{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:4L6DU36DHH7ROB47W33CRQMHCM","short_pith_number":"pith:4L6DU36D","canonical_record":{"source":{"id":"2002.06583","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-16T14:03:06Z","cross_cats_sorted":[],"title_canon_sha256":"7c43f098ae50b198fc17c2333b957bf28df0c497e45bf8f5ada871e075f06fe7","abstract_canon_sha256":"76fab61f70634bd6fdd277b1d97832f280939513a289437dca2ded33b98a7cb7"},"schema_version":"1.0"},"canonical_sha256":"e2fc3a6fc339ff17079fb6f628c187130b5348983d93d89b7bff068b69b32545","source":{"kind":"arxiv","id":"2002.06583","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.06583","created_at":"2026-07-05T00:41:07Z"},{"alias_kind":"arxiv_version","alias_value":"2002.06583v1","created_at":"2026-07-05T00:41:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06583","created_at":"2026-07-05T00:41:07Z"},{"alias_kind":"pith_short_12","alias_value":"4L6DU36DHH7R","created_at":"2026-07-05T00:41:07Z"},{"alias_kind":"pith_short_16","alias_value":"4L6DU36DHH7ROB47","created_at":"2026-07-05T00:41:07Z"},{"alias_kind":"pith_short_8","alias_value":"4L6DU36D","created_at":"2026-07-05T00:41:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:4L6DU36DHH7ROB47W33CRQMHCM","target":"record","payload":{"canonical_record":{"source":{"id":"2002.06583","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-16T14:03:06Z","cross_cats_sorted":[],"title_canon_sha256":"7c43f098ae50b198fc17c2333b957bf28df0c497e45bf8f5ada871e075f06fe7","abstract_canon_sha256":"76fab61f70634bd6fdd277b1d97832f280939513a289437dca2ded33b98a7cb7"},"schema_version":"1.0"},"canonical_sha256":"e2fc3a6fc339ff17079fb6f628c187130b5348983d93d89b7bff068b69b32545","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:41:07.412605Z","signature_b64":"8Yu1lNqF2h4UZIu88zAT4B7rfUUOKb2BubBZ3PpgNB9/rkOVxER2DX4GtJJDRCPukpu+2g6VsAClOlgLbQqwCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2fc3a6fc339ff17079fb6f628c187130b5348983d93d89b7bff068b69b32545","last_reissued_at":"2026-07-05T00:41:07.412159Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:41:07.412159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.06583","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":"2026-07-05T00:41:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bmTYlwsy6hl2jvTIgE50h17Ja27LIYrKX/DoJzg5rRPO8aomWSI8C45vtvR7d6C/QFt9SrSzq/SGZZ/LBDZzDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:56:13.342537Z"},"content_sha256":"69554631a121d944acc6bb0a83fea0beb3383ec849f3934c854c0ac800c09d52","schema_version":"1.0","event_id":"sha256:69554631a121d944acc6bb0a83fea0beb3383ec849f3934c854c0ac800c09d52"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:4L6DU36DHH7ROB47W33CRQMHCM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforced active learning for image segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arantxa Casanova, Christopher J. Pal, Negar Rostamzadeh, Pedro O. Pinheiro","submitted_at":"2020-02-16T14:03:06Z","abstract_excerpt":"Learning-based approaches for semantic segmentation have two inherent challenges. First, acquiring pixel-wise labels is expensive and time-consuming. Second, realistic segmentation datasets are highly unbalanced: some categories are much more abundant than others, biasing the performance to the most represented ones. In this paper, we are interested in focusing human labelling effort on a small subset of a larger pool of data, minimizing this effort while maximizing performance of a segmentation model on a hold-out set. We present a new active learning strategy for semantic segmentation based "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06583","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2002.06583/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T00:41:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"neSoTptBDkRRXuiROD+05OJZ48w819eac4Hfp9Jr3boY9V8unqnbjpo/pkLBi1CidgxgtTJ/6NJyMhUfWJLOBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:56:13.343043Z"},"content_sha256":"27dde504c1a890f055d238fb3018cb2fda2ec22953188487dab904a03722d1d9","schema_version":"1.0","event_id":"sha256:27dde504c1a890f055d238fb3018cb2fda2ec22953188487dab904a03722d1d9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4L6DU36DHH7ROB47W33CRQMHCM/bundle.json","state_url":"https://pith.science/pith/4L6DU36DHH7ROB47W33CRQMHCM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4L6DU36DHH7ROB47W33CRQMHCM/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":"2026-08-05T15:56:13Z","links":{"resolver":"https://pith.science/pith/4L6DU36DHH7ROB47W33CRQMHCM","bundle":"https://pith.science/pith/4L6DU36DHH7ROB47W33CRQMHCM/bundle.json","state":"https://pith.science/pith/4L6DU36DHH7ROB47W33CRQMHCM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4L6DU36DHH7ROB47W33CRQMHCM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4L6DU36DHH7ROB47W33CRQMHCM","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":"76fab61f70634bd6fdd277b1d97832f280939513a289437dca2ded33b98a7cb7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-16T14:03:06Z","title_canon_sha256":"7c43f098ae50b198fc17c2333b957bf28df0c497e45bf8f5ada871e075f06fe7"},"schema_version":"1.0","source":{"id":"2002.06583","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.06583","created_at":"2026-07-05T00:41:07Z"},{"alias_kind":"arxiv_version","alias_value":"2002.06583v1","created_at":"2026-07-05T00:41:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06583","created_at":"2026-07-05T00:41:07Z"},{"alias_kind":"pith_short_12","alias_value":"4L6DU36DHH7R","created_at":"2026-07-05T00:41:07Z"},{"alias_kind":"pith_short_16","alias_value":"4L6DU36DHH7ROB47","created_at":"2026-07-05T00:41:07Z"},{"alias_kind":"pith_short_8","alias_value":"4L6DU36D","created_at":"2026-07-05T00:41:07Z"}],"graph_snapshots":[{"event_id":"sha256:27dde504c1a890f055d238fb3018cb2fda2ec22953188487dab904a03722d1d9","target":"graph","created_at":"2026-07-05T00:41:07Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2002.06583/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning-based approaches for semantic segmentation have two inherent challenges. First, acquiring pixel-wise labels is expensive and time-consuming. Second, realistic segmentation datasets are highly unbalanced: some categories are much more abundant than others, biasing the performance to the most represented ones. In this paper, we are interested in focusing human labelling effort on a small subset of a larger pool of data, minimizing this effort while maximizing performance of a segmentation model on a hold-out set. We present a new active learning strategy for semantic segmentation based ","authors_text":"Arantxa Casanova, Christopher J. Pal, Negar Rostamzadeh, Pedro O. Pinheiro","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-16T14:03:06Z","title":"Reinforced active learning for image segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06583","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":"sha256:69554631a121d944acc6bb0a83fea0beb3383ec849f3934c854c0ac800c09d52","target":"record","created_at":"2026-07-05T00:41:07Z","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":"76fab61f70634bd6fdd277b1d97832f280939513a289437dca2ded33b98a7cb7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-16T14:03:06Z","title_canon_sha256":"7c43f098ae50b198fc17c2333b957bf28df0c497e45bf8f5ada871e075f06fe7"},"schema_version":"1.0","source":{"id":"2002.06583","kind":"arxiv","version":1}},"canonical_sha256":"e2fc3a6fc339ff17079fb6f628c187130b5348983d93d89b7bff068b69b32545","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2fc3a6fc339ff17079fb6f628c187130b5348983d93d89b7bff068b69b32545","first_computed_at":"2026-07-05T00:41:07.412159Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:41:07.412159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8Yu1lNqF2h4UZIu88zAT4B7rfUUOKb2BubBZ3PpgNB9/rkOVxER2DX4GtJJDRCPukpu+2g6VsAClOlgLbQqwCw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:41:07.412605Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.06583","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69554631a121d944acc6bb0a83fea0beb3383ec849f3934c854c0ac800c09d52","sha256:27dde504c1a890f055d238fb3018cb2fda2ec22953188487dab904a03722d1d9"],"state_sha256":"613f6465a08da52da8a95ed5d1194c003a6d0f8917994c547c9205cf83ae0b4f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OHPK/XW4z7hhfrjNqm+FLckpdEQRBbUMOqB4PguLDuYzO2nrs7LYh4FS1Yvw8FBtTXTDa5omhtbGHBtTDMh2Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T15:56:13.346426Z","bundle_sha256":"ecd80f6348fb7b5f03483200157d7e719c127c611446527ce6a109a00e8dff5a"}}