{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NNRPEF6IZW4CNEUCZPHWP5QP5W","short_pith_number":"pith:NNRPEF6I","canonical_record":{"source":{"id":"2605.12451","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T17:41:19Z","cross_cats_sorted":[],"title_canon_sha256":"8592cc2e8f2dd7d47a3fb67196b4887fd555fdad0b069db9e14e38a8592ed20b","abstract_canon_sha256":"010712e5ae26c546ec53ef670e53913fbb903aac5dc955087331f02aede6e48e"},"schema_version":"1.0"},"canonical_sha256":"6b62f217c8cdb8269282cbcf67f60fedbc93506977b0f26f94974ca71255abe6","source":{"kind":"arxiv","id":"2605.12451","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12451","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12451v2","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12451","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"pith_short_12","alias_value":"NNRPEF6IZW4C","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"pith_short_16","alias_value":"NNRPEF6IZW4CNEUC","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"pith_short_8","alias_value":"NNRPEF6I","created_at":"2026-05-20T00:05:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NNRPEF6IZW4CNEUCZPHWP5QP5W","target":"record","payload":{"canonical_record":{"source":{"id":"2605.12451","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T17:41:19Z","cross_cats_sorted":[],"title_canon_sha256":"8592cc2e8f2dd7d47a3fb67196b4887fd555fdad0b069db9e14e38a8592ed20b","abstract_canon_sha256":"010712e5ae26c546ec53ef670e53913fbb903aac5dc955087331f02aede6e48e"},"schema_version":"1.0"},"canonical_sha256":"6b62f217c8cdb8269282cbcf67f60fedbc93506977b0f26f94974ca71255abe6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:47.382466Z","signature_b64":"ro8jFLnQnEN9Z39Z5EaZ8hhAQAWR/D1jodS0RhnpZwE5r3huEUGpFYVAZm9JvHldI3Ed2c0wcvkSTISXLnH0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b62f217c8cdb8269282cbcf67f60fedbc93506977b0f26f94974ca71255abe6","last_reissued_at":"2026-05-20T00:05:47.381866Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:47.381866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.12451","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":"2026-05-20T00:05:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"blcwwa0j6V1BGqBgkwR81SlAHapKN1aSnm7IeLmhDQOBsuyyPJkQlXwoTMMI/4ICqCprgZMXPpcXjL/wshMMDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T16:15:05.846529Z"},"content_sha256":"4386e98843a7498be47d19c356e6663acd105fefac427c88ecb8cdd6974efba5","schema_version":"1.0","event_id":"sha256:4386e98843a7498be47d19c356e6663acd105fefac427c88ecb8cdd6974efba5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NNRPEF6IZW4CNEUCZPHWP5QP5W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FuTCR: Future-Targeted Contrast and Repulsion for Continual Panoptic Segmentation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"FuTCR identifies future-like regions in background pixels and uses contrast plus repulsion to reserve space for new classes in continual panoptic segmentation.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bryan A. Plummer, Deepti Ghadiyaram, Keanu Nichols, Nicholas Ikechukwu","submitted_at":"2026-05-12T17:41:19Z","abstract_excerpt":"Continual Panoptic Segmentation (CPS) requires methods that can quickly adapt to new categories over time. The nature of this dense prediction task means that training images may contain a mix of labeled and unlabeled objects. As nothing is known about these unlabeled objects a priori, existing methods often simply group any unlabeled pixel into a single \"background\" class during training. In effect, during training, they repeatedly tell the model that all the different background categories are the same (even when they aren't). This makes learning to identify different background categories a"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments across six CPS settings and a range of dataset sizes show FuTCR improves relative new-class panoptic quality over the state-of-the-art by up to 28%, while preserving or improving base-class performance with gains up to 4%.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That grouping model-predicted masks whose pixels are consistently classified as background but exhibit non-background logits reliably discovers coherent future-like regions without introducing noisy or misleading prototypes.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"FuTCR boosts new-class panoptic quality by up to 28% in continual settings by discovering future-like background regions and applying targeted contrast and repulsion to reserve space for incoming categories.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"FuTCR identifies future-like regions in background pixels and uses contrast plus repulsion to reserve space for new classes in continual panoptic segmentation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"84482e45de4af6d116287f574d0dcaea4d25a24afcaa494f59be39d58be45d3e"},"source":{"id":"2605.12451","kind":"arxiv","version":2},"verdict":{"id":"ecad3d9e-70c4-450e-9613-73506336d52d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T06:17:22.265371Z","strongest_claim":"Experiments across six CPS settings and a range of dataset sizes show FuTCR improves relative new-class panoptic quality over the state-of-the-art by up to 28%, while preserving or improving base-class performance with gains up to 4%.","one_line_summary":"FuTCR boosts new-class panoptic quality by up to 28% in continual settings by discovering future-like background regions and applying targeted contrast and repulsion to reserve space for incoming categories.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That grouping model-predicted masks whose pixels are consistently classified as background but exhibit non-background logits reliably discovers coherent future-like regions without introducing noisy or misleading prototypes.","pith_extraction_headline":"FuTCR identifies future-like regions in background pixels and uses contrast plus repulsion to reserve space for new classes in continual panoptic segmentation."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.12451/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T22:21:57.830284Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T10:35:04.329448Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T08:01:18.227524Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T07:27:18.586777Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"7a0352042680626cd036641d44794e0cbc291f805bc1e2cbef5235547f807951"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"a4c86637460ad4d0005b507a90cc53f8ce471085860ec4845ed0ec44ecac2b27"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"ecad3d9e-70c4-450e-9613-73506336d52d"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:05:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q44ZUAGAVqTF/t/MJW9mT2W2MM3ddtZHnKNTHsn8gPD/C6MvQAMXQ2Tndzvw4EFhli9LTGr8X2sPxfNaxdJACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T16:15:05.847502Z"},"content_sha256":"fc89eb5e6794db26930af60d7d46426ebd247f0f2e2445eedf0a980502e2f08b","schema_version":"1.0","event_id":"sha256:fc89eb5e6794db26930af60d7d46426ebd247f0f2e2445eedf0a980502e2f08b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NNRPEF6IZW4CNEUCZPHWP5QP5W/bundle.json","state_url":"https://pith.science/pith/NNRPEF6IZW4CNEUCZPHWP5QP5W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NNRPEF6IZW4CNEUCZPHWP5QP5W/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":"2026-05-29T16:15:05Z","links":{"resolver":"https://pith.science/pith/NNRPEF6IZW4CNEUCZPHWP5QP5W","bundle":"https://pith.science/pith/NNRPEF6IZW4CNEUCZPHWP5QP5W/bundle.json","state":"https://pith.science/pith/NNRPEF6IZW4CNEUCZPHWP5QP5W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NNRPEF6IZW4CNEUCZPHWP5QP5W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NNRPEF6IZW4CNEUCZPHWP5QP5W","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":"010712e5ae26c546ec53ef670e53913fbb903aac5dc955087331f02aede6e48e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T17:41:19Z","title_canon_sha256":"8592cc2e8f2dd7d47a3fb67196b4887fd555fdad0b069db9e14e38a8592ed20b"},"schema_version":"1.0","source":{"id":"2605.12451","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12451","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12451v2","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12451","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"pith_short_12","alias_value":"NNRPEF6IZW4C","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"pith_short_16","alias_value":"NNRPEF6IZW4CNEUC","created_at":"2026-05-20T00:05:47Z"},{"alias_kind":"pith_short_8","alias_value":"NNRPEF6I","created_at":"2026-05-20T00:05:47Z"}],"graph_snapshots":[{"event_id":"sha256:fc89eb5e6794db26930af60d7d46426ebd247f0f2e2445eedf0a980502e2f08b","target":"graph","created_at":"2026-05-20T00:05:47Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Experiments across six CPS settings and a range of dataset sizes show FuTCR improves relative new-class panoptic quality over the state-of-the-art by up to 28%, while preserving or improving base-class performance with gains up to 4%."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That grouping model-predicted masks whose pixels are consistently classified as background but exhibit non-background logits reliably discovers coherent future-like regions without introducing noisy or misleading prototypes."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"FuTCR boosts new-class panoptic quality by up to 28% in continual settings by discovering future-like background regions and applying targeted contrast and repulsion to reserve space for incoming categories."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"FuTCR identifies future-like regions in background pixels and uses contrast plus repulsion to reserve space for new classes in continual panoptic segmentation."}],"snapshot_sha256":"84482e45de4af6d116287f574d0dcaea4d25a24afcaa494f59be39d58be45d3e"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"a4c86637460ad4d0005b507a90cc53f8ce471085860ec4845ed0ec44ecac2b27"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T22:21:57.830284Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T10:35:04.329448Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T08:01:18.227524Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T07:27:18.586777Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.12451/integrity.json","findings":[],"snapshot_sha256":"7a0352042680626cd036641d44794e0cbc291f805bc1e2cbef5235547f807951","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Continual Panoptic Segmentation (CPS) requires methods that can quickly adapt to new categories over time. The nature of this dense prediction task means that training images may contain a mix of labeled and unlabeled objects. As nothing is known about these unlabeled objects a priori, existing methods often simply group any unlabeled pixel into a single \"background\" class during training. In effect, during training, they repeatedly tell the model that all the different background categories are the same (even when they aren't). This makes learning to identify different background categories a","authors_text":"Bryan A. Plummer, Deepti Ghadiyaram, Keanu Nichols, Nicholas Ikechukwu","cross_cats":[],"headline":"FuTCR identifies future-like regions in background pixels and uses contrast plus repulsion to reserve space for new classes in continual panoptic segmentation.","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T17:41:19Z","title":"FuTCR: Future-Targeted Contrast and Repulsion for Continual Panoptic Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.12451","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-13T06:17:22.265371Z","id":"ecad3d9e-70c4-450e-9613-73506336d52d","model_set":{"reader":"grok-4.3"},"one_line_summary":"FuTCR boosts new-class panoptic quality by up to 28% in continual settings by discovering future-like background regions and applying targeted contrast and repulsion to reserve space for incoming categories.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"FuTCR identifies future-like regions in background pixels and uses contrast plus repulsion to reserve space for new classes in continual panoptic segmentation.","strongest_claim":"Experiments across six CPS settings and a range of dataset sizes show FuTCR improves relative new-class panoptic quality over the state-of-the-art by up to 28%, while preserving or improving base-class performance with gains up to 4%.","weakest_assumption":"That grouping model-predicted masks whose pixels are consistently classified as background but exhibit non-background logits reliably discovers coherent future-like regions without introducing noisy or misleading prototypes."}},"verdict_id":"ecad3d9e-70c4-450e-9613-73506336d52d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4386e98843a7498be47d19c356e6663acd105fefac427c88ecb8cdd6974efba5","target":"record","created_at":"2026-05-20T00:05:47Z","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":"010712e5ae26c546ec53ef670e53913fbb903aac5dc955087331f02aede6e48e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T17:41:19Z","title_canon_sha256":"8592cc2e8f2dd7d47a3fb67196b4887fd555fdad0b069db9e14e38a8592ed20b"},"schema_version":"1.0","source":{"id":"2605.12451","kind":"arxiv","version":2}},"canonical_sha256":"6b62f217c8cdb8269282cbcf67f60fedbc93506977b0f26f94974ca71255abe6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b62f217c8cdb8269282cbcf67f60fedbc93506977b0f26f94974ca71255abe6","first_computed_at":"2026-05-20T00:05:47.381866Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:47.381866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ro8jFLnQnEN9Z39Z5EaZ8hhAQAWR/D1jodS0RhnpZwE5r3huEUGpFYVAZm9JvHldI3Ed2c0wcvkSTISXLnH0Aw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:47.382466Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12451","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4386e98843a7498be47d19c356e6663acd105fefac427c88ecb8cdd6974efba5","sha256:fc89eb5e6794db26930af60d7d46426ebd247f0f2e2445eedf0a980502e2f08b"],"state_sha256":"bb3e5a5305e277695124337c16172421b56cc5ac89a8c337f51b7c58092b9bd0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7csQQS/RVUOjdBdrktUEMFgWyfvsM0fnH7ZUfSqOSh/0DeoqCig+cMPz6yBx5aigyN1NeseNfyBW8xs5BfcJCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T16:15:05.850477Z","bundle_sha256":"5288be0002010c62e5a4535ac5d29ebb7344f077e1989cab2fe13ebb8feb35c3"}}