{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:XPM4E4IFKG45PKWXB53E54D3NK","short_pith_number":"pith:XPM4E4IF","canonical_record":{"source":{"id":"1804.04882","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-13T10:52:07Z","cross_cats_sorted":[],"title_canon_sha256":"cc41d5f9c7ecd40c4fa8b4c9c50b02bedb89f60c84b99a9391fc88cb2be27998","abstract_canon_sha256":"761af627e04617d343405a63eadee973561785f954d8898533979a74b1048584"},"schema_version":"1.0"},"canonical_sha256":"bbd9c2710551b9d7aad70f764ef07b6a9741db359133236590d5b27f971a58bb","source":{"kind":"arxiv","id":"1804.04882","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.04882","created_at":"2026-05-17T23:52:59Z"},{"alias_kind":"arxiv_version","alias_value":"1804.04882v2","created_at":"2026-05-17T23:52:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.04882","created_at":"2026-05-17T23:52:59Z"},{"alias_kind":"pith_short_12","alias_value":"XPM4E4IFKG45","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XPM4E4IFKG45PKWX","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XPM4E4IF","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:XPM4E4IFKG45PKWXB53E54D3NK","target":"record","payload":{"canonical_record":{"source":{"id":"1804.04882","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-13T10:52:07Z","cross_cats_sorted":[],"title_canon_sha256":"cc41d5f9c7ecd40c4fa8b4c9c50b02bedb89f60c84b99a9391fc88cb2be27998","abstract_canon_sha256":"761af627e04617d343405a63eadee973561785f954d8898533979a74b1048584"},"schema_version":"1.0"},"canonical_sha256":"bbd9c2710551b9d7aad70f764ef07b6a9741db359133236590d5b27f971a58bb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:59.241990Z","signature_b64":"rkviQnnxrqT76Sz5bUJ92PBK97Vzwy7/Bu4qCDZmxFbPPNciKlPPYmXmwkAkulOZBx4p8/qFNoDFTn4iiDjJBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbd9c2710551b9d7aad70f764ef07b6a9741db359133236590d5b27f971a58bb","last_reissued_at":"2026-05-17T23:52:59.241401Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:59.241401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.04882","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":"2026-05-17T23:52:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fg+EXlWEPukldL787sKBn9jENkNFThDYPLSWtcg7s08ot+GUqU3yXHeugd7x+ssRc5325lZksR6zppzea0DBBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T04:24:53.982145Z"},"content_sha256":"e2aa51a978d40dbae008339327ddc42f232ecf705cff1ab484606fad4909f6cc","schema_version":"1.0","event_id":"sha256:e2aa51a978d40dbae008339327ddc42f232ecf705cff1ab484606fad4909f6cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:XPM4E4IFKG45PKWXB53E54D3NK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Exploit the Prior Network Knowledge for Weakly-Supervised Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Carolina Redondo-Cabrera, Marcos Baptista-R\\'ios, Roberto J. L\\'opez-Sastre","submitted_at":"2018-04-13T10:52:07Z","abstract_excerpt":"Training a Convolutional Neural Network (CNN) for semantic segmentation typically requires to collect a large amount of accurate pixel-level annotations, a hard and expensive task. In contrast, simple image tags are easier to gather. With this paper we introduce a novel weakly-supervised semantic segmentation model able to learn from image labels, and just image labels. Our model uses the prior knowledge of a network trained for image recognition, employing these image annotations as an attention mechanism to identify semantic regions in the images. We then present a methodology that builds ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.04882","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":"2026-05-17T23:52:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"91Pj5GnEu/P8pNl7YK4JbQkqXRwhHUnRiq9XNrl9BCVHH9ncb2ukiTsSB1cXxGsfevZJti/Ka2Pfr8DCzBtdAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T04:24:53.982810Z"},"content_sha256":"f8401149b443c2c37ef9b24d9c8af837ccbeabfaae44e1b8ca5783fa28095975","schema_version":"1.0","event_id":"sha256:f8401149b443c2c37ef9b24d9c8af837ccbeabfaae44e1b8ca5783fa28095975"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XPM4E4IFKG45PKWXB53E54D3NK/bundle.json","state_url":"https://pith.science/pith/XPM4E4IFKG45PKWXB53E54D3NK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XPM4E4IFKG45PKWXB53E54D3NK/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":"2026-05-25T04:24:53Z","links":{"resolver":"https://pith.science/pith/XPM4E4IFKG45PKWXB53E54D3NK","bundle":"https://pith.science/pith/XPM4E4IFKG45PKWXB53E54D3NK/bundle.json","state":"https://pith.science/pith/XPM4E4IFKG45PKWXB53E54D3NK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XPM4E4IFKG45PKWXB53E54D3NK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:XPM4E4IFKG45PKWXB53E54D3NK","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":"761af627e04617d343405a63eadee973561785f954d8898533979a74b1048584","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-13T10:52:07Z","title_canon_sha256":"cc41d5f9c7ecd40c4fa8b4c9c50b02bedb89f60c84b99a9391fc88cb2be27998"},"schema_version":"1.0","source":{"id":"1804.04882","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.04882","created_at":"2026-05-17T23:52:59Z"},{"alias_kind":"arxiv_version","alias_value":"1804.04882v2","created_at":"2026-05-17T23:52:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.04882","created_at":"2026-05-17T23:52:59Z"},{"alias_kind":"pith_short_12","alias_value":"XPM4E4IFKG45","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XPM4E4IFKG45PKWX","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XPM4E4IF","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:f8401149b443c2c37ef9b24d9c8af837ccbeabfaae44e1b8ca5783fa28095975","target":"graph","created_at":"2026-05-17T23:52:59Z","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"},"paper":{"abstract_excerpt":"Training a Convolutional Neural Network (CNN) for semantic segmentation typically requires to collect a large amount of accurate pixel-level annotations, a hard and expensive task. In contrast, simple image tags are easier to gather. With this paper we introduce a novel weakly-supervised semantic segmentation model able to learn from image labels, and just image labels. Our model uses the prior knowledge of a network trained for image recognition, employing these image annotations as an attention mechanism to identify semantic regions in the images. We then present a methodology that builds ac","authors_text":"Carolina Redondo-Cabrera, Marcos Baptista-R\\'ios, Roberto J. L\\'opez-Sastre","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-13T10:52:07Z","title":"Learning to Exploit the Prior Network Knowledge for Weakly-Supervised Semantic Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.04882","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:e2aa51a978d40dbae008339327ddc42f232ecf705cff1ab484606fad4909f6cc","target":"record","created_at":"2026-05-17T23:52:59Z","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":"761af627e04617d343405a63eadee973561785f954d8898533979a74b1048584","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-13T10:52:07Z","title_canon_sha256":"cc41d5f9c7ecd40c4fa8b4c9c50b02bedb89f60c84b99a9391fc88cb2be27998"},"schema_version":"1.0","source":{"id":"1804.04882","kind":"arxiv","version":2}},"canonical_sha256":"bbd9c2710551b9d7aad70f764ef07b6a9741db359133236590d5b27f971a58bb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbd9c2710551b9d7aad70f764ef07b6a9741db359133236590d5b27f971a58bb","first_computed_at":"2026-05-17T23:52:59.241401Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:59.241401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rkviQnnxrqT76Sz5bUJ92PBK97Vzwy7/Bu4qCDZmxFbPPNciKlPPYmXmwkAkulOZBx4p8/qFNoDFTn4iiDjJBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:59.241990Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.04882","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2aa51a978d40dbae008339327ddc42f232ecf705cff1ab484606fad4909f6cc","sha256:f8401149b443c2c37ef9b24d9c8af837ccbeabfaae44e1b8ca5783fa28095975"],"state_sha256":"23755019c25fea39bd1fa337c827088f992428ab8b9d55dd9d0518925de28280"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BHdj5QEYDd8VQyBqRnsmOU9eDVGIE3j6AktmsX5iV/VEYu+tNc9h/v8FzbwiqR6VYRdDo3DlmQi9zafSflrmAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T04:24:53.986253Z","bundle_sha256":"0f1e9cd0ff95da3875b9df5c25d5bb439dd7ae566f2757979fd1bcaa5766878a"}}