{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:Y7NAIPOYEONOQBCG4MQMSHCIFG","short_pith_number":"pith:Y7NAIPOY","canonical_record":{"source":{"id":"1612.02766","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-08T18:46:39Z","cross_cats_sorted":[],"title_canon_sha256":"d988b439498506c3e68d35280a919a20f9c2c7f3b1ff95ea8e0a795292b15a4e","abstract_canon_sha256":"96b502cf262fc3376e2e493976e467c05978e84eb3906add4fdc5e8567d3a299"},"schema_version":"1.0"},"canonical_sha256":"c7da043dd8239ae80446e320c91c48298b78c8ce06d30c801ce26a32566b0698","source":{"kind":"arxiv","id":"1612.02766","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.02766","created_at":"2026-05-18T00:55:29Z"},{"alias_kind":"arxiv_version","alias_value":"1612.02766v1","created_at":"2026-05-18T00:55:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.02766","created_at":"2026-05-18T00:55:29Z"},{"alias_kind":"pith_short_12","alias_value":"Y7NAIPOYEONO","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"Y7NAIPOYEONOQBCG","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"Y7NAIPOY","created_at":"2026-05-18T12:30:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:Y7NAIPOYEONOQBCG4MQMSHCIFG","target":"record","payload":{"canonical_record":{"source":{"id":"1612.02766","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-08T18:46:39Z","cross_cats_sorted":[],"title_canon_sha256":"d988b439498506c3e68d35280a919a20f9c2c7f3b1ff95ea8e0a795292b15a4e","abstract_canon_sha256":"96b502cf262fc3376e2e493976e467c05978e84eb3906add4fdc5e8567d3a299"},"schema_version":"1.0"},"canonical_sha256":"c7da043dd8239ae80446e320c91c48298b78c8ce06d30c801ce26a32566b0698","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:55:29.164960Z","signature_b64":"oAKMc5AGV40y9jTQSZDtkWK+liH9WEtzKYcYzbkde7ZNVtR8suKrne5iuIbcaLWVSHUM5K+M6CG+Iuk09q2UDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7da043dd8239ae80446e320c91c48298b78c8ce06d30c801ce26a32566b0698","last_reissued_at":"2026-05-18T00:55:29.164405Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:55:29.164405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1612.02766","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":"2026-05-18T00:55:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7nCAS1YwoZUVc5z3rIIVvaNb06cUhuYVtAqafpslzi1v8siC1iKIePHDKXzAnniubwpu067gHj5ND/0DsYd+CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T19:00:49.994786Z"},"content_sha256":"f2c60835c0f6eddd01b3cd73f460345d292705506fa4d29d424ecc3e033ce936","schema_version":"1.0","event_id":"sha256:f2c60835c0f6eddd01b3cd73f460345d292705506fa4d29d424ecc3e033ce936"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:Y7NAIPOYEONOQBCG4MQMSHCIFG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Feedback Neural Network for Weakly Supervised Geo-Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amy Zhang, Andreas Gros, Thomas S. Huang, Tobias Tiecke, Xianming Liu","submitted_at":"2016-12-08T18:46:39Z","abstract_excerpt":"Learning from weakly-supervised data is one of the main challenges in machine learning and computer vision, especially for tasks such as image semantic segmentation where labeling is extremely expensive and subjective. In this paper, we propose a novel neural network architecture to perform weakly-supervised learning by suppressing irrelevant neuron activations. It localizes objects of interest by learning from image-level categorical labels in an end-to-end manner. We apply this algorithm to a practical challenge of transforming satellite images into a map of settlements and individual buildi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.02766","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":"2026-05-18T00:55:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PKoq8LZkkv3ijkTXWU8bDdp9bN/Q1U/KCyAwJVWPfGS8LdwePfUUA/8S9d2O48KGAQKvkgXWkvlVmGGcBgiFBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T19:00:49.995536Z"},"content_sha256":"506591c3c41bef725fdee0626b9ea2e4926db1793dcefaf4c3b2ce08dbf469f0","schema_version":"1.0","event_id":"sha256:506591c3c41bef725fdee0626b9ea2e4926db1793dcefaf4c3b2ce08dbf469f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y7NAIPOYEONOQBCG4MQMSHCIFG/bundle.json","state_url":"https://pith.science/pith/Y7NAIPOYEONOQBCG4MQMSHCIFG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y7NAIPOYEONOQBCG4MQMSHCIFG/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":"2026-05-31T19:00:49Z","links":{"resolver":"https://pith.science/pith/Y7NAIPOYEONOQBCG4MQMSHCIFG","bundle":"https://pith.science/pith/Y7NAIPOYEONOQBCG4MQMSHCIFG/bundle.json","state":"https://pith.science/pith/Y7NAIPOYEONOQBCG4MQMSHCIFG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y7NAIPOYEONOQBCG4MQMSHCIFG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:Y7NAIPOYEONOQBCG4MQMSHCIFG","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":"96b502cf262fc3376e2e493976e467c05978e84eb3906add4fdc5e8567d3a299","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-08T18:46:39Z","title_canon_sha256":"d988b439498506c3e68d35280a919a20f9c2c7f3b1ff95ea8e0a795292b15a4e"},"schema_version":"1.0","source":{"id":"1612.02766","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.02766","created_at":"2026-05-18T00:55:29Z"},{"alias_kind":"arxiv_version","alias_value":"1612.02766v1","created_at":"2026-05-18T00:55:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.02766","created_at":"2026-05-18T00:55:29Z"},{"alias_kind":"pith_short_12","alias_value":"Y7NAIPOYEONO","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"Y7NAIPOYEONOQBCG","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"Y7NAIPOY","created_at":"2026-05-18T12:30:53Z"}],"graph_snapshots":[{"event_id":"sha256:506591c3c41bef725fdee0626b9ea2e4926db1793dcefaf4c3b2ce08dbf469f0","target":"graph","created_at":"2026-05-18T00:55:29Z","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":"Learning from weakly-supervised data is one of the main challenges in machine learning and computer vision, especially for tasks such as image semantic segmentation where labeling is extremely expensive and subjective. In this paper, we propose a novel neural network architecture to perform weakly-supervised learning by suppressing irrelevant neuron activations. It localizes objects of interest by learning from image-level categorical labels in an end-to-end manner. We apply this algorithm to a practical challenge of transforming satellite images into a map of settlements and individual buildi","authors_text":"Amy Zhang, Andreas Gros, Thomas S. Huang, Tobias Tiecke, Xianming Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-08T18:46:39Z","title":"Feedback Neural Network for Weakly Supervised Geo-Semantic Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.02766","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:f2c60835c0f6eddd01b3cd73f460345d292705506fa4d29d424ecc3e033ce936","target":"record","created_at":"2026-05-18T00:55:29Z","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":"96b502cf262fc3376e2e493976e467c05978e84eb3906add4fdc5e8567d3a299","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-08T18:46:39Z","title_canon_sha256":"d988b439498506c3e68d35280a919a20f9c2c7f3b1ff95ea8e0a795292b15a4e"},"schema_version":"1.0","source":{"id":"1612.02766","kind":"arxiv","version":1}},"canonical_sha256":"c7da043dd8239ae80446e320c91c48298b78c8ce06d30c801ce26a32566b0698","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7da043dd8239ae80446e320c91c48298b78c8ce06d30c801ce26a32566b0698","first_computed_at":"2026-05-18T00:55:29.164405Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:55:29.164405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oAKMc5AGV40y9jTQSZDtkWK+liH9WEtzKYcYzbkde7ZNVtR8suKrne5iuIbcaLWVSHUM5K+M6CG+Iuk09q2UDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:55:29.164960Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.02766","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2c60835c0f6eddd01b3cd73f460345d292705506fa4d29d424ecc3e033ce936","sha256:506591c3c41bef725fdee0626b9ea2e4926db1793dcefaf4c3b2ce08dbf469f0"],"state_sha256":"e3e7c47f6fd8c6ad200951900bf9bd956b63b8d1a43d222c4091e6ecf2d4d29d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ecRYZp1LvAzPfrk/4lHS94kv4SCCcghPfvzhIsmtQ36Xy5b+gRKEBlqZjgASPQd4/uQT8iYq6lH+oksITUN9BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T19:00:49.999924Z","bundle_sha256":"a9462c3a00736e08b15e5f58425f13b11d4f169475a12b5aeba4be3812546e61"}}