{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:NXDGN2T3TKD77LBHPODYV3TOYS","short_pith_number":"pith:NXDGN2T3","canonical_record":{"source":{"id":"1902.09720","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-26T03:52:16Z","cross_cats_sorted":[],"title_canon_sha256":"067f8d290e190c3131e05f4a852074ac9d2df82eb4e445b1e1f3505239f41c5c","abstract_canon_sha256":"51589b02f700a245fc343b0aa6473dd36216a72f2cee5a610b3d1d2150d779ce"},"schema_version":"1.0"},"canonical_sha256":"6dc666ea7b9a87ffac277b878aee6ec4824c1065eb7db9480c380b07a5bec3b2","source":{"kind":"arxiv","id":"1902.09720","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.09720","created_at":"2026-05-17T23:52:35Z"},{"alias_kind":"arxiv_version","alias_value":"1902.09720v1","created_at":"2026-05-17T23:52:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.09720","created_at":"2026-05-17T23:52:35Z"},{"alias_kind":"pith_short_12","alias_value":"NXDGN2T3TKD7","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NXDGN2T3TKD77LBH","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NXDGN2T3","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:NXDGN2T3TKD77LBHPODYV3TOYS","target":"record","payload":{"canonical_record":{"source":{"id":"1902.09720","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-26T03:52:16Z","cross_cats_sorted":[],"title_canon_sha256":"067f8d290e190c3131e05f4a852074ac9d2df82eb4e445b1e1f3505239f41c5c","abstract_canon_sha256":"51589b02f700a245fc343b0aa6473dd36216a72f2cee5a610b3d1d2150d779ce"},"schema_version":"1.0"},"canonical_sha256":"6dc666ea7b9a87ffac277b878aee6ec4824c1065eb7db9480c380b07a5bec3b2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:35.514004Z","signature_b64":"5thHdwqsEeaNAGKmtB+/bVfcKJVn4tm5GcT8057DVW22TYgeJmyF94RSf+v3ZfzAB0wVibsWytR4FWxo7we2Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6dc666ea7b9a87ffac277b878aee6ec4824c1065eb7db9480c380b07a5bec3b2","last_reissued_at":"2026-05-17T23:52:35.513538Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:35.513538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.09720","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":"2026-05-17T23:52:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MJrbdwQBM4OzfSdsrdsoRViazUKHQCDaqxGneB+ddEHlA8A60i7YjBTIDO56nUG6UWmr+iHshLuyJBfsnL8TBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:09:57.755812Z"},"content_sha256":"0f931ab7391ce37c65da7a7082be552249d6d55d18a6b3d5db95008d8c566793","schema_version":"1.0","event_id":"sha256:0f931ab7391ce37c65da7a7082be552249d6d55d18a6b3d5db95008d8c566793"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:NXDGN2T3TKD77LBHPODYV3TOYS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning a Deep ConvNet for Multi-label Classification with Partial Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Greg Mori, Nazanin Mehrasa, Thibaut Durand","submitted_at":"2019-02-26T03:52:16Z","abstract_excerpt":"Deep ConvNets have shown great performance for single-label image classification (e.g. ImageNet), but it is necessary to move beyond the single-label classification task because pictures of everyday life are inherently multi-label. Multi-label classification is a more difficult task than single-label classification because both the input images and output label spaces are more complex. Furthermore, collecting clean multi-label annotations is more difficult to scale-up than single-label annotations. To reduce the annotation cost, we propose to train a model with partial labels i.e. only some la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.09720","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":""},"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":"2026-05-17T23:52:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JRmvtuKJfuW1BmfXIHWgGBB3oZrT6AR6u0h3CUuFylxdeMuEw7rzt+OcNw0otXtCe7goKJj4N6Pw2+iJViGNDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:09:57.756500Z"},"content_sha256":"0e078d9e40f78ed6ffbe42c67d164e7b8859b87eadfa29b79c9e54456113bbca","schema_version":"1.0","event_id":"sha256:0e078d9e40f78ed6ffbe42c67d164e7b8859b87eadfa29b79c9e54456113bbca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NXDGN2T3TKD77LBHPODYV3TOYS/bundle.json","state_url":"https://pith.science/pith/NXDGN2T3TKD77LBHPODYV3TOYS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NXDGN2T3TKD77LBHPODYV3TOYS/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":"2026-05-25T23:09:57Z","links":{"resolver":"https://pith.science/pith/NXDGN2T3TKD77LBHPODYV3TOYS","bundle":"https://pith.science/pith/NXDGN2T3TKD77LBHPODYV3TOYS/bundle.json","state":"https://pith.science/pith/NXDGN2T3TKD77LBHPODYV3TOYS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NXDGN2T3TKD77LBHPODYV3TOYS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:NXDGN2T3TKD77LBHPODYV3TOYS","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":"51589b02f700a245fc343b0aa6473dd36216a72f2cee5a610b3d1d2150d779ce","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-26T03:52:16Z","title_canon_sha256":"067f8d290e190c3131e05f4a852074ac9d2df82eb4e445b1e1f3505239f41c5c"},"schema_version":"1.0","source":{"id":"1902.09720","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.09720","created_at":"2026-05-17T23:52:35Z"},{"alias_kind":"arxiv_version","alias_value":"1902.09720v1","created_at":"2026-05-17T23:52:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.09720","created_at":"2026-05-17T23:52:35Z"},{"alias_kind":"pith_short_12","alias_value":"NXDGN2T3TKD7","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NXDGN2T3TKD77LBH","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NXDGN2T3","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:0e078d9e40f78ed6ffbe42c67d164e7b8859b87eadfa29b79c9e54456113bbca","target":"graph","created_at":"2026-05-17T23:52:35Z","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":"Deep ConvNets have shown great performance for single-label image classification (e.g. ImageNet), but it is necessary to move beyond the single-label classification task because pictures of everyday life are inherently multi-label. Multi-label classification is a more difficult task than single-label classification because both the input images and output label spaces are more complex. Furthermore, collecting clean multi-label annotations is more difficult to scale-up than single-label annotations. To reduce the annotation cost, we propose to train a model with partial labels i.e. only some la","authors_text":"Greg Mori, Nazanin Mehrasa, Thibaut Durand","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-26T03:52:16Z","title":"Learning a Deep ConvNet for Multi-label Classification with Partial Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.09720","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":"sha256:0f931ab7391ce37c65da7a7082be552249d6d55d18a6b3d5db95008d8c566793","target":"record","created_at":"2026-05-17T23:52:35Z","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":"51589b02f700a245fc343b0aa6473dd36216a72f2cee5a610b3d1d2150d779ce","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-26T03:52:16Z","title_canon_sha256":"067f8d290e190c3131e05f4a852074ac9d2df82eb4e445b1e1f3505239f41c5c"},"schema_version":"1.0","source":{"id":"1902.09720","kind":"arxiv","version":1}},"canonical_sha256":"6dc666ea7b9a87ffac277b878aee6ec4824c1065eb7db9480c380b07a5bec3b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6dc666ea7b9a87ffac277b878aee6ec4824c1065eb7db9480c380b07a5bec3b2","first_computed_at":"2026-05-17T23:52:35.513538Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:35.513538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5thHdwqsEeaNAGKmtB+/bVfcKJVn4tm5GcT8057DVW22TYgeJmyF94RSf+v3ZfzAB0wVibsWytR4FWxo7we2Bg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:35.514004Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.09720","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f931ab7391ce37c65da7a7082be552249d6d55d18a6b3d5db95008d8c566793","sha256:0e078d9e40f78ed6ffbe42c67d164e7b8859b87eadfa29b79c9e54456113bbca"],"state_sha256":"18e3f77010a88db214d7a17842e9f1ee77b8a6fb1f79477d4dc2a6e0e29c5919"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yj+Jv6KP6Uv7SJjzJ8Khxba6uQvpKlqBrVh6A/5iUxAAtLJE3m9eG6Ysh5BrPFz8jb4gBnhD7kr5LQVDZV3oAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T23:09:57.760172Z","bundle_sha256":"591e625ca8c04c71dca71609df46082a1287c03878a88d479b5735a5317196c5"}}