{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:N33DAKGD7WNHYRC3X76VFPHLKS","short_pith_number":"pith:N33DAKGD","canonical_record":{"source":{"id":"1907.03402","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-08T04:36:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"23b20de94171527d636548d53e5820aee151c54fd9a29f2941189d2ddeac4f75","abstract_canon_sha256":"23900a66c12fdce11bbe8f4cd8082f71045597031a31187a7cf9994cbaf38ad7"},"schema_version":"1.0"},"canonical_sha256":"6ef63028c3fd9a7c445bbffd52bceb54a74175a6333cfc689b40b371992ddb1c","source":{"kind":"arxiv","id":"1907.03402","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.03402","created_at":"2026-05-17T23:41:06Z"},{"alias_kind":"arxiv_version","alias_value":"1907.03402v2","created_at":"2026-05-17T23:41:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.03402","created_at":"2026-05-17T23:41:06Z"},{"alias_kind":"pith_short_12","alias_value":"N33DAKGD7WNH","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"N33DAKGD7WNHYRC3","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"N33DAKGD","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:N33DAKGD7WNHYRC3X76VFPHLKS","target":"record","payload":{"canonical_record":{"source":{"id":"1907.03402","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-08T04:36:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"23b20de94171527d636548d53e5820aee151c54fd9a29f2941189d2ddeac4f75","abstract_canon_sha256":"23900a66c12fdce11bbe8f4cd8082f71045597031a31187a7cf9994cbaf38ad7"},"schema_version":"1.0"},"canonical_sha256":"6ef63028c3fd9a7c445bbffd52bceb54a74175a6333cfc689b40b371992ddb1c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:06.945764Z","signature_b64":"K59sZSDo8cDARc83d00DoNKI3gLxi3gzDJ7MsgUT0Twptpa7fnqVVsZ2b9MY2vZARM3/l0MRQuV8YuvpL6i9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ef63028c3fd9a7c445bbffd52bceb54a74175a6333cfc689b40b371992ddb1c","last_reissued_at":"2026-05-17T23:41:06.945061Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:06.945061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.03402","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":"2026-05-17T23:41:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MdTjv6XIwgdtuPGks4hj/TCM5kAmRMNA8mjb2EdqH45Xbr10eO3jkHL+Eph7vIu8CT8k/F3eVXuO1dBhacwyBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T10:43:46.248706Z"},"content_sha256":"365eaa71af747642d9e1ed6f346469dd242eaadd510e856731a090537d146e37","schema_version":"1.0","event_id":"sha256:365eaa71af747642d9e1ed6f346469dd242eaadd510e856731a090537d146e37"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:N33DAKGD7WNHYRC3X76VFPHLKS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distill-2MD-MTL: Data Distillation based on Multi-Dataset Multi-Domain Multi-Task Frame Work to Solve Face Related Tasksks, Multi Task Learning, Semi-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Mohammad Amin Shabani, Nam Ik Cho, Sepidehsadat Hosseini","submitted_at":"2019-07-08T04:36:32Z","abstract_excerpt":"We propose a new semi-supervised learning method on face-related tasks based on Multi-Task Learning (MTL) and data distillation. The proposed method exploits multiple datasets with different labels for different-but-related tasks such as simultaneous age, gender, race, facial expression estimation. Specifically, when there are only a few well-labeled data for a specific task among the multiple related ones, we exploit the labels of other related tasks in different domains. Our approach is composed of (1) a new MTL method which can deal with weakly labeled datasets and perform several tasks sim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.03402","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":""},"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":"2026-05-17T23:41:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sOgAK5ne3VEnFEeMsdbdCayhnMmBd16yKAGQYz+ti6U+MBEv/WmbFaKwXnRdEw+cDpO/D5338hKbFEZ6855HCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T10:43:46.249056Z"},"content_sha256":"a9f94d23b5ae708b8532cdcf20d3956431554c0e9707b4a34357a1224a87a103","schema_version":"1.0","event_id":"sha256:a9f94d23b5ae708b8532cdcf20d3956431554c0e9707b4a34357a1224a87a103"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N33DAKGD7WNHYRC3X76VFPHLKS/bundle.json","state_url":"https://pith.science/pith/N33DAKGD7WNHYRC3X76VFPHLKS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N33DAKGD7WNHYRC3X76VFPHLKS/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":"2026-05-20T10:43:46Z","links":{"resolver":"https://pith.science/pith/N33DAKGD7WNHYRC3X76VFPHLKS","bundle":"https://pith.science/pith/N33DAKGD7WNHYRC3X76VFPHLKS/bundle.json","state":"https://pith.science/pith/N33DAKGD7WNHYRC3X76VFPHLKS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N33DAKGD7WNHYRC3X76VFPHLKS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:N33DAKGD7WNHYRC3X76VFPHLKS","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":"23900a66c12fdce11bbe8f4cd8082f71045597031a31187a7cf9994cbaf38ad7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-08T04:36:32Z","title_canon_sha256":"23b20de94171527d636548d53e5820aee151c54fd9a29f2941189d2ddeac4f75"},"schema_version":"1.0","source":{"id":"1907.03402","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.03402","created_at":"2026-05-17T23:41:06Z"},{"alias_kind":"arxiv_version","alias_value":"1907.03402v2","created_at":"2026-05-17T23:41:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.03402","created_at":"2026-05-17T23:41:06Z"},{"alias_kind":"pith_short_12","alias_value":"N33DAKGD7WNH","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"N33DAKGD7WNHYRC3","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"N33DAKGD","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:a9f94d23b5ae708b8532cdcf20d3956431554c0e9707b4a34357a1224a87a103","target":"graph","created_at":"2026-05-17T23:41:06Z","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"},"paper":{"abstract_excerpt":"We propose a new semi-supervised learning method on face-related tasks based on Multi-Task Learning (MTL) and data distillation. The proposed method exploits multiple datasets with different labels for different-but-related tasks such as simultaneous age, gender, race, facial expression estimation. Specifically, when there are only a few well-labeled data for a specific task among the multiple related ones, we exploit the labels of other related tasks in different domains. Our approach is composed of (1) a new MTL method which can deal with weakly labeled datasets and perform several tasks sim","authors_text":"Mohammad Amin Shabani, Nam Ik Cho, Sepidehsadat Hosseini","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-08T04:36:32Z","title":"Distill-2MD-MTL: Data Distillation based on Multi-Dataset Multi-Domain Multi-Task Frame Work to Solve Face Related Tasksks, Multi Task Learning, Semi-Supervised Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.03402","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":"sha256:365eaa71af747642d9e1ed6f346469dd242eaadd510e856731a090537d146e37","target":"record","created_at":"2026-05-17T23:41:06Z","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":"23900a66c12fdce11bbe8f4cd8082f71045597031a31187a7cf9994cbaf38ad7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-08T04:36:32Z","title_canon_sha256":"23b20de94171527d636548d53e5820aee151c54fd9a29f2941189d2ddeac4f75"},"schema_version":"1.0","source":{"id":"1907.03402","kind":"arxiv","version":2}},"canonical_sha256":"6ef63028c3fd9a7c445bbffd52bceb54a74175a6333cfc689b40b371992ddb1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ef63028c3fd9a7c445bbffd52bceb54a74175a6333cfc689b40b371992ddb1c","first_computed_at":"2026-05-17T23:41:06.945061Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:06.945061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K59sZSDo8cDARc83d00DoNKI3gLxi3gzDJ7MsgUT0Twptpa7fnqVVsZ2b9MY2vZARM3/l0MRQuV8YuvpL6i9Cw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:06.945764Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.03402","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:365eaa71af747642d9e1ed6f346469dd242eaadd510e856731a090537d146e37","sha256:a9f94d23b5ae708b8532cdcf20d3956431554c0e9707b4a34357a1224a87a103"],"state_sha256":"7c12aca2946de1ebcce3ca56e61164b30b89be463d83a99730a0db5ee8250cab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qlZivM56fzEJYRI4zA4J4aa5rTQqA5UFEj6WIXJXBKxIhQRiFL0V4NgUotp852BcHMf3h7Qxt5s+qiivgAPeDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T10:43:46.251086Z","bundle_sha256":"8547aa1fb733cbbb290c20486dcc6a147246b626326ecf54d08f34afc67827c8"}}