{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:PG3SGELX7CPZ5EMY5CAPEPZJHH","short_pith_number":"pith:PG3SGELX","canonical_record":{"source":{"id":"2201.02305","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-07T02:46:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"52f70dfa1448d487a2f3c38b4afef703a1b52e0f6d44c82aaef98ca96be45d9f","abstract_canon_sha256":"3eea5ef3161cb0464de555c196ab70bd060c59eb1560d7c8874bc2e48c9a6281"},"schema_version":"1.0"},"canonical_sha256":"79b7231177f89f9e9198e880f23f2939f62351fbee212eaffaab288bba7340d3","source":{"kind":"arxiv","id":"2201.02305","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.02305","created_at":"2026-07-05T03:46:39Z"},{"alias_kind":"arxiv_version","alias_value":"2201.02305v1","created_at":"2026-07-05T03:46:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.02305","created_at":"2026-07-05T03:46:39Z"},{"alias_kind":"pith_short_12","alias_value":"PG3SGELX7CPZ","created_at":"2026-07-05T03:46:39Z"},{"alias_kind":"pith_short_16","alias_value":"PG3SGELX7CPZ5EMY","created_at":"2026-07-05T03:46:39Z"},{"alias_kind":"pith_short_8","alias_value":"PG3SGELX","created_at":"2026-07-05T03:46:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:PG3SGELX7CPZ5EMY5CAPEPZJHH","target":"record","payload":{"canonical_record":{"source":{"id":"2201.02305","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-07T02:46:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"52f70dfa1448d487a2f3c38b4afef703a1b52e0f6d44c82aaef98ca96be45d9f","abstract_canon_sha256":"3eea5ef3161cb0464de555c196ab70bd060c59eb1560d7c8874bc2e48c9a6281"},"schema_version":"1.0"},"canonical_sha256":"79b7231177f89f9e9198e880f23f2939f62351fbee212eaffaab288bba7340d3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:46:39.874711Z","signature_b64":"3hD4GLRAWbttcAlPs+L32UyscTwmjlUlom57c3/XPB8s32OoKmWI9Jgqs+KYVpFgB8JNrSb+NhQwDT3Gr/vCBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79b7231177f89f9e9198e880f23f2939f62351fbee212eaffaab288bba7340d3","last_reissued_at":"2026-07-05T03:46:39.874213Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:46:39.874213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.02305","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":"2026-07-05T03:46:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2dRmLC2wVSTA56qKaVI59ruMIAAn7r/8KO+6EqI/HtoRCFWRL/j5VVCQuBGcXKpmP8FQqXp7ejEyopch888BCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T14:00:42.870993Z"},"content_sha256":"2c393abdbd77461c0cba41af490a6ee58f454e1a34ec3afa6f28fb84fd53f3e1","schema_version":"1.0","event_id":"sha256:2c393abdbd77461c0cba41af490a6ee58f454e1a34ec3afa6f28fb84fd53f3e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:PG3SGELX7CPZ5EMY5CAPEPZJHH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Multi-Tasks with Inconsistent Labels by using Auxiliary Big Task","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Quan Feng, Songcan Chen","submitted_at":"2022-01-07T02:46:47Z","abstract_excerpt":"Multi-task learning is to improve the performance of the model by transferring and exploiting common knowledge among tasks. Existing MTL works mainly focus on the scenario where label sets among multiple tasks (MTs) are usually the same, thus they can be utilized for learning across the tasks. While almost rare works explore the scenario where each task only has a small amount of training samples, and their label sets are just partially overlapped or even not. Learning such MTs is more challenging because of less correlation information available among these tasks. For this, we propose a frame"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.02305","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/2201.02305/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":"2026-07-05T03:46:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9/mb93mpUmp0tNo12c0bvkUPzllHKYI85zziwvj+yfJahqVnnWTMg8HJh0tQb7BAy74eD5rVF5x13dx4IBaSDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T14:00:42.871511Z"},"content_sha256":"ef032d15e2d8dc908bfa3be1a60d21bb4d7eb3d451fc70b6a3800c947d50fc07","schema_version":"1.0","event_id":"sha256:ef032d15e2d8dc908bfa3be1a60d21bb4d7eb3d451fc70b6a3800c947d50fc07"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PG3SGELX7CPZ5EMY5CAPEPZJHH/bundle.json","state_url":"https://pith.science/pith/PG3SGELX7CPZ5EMY5CAPEPZJHH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PG3SGELX7CPZ5EMY5CAPEPZJHH/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":"2026-08-23T14:00:42Z","links":{"resolver":"https://pith.science/pith/PG3SGELX7CPZ5EMY5CAPEPZJHH","bundle":"https://pith.science/pith/PG3SGELX7CPZ5EMY5CAPEPZJHH/bundle.json","state":"https://pith.science/pith/PG3SGELX7CPZ5EMY5CAPEPZJHH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PG3SGELX7CPZ5EMY5CAPEPZJHH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:PG3SGELX7CPZ5EMY5CAPEPZJHH","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":"3eea5ef3161cb0464de555c196ab70bd060c59eb1560d7c8874bc2e48c9a6281","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-07T02:46:47Z","title_canon_sha256":"52f70dfa1448d487a2f3c38b4afef703a1b52e0f6d44c82aaef98ca96be45d9f"},"schema_version":"1.0","source":{"id":"2201.02305","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.02305","created_at":"2026-07-05T03:46:39Z"},{"alias_kind":"arxiv_version","alias_value":"2201.02305v1","created_at":"2026-07-05T03:46:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.02305","created_at":"2026-07-05T03:46:39Z"},{"alias_kind":"pith_short_12","alias_value":"PG3SGELX7CPZ","created_at":"2026-07-05T03:46:39Z"},{"alias_kind":"pith_short_16","alias_value":"PG3SGELX7CPZ5EMY","created_at":"2026-07-05T03:46:39Z"},{"alias_kind":"pith_short_8","alias_value":"PG3SGELX","created_at":"2026-07-05T03:46:39Z"}],"graph_snapshots":[{"event_id":"sha256:ef032d15e2d8dc908bfa3be1a60d21bb4d7eb3d451fc70b6a3800c947d50fc07","target":"graph","created_at":"2026-07-05T03:46:39Z","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/2201.02305/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-task learning is to improve the performance of the model by transferring and exploiting common knowledge among tasks. Existing MTL works mainly focus on the scenario where label sets among multiple tasks (MTs) are usually the same, thus they can be utilized for learning across the tasks. While almost rare works explore the scenario where each task only has a small amount of training samples, and their label sets are just partially overlapped or even not. Learning such MTs is more challenging because of less correlation information available among these tasks. For this, we propose a frame","authors_text":"Quan Feng, Songcan Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-07T02:46:47Z","title":"Learning Multi-Tasks with Inconsistent Labels by using Auxiliary Big Task"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.02305","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":"sha256:2c393abdbd77461c0cba41af490a6ee58f454e1a34ec3afa6f28fb84fd53f3e1","target":"record","created_at":"2026-07-05T03:46:39Z","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":"3eea5ef3161cb0464de555c196ab70bd060c59eb1560d7c8874bc2e48c9a6281","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-07T02:46:47Z","title_canon_sha256":"52f70dfa1448d487a2f3c38b4afef703a1b52e0f6d44c82aaef98ca96be45d9f"},"schema_version":"1.0","source":{"id":"2201.02305","kind":"arxiv","version":1}},"canonical_sha256":"79b7231177f89f9e9198e880f23f2939f62351fbee212eaffaab288bba7340d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79b7231177f89f9e9198e880f23f2939f62351fbee212eaffaab288bba7340d3","first_computed_at":"2026-07-05T03:46:39.874213Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:46:39.874213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3hD4GLRAWbttcAlPs+L32UyscTwmjlUlom57c3/XPB8s32OoKmWI9Jgqs+KYVpFgB8JNrSb+NhQwDT3Gr/vCBg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:46:39.874711Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.02305","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c393abdbd77461c0cba41af490a6ee58f454e1a34ec3afa6f28fb84fd53f3e1","sha256:ef032d15e2d8dc908bfa3be1a60d21bb4d7eb3d451fc70b6a3800c947d50fc07"],"state_sha256":"6525108ed0bbdba1d35de45027e2874e5c34313726916de05b8f351b7a379997"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yqZuTeRQkB6X4mOzaaU26P3/ddpoCAAdLDSn0OE+ELo51WBLDpjEZD5F0Lx0WXRB+cC/6jGlueDo1VYDqQMrDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T14:00:42.875631Z","bundle_sha256":"86d4e683f444b9d07ca47518c8904e1a0fce625d2462f696dff67e0ccff8b294"}}