{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:IXYYWA7ESV6PDA2ICZKE76N65Z","short_pith_number":"pith:IXYYWA7E","canonical_record":{"source":{"id":"1803.06414","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-16T21:58:51Z","cross_cats_sorted":[],"title_canon_sha256":"0d6b444d041054235b8525c37362abd7c200b4bc721ea7cdcfb2abbfe7b82711","abstract_canon_sha256":"5cdb6e7f9093e4d5bbb9fecba5c7c6a69e10870da8ec5de914bc3b53dc6e9126"},"schema_version":"1.0"},"canonical_sha256":"45f18b03e4957cf1834816544ff9beee4e57a210d67c6e5f4f80638cd9e00157","source":{"kind":"arxiv","id":"1803.06414","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.06414","created_at":"2026-05-18T00:20:45Z"},{"alias_kind":"arxiv_version","alias_value":"1803.06414v1","created_at":"2026-05-18T00:20:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.06414","created_at":"2026-05-18T00:20:45Z"},{"alias_kind":"pith_short_12","alias_value":"IXYYWA7ESV6P","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"IXYYWA7ESV6PDA2I","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"IXYYWA7E","created_at":"2026-05-18T12:32:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:IXYYWA7ESV6PDA2ICZKE76N65Z","target":"record","payload":{"canonical_record":{"source":{"id":"1803.06414","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-16T21:58:51Z","cross_cats_sorted":[],"title_canon_sha256":"0d6b444d041054235b8525c37362abd7c200b4bc721ea7cdcfb2abbfe7b82711","abstract_canon_sha256":"5cdb6e7f9093e4d5bbb9fecba5c7c6a69e10870da8ec5de914bc3b53dc6e9126"},"schema_version":"1.0"},"canonical_sha256":"45f18b03e4957cf1834816544ff9beee4e57a210d67c6e5f4f80638cd9e00157","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:45.959010Z","signature_b64":"Co/3bRia+JdbWrNBoGIrHxPONgoPdXQKa+oUkWedK3Zv15eIDlOCrnXHyaBI79xPcKbOLRAm5rkjiX1z7uTcCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45f18b03e4957cf1834816544ff9beee4e57a210d67c6e5f4f80638cd9e00157","last_reissued_at":"2026-05-18T00:20:45.958591Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:45.958591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.06414","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":"2026-05-18T00:20:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CKLsJt3R9qUNBPwED2lu8pCSq8ZHL4vuttHNHVj2H1Iao9DLN+XGFI+bqBgp7Z5Uo1Zo2oowASjArFsMWsrrDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T00:50:07.148409Z"},"content_sha256":"aa1885489da8ef0a4940f6d78a8757d60e8cb6b5ec775cd6e375c4b3f49ce7a1","schema_version":"1.0","event_id":"sha256:aa1885489da8ef0a4940f6d78a8757d60e8cb6b5ec775cd6e375c4b3f49ce7a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:IXYYWA7ESV6PDA2ICZKE76N65Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Segment via Cut-and-Paste","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jonathan Huang, Matthew Brown, Tal Remez","submitted_at":"2018-03-16T21:58:51Z","abstract_excerpt":"This paper presents a weakly-supervised approach to object instance segmentation. Starting with known or predicted object bounding boxes, we learn object masks by playing a game of cut-and-paste in an adversarial learning setup. A mask generator takes a detection box and Faster R-CNN features, and constructs a segmentation mask that is used to cut-and-paste the object into a new image location. The discriminator tries to distinguish between real objects, and those cut and pasted via the generator, giving a learning signal that leads to improved object masks. We verify our method experimentally"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.06414","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":"2026-05-18T00:20:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"55zXSKiwqk6Gt83xoXRSw8UoXZVD4uJFI1HsWmAmRcCttTKz7X937SxmMj1wwfBoP+4l07lboix6fZAZNi7TBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T00:50:07.148762Z"},"content_sha256":"4841cbde7340130434ef6b75420a7a7fd148b69b1fe0fec87b247eaa9e4387dd","schema_version":"1.0","event_id":"sha256:4841cbde7340130434ef6b75420a7a7fd148b69b1fe0fec87b247eaa9e4387dd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IXYYWA7ESV6PDA2ICZKE76N65Z/bundle.json","state_url":"https://pith.science/pith/IXYYWA7ESV6PDA2ICZKE76N65Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IXYYWA7ESV6PDA2ICZKE76N65Z/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":"2026-05-28T00:50:07Z","links":{"resolver":"https://pith.science/pith/IXYYWA7ESV6PDA2ICZKE76N65Z","bundle":"https://pith.science/pith/IXYYWA7ESV6PDA2ICZKE76N65Z/bundle.json","state":"https://pith.science/pith/IXYYWA7ESV6PDA2ICZKE76N65Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IXYYWA7ESV6PDA2ICZKE76N65Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:IXYYWA7ESV6PDA2ICZKE76N65Z","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":"5cdb6e7f9093e4d5bbb9fecba5c7c6a69e10870da8ec5de914bc3b53dc6e9126","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-16T21:58:51Z","title_canon_sha256":"0d6b444d041054235b8525c37362abd7c200b4bc721ea7cdcfb2abbfe7b82711"},"schema_version":"1.0","source":{"id":"1803.06414","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.06414","created_at":"2026-05-18T00:20:45Z"},{"alias_kind":"arxiv_version","alias_value":"1803.06414v1","created_at":"2026-05-18T00:20:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.06414","created_at":"2026-05-18T00:20:45Z"},{"alias_kind":"pith_short_12","alias_value":"IXYYWA7ESV6P","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"IXYYWA7ESV6PDA2I","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"IXYYWA7E","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:4841cbde7340130434ef6b75420a7a7fd148b69b1fe0fec87b247eaa9e4387dd","target":"graph","created_at":"2026-05-18T00:20:45Z","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":"This paper presents a weakly-supervised approach to object instance segmentation. Starting with known or predicted object bounding boxes, we learn object masks by playing a game of cut-and-paste in an adversarial learning setup. A mask generator takes a detection box and Faster R-CNN features, and constructs a segmentation mask that is used to cut-and-paste the object into a new image location. The discriminator tries to distinguish between real objects, and those cut and pasted via the generator, giving a learning signal that leads to improved object masks. We verify our method experimentally","authors_text":"Jonathan Huang, Matthew Brown, Tal Remez","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-16T21:58:51Z","title":"Learning to Segment via Cut-and-Paste"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.06414","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:aa1885489da8ef0a4940f6d78a8757d60e8cb6b5ec775cd6e375c4b3f49ce7a1","target":"record","created_at":"2026-05-18T00:20:45Z","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":"5cdb6e7f9093e4d5bbb9fecba5c7c6a69e10870da8ec5de914bc3b53dc6e9126","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-16T21:58:51Z","title_canon_sha256":"0d6b444d041054235b8525c37362abd7c200b4bc721ea7cdcfb2abbfe7b82711"},"schema_version":"1.0","source":{"id":"1803.06414","kind":"arxiv","version":1}},"canonical_sha256":"45f18b03e4957cf1834816544ff9beee4e57a210d67c6e5f4f80638cd9e00157","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45f18b03e4957cf1834816544ff9beee4e57a210d67c6e5f4f80638cd9e00157","first_computed_at":"2026-05-18T00:20:45.958591Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:20:45.958591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Co/3bRia+JdbWrNBoGIrHxPONgoPdXQKa+oUkWedK3Zv15eIDlOCrnXHyaBI79xPcKbOLRAm5rkjiX1z7uTcCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:20:45.959010Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.06414","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa1885489da8ef0a4940f6d78a8757d60e8cb6b5ec775cd6e375c4b3f49ce7a1","sha256:4841cbde7340130434ef6b75420a7a7fd148b69b1fe0fec87b247eaa9e4387dd"],"state_sha256":"ee7785c33c607a3be5e649ad8646a9c9473191b5e9e517b020b41532ab45717a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uoQ9AVKgSNE87A0BOkxBU90AQ1BqNPptYzJrw43FwEEMqC8tfuW06n3VCmgOfKkrEl2T6ldxSlSOOQw+Ub9qBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T00:50:07.150702Z","bundle_sha256":"26a84788bf7ce9a0142272e57089ab5f93da3f9c639ddb5845ae96f9257aae41"}}