{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:YDLQ5T5MP3HQRLFJRESKMLRNZN","short_pith_number":"pith:YDLQ5T5M","canonical_record":{"source":{"id":"1506.03648","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-06-11T12:30:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8c60c8e0b8e0f7c5a74c176fafc02a9e052be719a79fe2016071688d98c8cb34","abstract_canon_sha256":"c55607cd1533c5489be245964b4fe38156aecfbcc9355c7752dbbbdefeba2d25"},"schema_version":"1.0"},"canonical_sha256":"c0d70ecfac7ecf08aca98924a62e2dcb515e25dca72218fb41f8f3eb0d61ff0d","source":{"kind":"arxiv","id":"1506.03648","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.03648","created_at":"2026-05-18T01:29:54Z"},{"alias_kind":"arxiv_version","alias_value":"1506.03648v2","created_at":"2026-05-18T01:29:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.03648","created_at":"2026-05-18T01:29:54Z"},{"alias_kind":"pith_short_12","alias_value":"YDLQ5T5MP3HQ","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_16","alias_value":"YDLQ5T5MP3HQRLFJ","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_8","alias_value":"YDLQ5T5M","created_at":"2026-05-18T12:29:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:YDLQ5T5MP3HQRLFJRESKMLRNZN","target":"record","payload":{"canonical_record":{"source":{"id":"1506.03648","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-06-11T12:30:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8c60c8e0b8e0f7c5a74c176fafc02a9e052be719a79fe2016071688d98c8cb34","abstract_canon_sha256":"c55607cd1533c5489be245964b4fe38156aecfbcc9355c7752dbbbdefeba2d25"},"schema_version":"1.0"},"canonical_sha256":"c0d70ecfac7ecf08aca98924a62e2dcb515e25dca72218fb41f8f3eb0d61ff0d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:29:54.035528Z","signature_b64":"QoUBSEedJKhuSuWRYnbvFyGHLKtyY2e/djsohPjV73fScvr2uWDz7dPCTRc43gs4gf5GAFkUlBLs4b2vrlaDCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0d70ecfac7ecf08aca98924a62e2dcb515e25dca72218fb41f8f3eb0d61ff0d","last_reissued_at":"2026-05-18T01:29:54.034973Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:29:54.034973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1506.03648","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":"2026-05-18T01:29:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tHGi4O4+Yy/7GtqIdcmHdFZQFKybNDGL3ufpYb+sgfS6cgCPQqv+lv4Pi/6J/vj3k4+enL6MA8uPT9rBUALVDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T23:15:04.224515Z"},"content_sha256":"bebd035e317d3a8d6d154c178dc533bd6b68253ecac18ef465226e788e9e38e9","schema_version":"1.0","event_id":"sha256:bebd035e317d3a8d6d154c178dc533bd6b68253ecac18ef465226e788e9e38e9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:YDLQ5T5MP3HQRLFJRESKMLRNZN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Constrained Convolutional Neural Networks for Weakly Supervised Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Deepak Pathak, Philipp Kr\\\"ahenb\\\"uhl, Trevor Darrell","submitted_at":"2015-06-11T12:30:17Z","abstract_excerpt":"We present an approach to learn a dense pixel-wise labeling from image-level tags. Each image-level tag imposes constraints on the output labeling of a Convolutional Neural Network (CNN) classifier. We propose Constrained CNN (CCNN), a method which uses a novel loss function to optimize for any set of linear constraints on the output space (i.e. predicted label distribution) of a CNN. Our loss formulation is easy to optimize and can be incorporated directly into standard stochastic gradient descent optimization. The key idea is to phrase the training objective as a biconvex optimization for li"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.03648","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":"2026-05-18T01:29:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MCtJQO/nejfjLf5QVzyXuozOpvgwZkyo94qqgqDLkVPV5qAOf9Bd+qoy53/5pe7n6n3JzmXA/5995Hqzh0OpCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T23:15:04.224911Z"},"content_sha256":"bbc8da1e09dd645ff1efb51068cc7419dd93d8d46883cf513c8b0a050cb5e84b","schema_version":"1.0","event_id":"sha256:bbc8da1e09dd645ff1efb51068cc7419dd93d8d46883cf513c8b0a050cb5e84b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YDLQ5T5MP3HQRLFJRESKMLRNZN/bundle.json","state_url":"https://pith.science/pith/YDLQ5T5MP3HQRLFJRESKMLRNZN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YDLQ5T5MP3HQRLFJRESKMLRNZN/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":"2026-06-11T23:15:04Z","links":{"resolver":"https://pith.science/pith/YDLQ5T5MP3HQRLFJRESKMLRNZN","bundle":"https://pith.science/pith/YDLQ5T5MP3HQRLFJRESKMLRNZN/bundle.json","state":"https://pith.science/pith/YDLQ5T5MP3HQRLFJRESKMLRNZN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YDLQ5T5MP3HQRLFJRESKMLRNZN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:YDLQ5T5MP3HQRLFJRESKMLRNZN","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":"c55607cd1533c5489be245964b4fe38156aecfbcc9355c7752dbbbdefeba2d25","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-06-11T12:30:17Z","title_canon_sha256":"8c60c8e0b8e0f7c5a74c176fafc02a9e052be719a79fe2016071688d98c8cb34"},"schema_version":"1.0","source":{"id":"1506.03648","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.03648","created_at":"2026-05-18T01:29:54Z"},{"alias_kind":"arxiv_version","alias_value":"1506.03648v2","created_at":"2026-05-18T01:29:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.03648","created_at":"2026-05-18T01:29:54Z"},{"alias_kind":"pith_short_12","alias_value":"YDLQ5T5MP3HQ","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_16","alias_value":"YDLQ5T5MP3HQRLFJ","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_8","alias_value":"YDLQ5T5M","created_at":"2026-05-18T12:29:50Z"}],"graph_snapshots":[{"event_id":"sha256:bbc8da1e09dd645ff1efb51068cc7419dd93d8d46883cf513c8b0a050cb5e84b","target":"graph","created_at":"2026-05-18T01:29:54Z","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 present an approach to learn a dense pixel-wise labeling from image-level tags. Each image-level tag imposes constraints on the output labeling of a Convolutional Neural Network (CNN) classifier. We propose Constrained CNN (CCNN), a method which uses a novel loss function to optimize for any set of linear constraints on the output space (i.e. predicted label distribution) of a CNN. Our loss formulation is easy to optimize and can be incorporated directly into standard stochastic gradient descent optimization. The key idea is to phrase the training objective as a biconvex optimization for li","authors_text":"Deepak Pathak, Philipp Kr\\\"ahenb\\\"uhl, Trevor Darrell","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-06-11T12:30:17Z","title":"Constrained Convolutional Neural Networks for Weakly Supervised Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.03648","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:bebd035e317d3a8d6d154c178dc533bd6b68253ecac18ef465226e788e9e38e9","target":"record","created_at":"2026-05-18T01:29:54Z","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":"c55607cd1533c5489be245964b4fe38156aecfbcc9355c7752dbbbdefeba2d25","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-06-11T12:30:17Z","title_canon_sha256":"8c60c8e0b8e0f7c5a74c176fafc02a9e052be719a79fe2016071688d98c8cb34"},"schema_version":"1.0","source":{"id":"1506.03648","kind":"arxiv","version":2}},"canonical_sha256":"c0d70ecfac7ecf08aca98924a62e2dcb515e25dca72218fb41f8f3eb0d61ff0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0d70ecfac7ecf08aca98924a62e2dcb515e25dca72218fb41f8f3eb0d61ff0d","first_computed_at":"2026-05-18T01:29:54.034973Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:29:54.034973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QoUBSEedJKhuSuWRYnbvFyGHLKtyY2e/djsohPjV73fScvr2uWDz7dPCTRc43gs4gf5GAFkUlBLs4b2vrlaDCw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:29:54.035528Z","signed_message":"canonical_sha256_bytes"},"source_id":"1506.03648","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bebd035e317d3a8d6d154c178dc533bd6b68253ecac18ef465226e788e9e38e9","sha256:bbc8da1e09dd645ff1efb51068cc7419dd93d8d46883cf513c8b0a050cb5e84b"],"state_sha256":"83776e2b0038f1e7de8c06dd4321e635c698cf6530d36dfd01dc847e62aa2211"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DMGVYrstQTyn3iP5IDLFCwwrh/OuqDd75tUos1Y6EfhkION0kP5mECzBkbtcnJqOo+ntDqx+EmVI0BLn5TvKAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T23:15:04.227650Z","bundle_sha256":"45af0db398b62c0a0deddf3bcbfa8930baf837863b0b1bf06c14934bc51118b5"}}