e5095889dcbbb0b0a565e20aaeb","cross_cats_sorted":["cs.AI","cs.CV","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-31T07:05:31Z","title_canon_sha256":"15c973dc2af4aa3317b2db1d1deebca1e0944bf9741ce2d3a6f5560b2016f400"},"schema_version":"1.0","source":{"id":"2201.01155","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.01155","created_at":"2026-07-05T03:45:17Z"},{"alias_kind":"arxiv_version","alias_value":"2201.01155v1","created_at":"2026-07-05T03:45:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.01155","created_at":"2026-07-05T03:45:17Z"},{"alias_kind":"pith_short_12","alias_value":"6Q767YNPLQTR","created_at":"2026-07-05T03:45:17Z"},{"alias_kind":"pith_short_16","alias_value":"6Q767YNPLQTRDFK6","created_at":"2026-07-05T03:45:17Z"},{"alias_kind":"pith_short_8","alias_value":"6Q767YNP","created_at":"2026-07-05T03:45:17Z"}],"graph_snapshots":[{"event_id":"sha256:cd6dff0a873fc4ef4feb11cc2e09424c0d5dc3417635b0f5f950009c9509b809","target":"graph","created_at":"2026-07-05T03:45:17Z","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/2201.01155/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding how the predictions of deep learning models are formed during the training process is crucial to improve model performance and fix model defects, especially when we need to investigate nontrivial training strategies such as active learning, and track the root cause of unexpected training results such as performance degeneration.\n  In this work, we propose a time-travelling visual solution DeepVisualInsight (DVI), aiming to manifest the spatio-temporal causality while training a deep learning image classifier. The spatio-temporal causality demonstrates how the gradient-descent alg","authors_text":"Chao Wang, Hong Mei, Jin Song Dong, Ruofan Liu, Xianglin Yang, Yun Lin, Zhenfeng He","cross_cats":["cs.AI","cs.CV","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-31T07:05:31Z","title":"DeepVisualInsight: Time-Travelling Visualization for Spatio-Temporal Causality of Deep Classification Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.01155","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:d28159458eb4fd0f9d5ab156bfb39412793ab45d859904173a3fd5cdcb0f8cf6","target":"record","created_at":"2026-07-05T03:45:17Z","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":"22c6c79ad1f26a93206a0c56f2549f54a5ee5e5095889dcbbb0b0a565e20aaeb","cross_cats_sorted":["cs.AI","cs.CV","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-31T07:05:31Z","title_canon_sha256":"15c973dc2af4aa3317b2db1d1deebca1e0944bf9741ce2d3a6f5560b2016f400"},"schema_version":"1.0","source":{"id":"2201.01155","kind":"arxiv","version":1}},"canonical_sha256":"f43fefe1af5c2711955eb1a9a4d66cbb4e7caa40031753e7d9a63af9582b0a0a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f43fefe1af5c2711955eb1a9a4d66cbb4e7caa40031753e7d9a63af9582b0a0a","first_computed_at":"2026-07-05T03:45:17.336678Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:45:17.336678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tzRDFmC70WbeunS99KGQcvIjFrxeC50MxJKyq+p54q++U13DVH0uBUfOXftRO0LPQUlfeIJO4RP9f0ImC43nCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:45:17.337095Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.01155","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d28159458eb4fd0f9d5ab156bfb39412793ab45d859904173a3fd5cdcb0f8cf6","sha256:cd6dff0a873fc4ef4feb11cc2e09424c0d5dc3417635b0f5f950009c9509b809"],"state_sha256":"5f54edf6130c2497eefbe14f53503708bde4b3b9b1347939b9eb8495ec6f437e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o2m7bBrInMYpC1CDcWDcL4oEviJX3QJUhAJV2xOtnzMaDD6rHlOmizQ2aIOJaVC/EKWd3lMvV2fqYMJ5Ka2RDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:38:02.925163Z","bundle_sha256":"375a6571776ce3dc70cf713eb657884f839ed02fe3a8d9fd72889158307dfe14"}}