{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:RMMAFYDYZ7HDLDO5GBATWIMHP3","short_pith_number":"pith:RMMAFYDY","canonical_record":{"source":{"id":"1612.01075","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2016-12-04T05:51:55Z","cross_cats_sorted":[],"title_canon_sha256":"751474828344ebc58d28143d21f22e3bd4b7d2e8d6520d4533e679f680bf4f6d","abstract_canon_sha256":"cfaf852ea0231c3fc39a33dad3ea9b68134a3563c7d2a01200db4ca19d1db003"},"schema_version":"1.0"},"canonical_sha256":"8b1802e078cfce358ddd30413b21877ed7de85cf9cc46e1718fabb9f0148c564","source":{"kind":"arxiv","id":"1612.01075","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.01075","created_at":"2026-05-18T00:55:53Z"},{"alias_kind":"arxiv_version","alias_value":"1612.01075v1","created_at":"2026-05-18T00:55:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.01075","created_at":"2026-05-18T00:55:53Z"},{"alias_kind":"pith_short_12","alias_value":"RMMAFYDYZ7HD","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"RMMAFYDYZ7HDLDO5","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"RMMAFYDY","created_at":"2026-05-18T12:30:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:RMMAFYDYZ7HDLDO5GBATWIMHP3","target":"record","payload":{"canonical_record":{"source":{"id":"1612.01075","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2016-12-04T05:51:55Z","cross_cats_sorted":[],"title_canon_sha256":"751474828344ebc58d28143d21f22e3bd4b7d2e8d6520d4533e679f680bf4f6d","abstract_canon_sha256":"cfaf852ea0231c3fc39a33dad3ea9b68134a3563c7d2a01200db4ca19d1db003"},"schema_version":"1.0"},"canonical_sha256":"8b1802e078cfce358ddd30413b21877ed7de85cf9cc46e1718fabb9f0148c564","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:55:53.410926Z","signature_b64":"dwFqCclAp3lFjbjlarrjkqF8XVR30voi4SaUPyDkHbPvvqkieAr4f7u/M2JlnVGisCOuopzM7pFgoIAJiObaBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b1802e078cfce358ddd30413b21877ed7de85cf9cc46e1718fabb9f0148c564","last_reissued_at":"2026-05-18T00:55:53.410567Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:55:53.410567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1612.01075","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":"2026-05-18T00:55:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6sDaOWyEVRAZvDsmDqaPN3DF48H0XfXAX70MvzcM3es5TmVwr/ZbYXwZji/dTSD4nTIGyXJ0IHBK/aDWQ3itBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T20:06:01.641103Z"},"content_sha256":"029d8eb0025ba616126769b14636ec64dac718e12dc26bc93f9aebce4db84b9f","schema_version":"1.0","event_id":"sha256:029d8eb0025ba616126769b14636ec64dac718e12dc26bc93f9aebce4db84b9f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:RMMAFYDYZ7HDLDO5GBATWIMHP3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Joint Visual Denoising and Classification using Deep Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gang Chen, Sargur N. Srihari, Yawei Li","submitted_at":"2016-12-04T05:51:55Z","abstract_excerpt":"Visual restoration and recognition are traditionally addressed in pipeline fashion, i.e. denoising followed by classification. Instead, observing correlations between the two tasks, for example clearer image will lead to better categorization and vice visa, we propose a joint framework for visual restoration and recognition for handwritten images, inspired by advances in deep autoencoder and multi-modality learning. Our model is a 3-pathway deep architecture with a hidden-layer representation which is shared by multi-inputs and outputs, and each branch can be composed of a multi-layer deep mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.01075","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":"2026-05-18T00:55:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lDTWZatUUWUeB7u87UZlkohfgPGQF/VrPA0HKLCQoFsnpvZY4HbhU445NeYIxPVRXI4GoWQhi4cjfN/cgUcACg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T20:06:01.641862Z"},"content_sha256":"a81cb399ed29d61a804ace1cd3fe2df49cfa0012808a1bd06ffb9f4ca6b969c1","schema_version":"1.0","event_id":"sha256:a81cb399ed29d61a804ace1cd3fe2df49cfa0012808a1bd06ffb9f4ca6b969c1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RMMAFYDYZ7HDLDO5GBATWIMHP3/bundle.json","state_url":"https://pith.science/pith/RMMAFYDYZ7HDLDO5GBATWIMHP3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RMMAFYDYZ7HDLDO5GBATWIMHP3/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":"2026-06-11T20:06:01Z","links":{"resolver":"https://pith.science/pith/RMMAFYDYZ7HDLDO5GBATWIMHP3","bundle":"https://pith.science/pith/RMMAFYDYZ7HDLDO5GBATWIMHP3/bundle.json","state":"https://pith.science/pith/RMMAFYDYZ7HDLDO5GBATWIMHP3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RMMAFYDYZ7HDLDO5GBATWIMHP3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:RMMAFYDYZ7HDLDO5GBATWIMHP3","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":"cfaf852ea0231c3fc39a33dad3ea9b68134a3563c7d2a01200db4ca19d1db003","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2016-12-04T05:51:55Z","title_canon_sha256":"751474828344ebc58d28143d21f22e3bd4b7d2e8d6520d4533e679f680bf4f6d"},"schema_version":"1.0","source":{"id":"1612.01075","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.01075","created_at":"2026-05-18T00:55:53Z"},{"alias_kind":"arxiv_version","alias_value":"1612.01075v1","created_at":"2026-05-18T00:55:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.01075","created_at":"2026-05-18T00:55:53Z"},{"alias_kind":"pith_short_12","alias_value":"RMMAFYDYZ7HD","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"RMMAFYDYZ7HDLDO5","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"RMMAFYDY","created_at":"2026-05-18T12:30:41Z"}],"graph_snapshots":[{"event_id":"sha256:a81cb399ed29d61a804ace1cd3fe2df49cfa0012808a1bd06ffb9f4ca6b969c1","target":"graph","created_at":"2026-05-18T00:55:53Z","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":"Visual restoration and recognition are traditionally addressed in pipeline fashion, i.e. denoising followed by classification. Instead, observing correlations between the two tasks, for example clearer image will lead to better categorization and vice visa, we propose a joint framework for visual restoration and recognition for handwritten images, inspired by advances in deep autoencoder and multi-modality learning. Our model is a 3-pathway deep architecture with a hidden-layer representation which is shared by multi-inputs and outputs, and each branch can be composed of a multi-layer deep mod","authors_text":"Gang Chen, Sargur N. Srihari, Yawei Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2016-12-04T05:51:55Z","title":"Joint Visual Denoising and Classification using Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.01075","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":"sha256:029d8eb0025ba616126769b14636ec64dac718e12dc26bc93f9aebce4db84b9f","target":"record","created_at":"2026-05-18T00:55:53Z","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":"cfaf852ea0231c3fc39a33dad3ea9b68134a3563c7d2a01200db4ca19d1db003","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2016-12-04T05:51:55Z","title_canon_sha256":"751474828344ebc58d28143d21f22e3bd4b7d2e8d6520d4533e679f680bf4f6d"},"schema_version":"1.0","source":{"id":"1612.01075","kind":"arxiv","version":1}},"canonical_sha256":"8b1802e078cfce358ddd30413b21877ed7de85cf9cc46e1718fabb9f0148c564","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b1802e078cfce358ddd30413b21877ed7de85cf9cc46e1718fabb9f0148c564","first_computed_at":"2026-05-18T00:55:53.410567Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:55:53.410567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dwFqCclAp3lFjbjlarrjkqF8XVR30voi4SaUPyDkHbPvvqkieAr4f7u/M2JlnVGisCOuopzM7pFgoIAJiObaBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:55:53.410926Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.01075","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:029d8eb0025ba616126769b14636ec64dac718e12dc26bc93f9aebce4db84b9f","sha256:a81cb399ed29d61a804ace1cd3fe2df49cfa0012808a1bd06ffb9f4ca6b969c1"],"state_sha256":"451f924c39f17db46c23acab08f38b884d651f5d5c69dfca25be223d43c22f58"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NIfpA8TeH/MX/7b8S/Ibm8+bMqEtgclXzRlFmdcWYe4CPOFh5ebKQfpzC+RqhBwZ87TdQ0unPwPYlx2+jKyyCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T20:06:01.646007Z","bundle_sha256":"c15d1fcfea5cd01cd2bd81399bc23496298fb92648e6559b59b0e8063c4bb94a"}}