{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:Q6EFXSP3UGNGTWCZISSJKW6IRH","short_pith_number":"pith:Q6EFXSP3","canonical_record":{"source":{"id":"1803.09569","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-26T13:14:58Z","cross_cats_sorted":[],"title_canon_sha256":"6ac76d7f9eb02ebfeaeb8ca163d61af5920b790211252f3d1def00d1ac9884d0","abstract_canon_sha256":"e04c17b40f3dd6730829c463f2d9e2c7c8c5c26cdae3c67ca4d5e9cbb4cd65dc"},"schema_version":"1.0"},"canonical_sha256":"87885bc9fba19a69d85944a4955bc889de55ebdf0f333d8ec2eaf34bee1a51a0","source":{"kind":"arxiv","id":"1803.09569","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.09569","created_at":"2026-05-18T00:18:45Z"},{"alias_kind":"arxiv_version","alias_value":"1803.09569v2","created_at":"2026-05-18T00:18:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09569","created_at":"2026-05-18T00:18:45Z"},{"alias_kind":"pith_short_12","alias_value":"Q6EFXSP3UGNG","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"Q6EFXSP3UGNGTWCZ","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"Q6EFXSP3","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:Q6EFXSP3UGNGTWCZISSJKW6IRH","target":"record","payload":{"canonical_record":{"source":{"id":"1803.09569","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-26T13:14:58Z","cross_cats_sorted":[],"title_canon_sha256":"6ac76d7f9eb02ebfeaeb8ca163d61af5920b790211252f3d1def00d1ac9884d0","abstract_canon_sha256":"e04c17b40f3dd6730829c463f2d9e2c7c8c5c26cdae3c67ca4d5e9cbb4cd65dc"},"schema_version":"1.0"},"canonical_sha256":"87885bc9fba19a69d85944a4955bc889de55ebdf0f333d8ec2eaf34bee1a51a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:45.525326Z","signature_b64":"vC2nSIfdabf6jQR8Ro1LgsRyIE46x06OcTg6gJ+0jHT2iLfi46w2n3IYQR3QhjLaivhvN4vOioO0pXg6vCURBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87885bc9fba19a69d85944a4955bc889de55ebdf0f333d8ec2eaf34bee1a51a0","last_reissued_at":"2026-05-18T00:18:45.524886Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:45.524886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.09569","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":"2026-05-18T00:18:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vSxXeON1XgI+n93yY5P7yqrBPVwsnrvXZ7YeIGb2M9TEh3YB1lnejG2PQ3MC3+J5KPCMZegNUNHxNMBMsOV3DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T03:54:32.388282Z"},"content_sha256":"e466495076f22403a3246dee5cfe44f54bf079792fb56424b37071e56454e3e7","schema_version":"1.0","event_id":"sha256:e466495076f22403a3246dee5cfe44f54bf079792fb56424b37071e56454e3e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:Q6EFXSP3UGNGTWCZISSJKW6IRH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Regularized Losses for Weakly-supervised CNN Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdelaziz Djelouah, Christopher Schroers, Federico Perazzi, Ismail Ben Ayed, Meng Tang, Yuri Boykov","submitted_at":"2018-03-26T13:14:58Z","abstract_excerpt":"Minimization of regularized losses is a principled approach to weak supervision well-established in deep learning, in general. However, it is largely overlooked in semantic segmentation currently dominated by methods mimicking full supervision via \"fake\" fully-labeled training masks (proposals) generated from available partial input. To obtain such full masks the typical methods explicitly use standard regularization techniques for \"shallow\" segmentation, e.g. graph cuts or dense CRFs. In contrast, we integrate such standard regularizers directly into the loss functions over partial input. Thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09569","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":"2026-05-18T00:18:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pvV44cRo+HO4o7O87iYceLoM6yZ9xfQ8UF0maSjOCCKnyNoFA/76g7zRPHdMLY4XK7DfCsWSLPy0G+QenVscBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T03:54:32.388661Z"},"content_sha256":"d7d9d03ccc6f7cf558df8d5ae2e2a8d3af6ccdd0f8702955d96784884e6bdc74","schema_version":"1.0","event_id":"sha256:d7d9d03ccc6f7cf558df8d5ae2e2a8d3af6ccdd0f8702955d96784884e6bdc74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q6EFXSP3UGNGTWCZISSJKW6IRH/bundle.json","state_url":"https://pith.science/pith/Q6EFXSP3UGNGTWCZISSJKW6IRH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q6EFXSP3UGNGTWCZISSJKW6IRH/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":"2026-06-01T03:54:32Z","links":{"resolver":"https://pith.science/pith/Q6EFXSP3UGNGTWCZISSJKW6IRH","bundle":"https://pith.science/pith/Q6EFXSP3UGNGTWCZISSJKW6IRH/bundle.json","state":"https://pith.science/pith/Q6EFXSP3UGNGTWCZISSJKW6IRH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q6EFXSP3UGNGTWCZISSJKW6IRH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:Q6EFXSP3UGNGTWCZISSJKW6IRH","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":"e04c17b40f3dd6730829c463f2d9e2c7c8c5c26cdae3c67ca4d5e9cbb4cd65dc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-26T13:14:58Z","title_canon_sha256":"6ac76d7f9eb02ebfeaeb8ca163d61af5920b790211252f3d1def00d1ac9884d0"},"schema_version":"1.0","source":{"id":"1803.09569","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.09569","created_at":"2026-05-18T00:18:45Z"},{"alias_kind":"arxiv_version","alias_value":"1803.09569v2","created_at":"2026-05-18T00:18:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09569","created_at":"2026-05-18T00:18:45Z"},{"alias_kind":"pith_short_12","alias_value":"Q6EFXSP3UGNG","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"Q6EFXSP3UGNGTWCZ","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"Q6EFXSP3","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:d7d9d03ccc6f7cf558df8d5ae2e2a8d3af6ccdd0f8702955d96784884e6bdc74","target":"graph","created_at":"2026-05-18T00:18:45Z","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":"Minimization of regularized losses is a principled approach to weak supervision well-established in deep learning, in general. However, it is largely overlooked in semantic segmentation currently dominated by methods mimicking full supervision via \"fake\" fully-labeled training masks (proposals) generated from available partial input. To obtain such full masks the typical methods explicitly use standard regularization techniques for \"shallow\" segmentation, e.g. graph cuts or dense CRFs. In contrast, we integrate such standard regularizers directly into the loss functions over partial input. Thi","authors_text":"Abdelaziz Djelouah, Christopher Schroers, Federico Perazzi, Ismail Ben Ayed, Meng Tang, Yuri Boykov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-26T13:14:58Z","title":"On Regularized Losses for Weakly-supervised CNN Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09569","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:e466495076f22403a3246dee5cfe44f54bf079792fb56424b37071e56454e3e7","target":"record","created_at":"2026-05-18T00:18:45Z","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":"e04c17b40f3dd6730829c463f2d9e2c7c8c5c26cdae3c67ca4d5e9cbb4cd65dc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-26T13:14:58Z","title_canon_sha256":"6ac76d7f9eb02ebfeaeb8ca163d61af5920b790211252f3d1def00d1ac9884d0"},"schema_version":"1.0","source":{"id":"1803.09569","kind":"arxiv","version":2}},"canonical_sha256":"87885bc9fba19a69d85944a4955bc889de55ebdf0f333d8ec2eaf34bee1a51a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87885bc9fba19a69d85944a4955bc889de55ebdf0f333d8ec2eaf34bee1a51a0","first_computed_at":"2026-05-18T00:18:45.524886Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:18:45.524886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vC2nSIfdabf6jQR8Ro1LgsRyIE46x06OcTg6gJ+0jHT2iLfi46w2n3IYQR3QhjLaivhvN4vOioO0pXg6vCURBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:18:45.525326Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.09569","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e466495076f22403a3246dee5cfe44f54bf079792fb56424b37071e56454e3e7","sha256:d7d9d03ccc6f7cf558df8d5ae2e2a8d3af6ccdd0f8702955d96784884e6bdc74"],"state_sha256":"b7864075ff253ebcd739defa666cb6faca3b0251338d378f845438be7aed0111"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XFoHMYM1JMtfT43ByYEs5r+cGq+vCs01oJ8z1oRyYwHI906pLdwmaK0z9PQWMZWUAowHkMmOtKJ05A7kbbVACA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T03:54:32.390655Z","bundle_sha256":"4435d0f1fa69c61d58f913910271d1268b8c0350d7c2e2e9e540cab34862c0a7"}}