{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ID2OIUXNVFGJTTFKLJAKIMBC2Y","short_pith_number":"pith:ID2OIUXN","canonical_record":{"source":{"id":"2303.13251","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-23T13:33:58Z","cross_cats_sorted":[],"title_canon_sha256":"7dcd3fc6992c5c146f148cd85a605075b63566ab043ac00ff8e4a15b7fc6a84d","abstract_canon_sha256":"a919c60bb753a3b4de5eaa746701ffbe818711ce5bb6eee29e8c2050a123eb6f"},"schema_version":"1.0"},"canonical_sha256":"40f4e452eda94c99ccaa5a40a43022d632ab9dbcdcf689ebf413a21f60e33153","source":{"kind":"arxiv","id":"2303.13251","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.13251","created_at":"2026-07-05T05:53:59Z"},{"alias_kind":"arxiv_version","alias_value":"2303.13251v1","created_at":"2026-07-05T05:53:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.13251","created_at":"2026-07-05T05:53:59Z"},{"alias_kind":"pith_short_12","alias_value":"ID2OIUXNVFGJ","created_at":"2026-07-05T05:53:59Z"},{"alias_kind":"pith_short_16","alias_value":"ID2OIUXNVFGJTTFK","created_at":"2026-07-05T05:53:59Z"},{"alias_kind":"pith_short_8","alias_value":"ID2OIUXN","created_at":"2026-07-05T05:53:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ID2OIUXNVFGJTTFKLJAKIMBC2Y","target":"record","payload":{"canonical_record":{"source":{"id":"2303.13251","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-23T13:33:58Z","cross_cats_sorted":[],"title_canon_sha256":"7dcd3fc6992c5c146f148cd85a605075b63566ab043ac00ff8e4a15b7fc6a84d","abstract_canon_sha256":"a919c60bb753a3b4de5eaa746701ffbe818711ce5bb6eee29e8c2050a123eb6f"},"schema_version":"1.0"},"canonical_sha256":"40f4e452eda94c99ccaa5a40a43022d632ab9dbcdcf689ebf413a21f60e33153","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:53:59.802855Z","signature_b64":"GIuhTJxxAi1JyxKvudZSzEzoxG7zAv/doxWpoJbkudOZNOMoYQOtfQvkNO/THI1NR/Tnx61ymirFBWUz7FDWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40f4e452eda94c99ccaa5a40a43022d632ab9dbcdcf689ebf413a21f60e33153","last_reissued_at":"2026-07-05T05:53:59.802462Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:53:59.802462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.13251","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":"2026-07-05T05:53:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eYD25S+ZH7H43HaQZM2LuePj977Lqvi+dCV+bt6XsYdUtwjsv0LzZSSE8W60FoKsREmwVfiYDe5P8Cb2LPLCBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T07:22:50.009185Z"},"content_sha256":"1184d8bebb778a0f950a23eee687aa16c02185035d9aa32eee834a20d94433aa","schema_version":"1.0","event_id":"sha256:1184d8bebb778a0f950a23eee687aa16c02185035d9aa32eee834a20d94433aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ID2OIUXNVFGJTTFKLJAKIMBC2Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Bag-of-Prototypes Representation for Dataset-Level Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liang Zheng, Tom Gedeon, Weijian Deng, Weijie Tu","submitted_at":"2023-03-23T13:33:58Z","abstract_excerpt":"This work investigates dataset vectorization for two dataset-level tasks: assessing training set suitability and test set difficulty. The former measures how suitable a training set is for a target domain, while the latter studies how challenging a test set is for a learned model. Central to the two tasks is measuring the underlying relationship between datasets. This needs a desirable dataset vectorization scheme, which should preserve as much discriminative dataset information as possible so that the distance between the resulting dataset vectors can reflect dataset-to-dataset similarity. To"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.13251","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/2303.13251/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":"2026-07-05T05:53:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QmoBUj4npRcj75v5hyREbO6YUlUx8uXKSCAjPB/QBETeRhghbKJwimG++SXk4Rx728jUYWIut7/KxPrHxtfHCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T07:22:50.009685Z"},"content_sha256":"3858074eae930451fefe189d3f812da4ed3a4c94bfec650080ea23274f5301b3","schema_version":"1.0","event_id":"sha256:3858074eae930451fefe189d3f812da4ed3a4c94bfec650080ea23274f5301b3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ID2OIUXNVFGJTTFKLJAKIMBC2Y/bundle.json","state_url":"https://pith.science/pith/ID2OIUXNVFGJTTFKLJAKIMBC2Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ID2OIUXNVFGJTTFKLJAKIMBC2Y/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":"2026-08-01T07:22:50Z","links":{"resolver":"https://pith.science/pith/ID2OIUXNVFGJTTFKLJAKIMBC2Y","bundle":"https://pith.science/pith/ID2OIUXNVFGJTTFKLJAKIMBC2Y/bundle.json","state":"https://pith.science/pith/ID2OIUXNVFGJTTFKLJAKIMBC2Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ID2OIUXNVFGJTTFKLJAKIMBC2Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ID2OIUXNVFGJTTFKLJAKIMBC2Y","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":"a919c60bb753a3b4de5eaa746701ffbe818711ce5bb6eee29e8c2050a123eb6f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-23T13:33:58Z","title_canon_sha256":"7dcd3fc6992c5c146f148cd85a605075b63566ab043ac00ff8e4a15b7fc6a84d"},"schema_version":"1.0","source":{"id":"2303.13251","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.13251","created_at":"2026-07-05T05:53:59Z"},{"alias_kind":"arxiv_version","alias_value":"2303.13251v1","created_at":"2026-07-05T05:53:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.13251","created_at":"2026-07-05T05:53:59Z"},{"alias_kind":"pith_short_12","alias_value":"ID2OIUXNVFGJ","created_at":"2026-07-05T05:53:59Z"},{"alias_kind":"pith_short_16","alias_value":"ID2OIUXNVFGJTTFK","created_at":"2026-07-05T05:53:59Z"},{"alias_kind":"pith_short_8","alias_value":"ID2OIUXN","created_at":"2026-07-05T05:53:59Z"}],"graph_snapshots":[{"event_id":"sha256:3858074eae930451fefe189d3f812da4ed3a4c94bfec650080ea23274f5301b3","target":"graph","created_at":"2026-07-05T05:53:59Z","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/2303.13251/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work investigates dataset vectorization for two dataset-level tasks: assessing training set suitability and test set difficulty. The former measures how suitable a training set is for a target domain, while the latter studies how challenging a test set is for a learned model. Central to the two tasks is measuring the underlying relationship between datasets. This needs a desirable dataset vectorization scheme, which should preserve as much discriminative dataset information as possible so that the distance between the resulting dataset vectors can reflect dataset-to-dataset similarity. To","authors_text":"Liang Zheng, Tom Gedeon, Weijian Deng, Weijie Tu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-23T13:33:58Z","title":"A Bag-of-Prototypes Representation for Dataset-Level Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.13251","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":"sha256:1184d8bebb778a0f950a23eee687aa16c02185035d9aa32eee834a20d94433aa","target":"record","created_at":"2026-07-05T05:53:59Z","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":"a919c60bb753a3b4de5eaa746701ffbe818711ce5bb6eee29e8c2050a123eb6f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-23T13:33:58Z","title_canon_sha256":"7dcd3fc6992c5c146f148cd85a605075b63566ab043ac00ff8e4a15b7fc6a84d"},"schema_version":"1.0","source":{"id":"2303.13251","kind":"arxiv","version":1}},"canonical_sha256":"40f4e452eda94c99ccaa5a40a43022d632ab9dbcdcf689ebf413a21f60e33153","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40f4e452eda94c99ccaa5a40a43022d632ab9dbcdcf689ebf413a21f60e33153","first_computed_at":"2026-07-05T05:53:59.802462Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:53:59.802462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GIuhTJxxAi1JyxKvudZSzEzoxG7zAv/doxWpoJbkudOZNOMoYQOtfQvkNO/THI1NR/Tnx61ymirFBWUz7FDWDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:53:59.802855Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.13251","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1184d8bebb778a0f950a23eee687aa16c02185035d9aa32eee834a20d94433aa","sha256:3858074eae930451fefe189d3f812da4ed3a4c94bfec650080ea23274f5301b3"],"state_sha256":"55522b2f2d07ca4ee90766392e9454e0452cef29a2c91f3d2a8e950aa0eb2a29"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6nJD7AQeIVlodQE19N5awVerYDIzeOPcMnhV/ybdoaBY4g7/ilnmzIDs0wl2vcsCQO3YbHg1QLofN8iV05wiBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T07:22:50.013080Z","bundle_sha256":"0f4d6ed8f63475249f4996ba897198e2ac7289ed7af5fcfae52f9e8c5e5a0b47"}}