{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:EXUFQ5KCYOPXDLDM6QNL4ZUPRN","short_pith_number":"pith:EXUFQ5KC","schema_version":"1.0","canonical_sha256":"25e8587542c39f71ac6cf41abe668f8b472cf57e3d8db01c68ef934096c6a806","source":{"kind":"arxiv","id":"2003.06975","version":2},"attestation_state":"computed","paper":{"title":"TACO: Trash Annotations in Context for Litter Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Pedro F Proen\\c{c}a, Pedro Sim\\~oes","submitted_at":"2020-03-16T02:17:07Z","abstract_excerpt":"TACO is an open image dataset for litter detection and segmentation, which is growing through crowdsourcing. Firstly, this paper describes this dataset and the tools developed to support it. Secondly, we report instance segmentation performance using Mask R-CNN on the current version of TACO. Despite its small size (1500 images and 4784 annotations), our results are promising on this challenging problem. However, to achieve satisfactory trash detection in the wild for deployment, TACO still needs much more manual annotations. These can be contributed using: http://tacodataset.org/"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2003.06975","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-16T02:17:07Z","cross_cats_sorted":[],"title_canon_sha256":"863d9de4d3335e06cc591825349f6283b6865479ff1f5fb901d7c8aa826ac9bc","abstract_canon_sha256":"bf0d80099b9eb4c34d29529494fe90dea0b06a9a30bf70ba41190322e146dce5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:48:25.751592Z","signature_b64":"0UCDu78li3GWhqew+ZHt25n+ocXtnOAc7NAk3xAs1/SRRK6KfvxVl65ppHFPT9NSIMSf7yNgm8ONzqodpULaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25e8587542c39f71ac6cf41abe668f8b472cf57e3d8db01c68ef934096c6a806","last_reissued_at":"2026-07-05T00:48:25.751069Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:48:25.751069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TACO: Trash Annotations in Context for Litter Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Pedro F Proen\\c{c}a, Pedro Sim\\~oes","submitted_at":"2020-03-16T02:17:07Z","abstract_excerpt":"TACO is an open image dataset for litter detection and segmentation, which is growing through crowdsourcing. Firstly, this paper describes this dataset and the tools developed to support it. Secondly, we report instance segmentation performance using Mask R-CNN on the current version of TACO. Despite its small size (1500 images and 4784 annotations), our results are promising on this challenging problem. However, to achieve satisfactory trash detection in the wild for deployment, TACO still needs much more manual annotations. These can be contributed using: http://tacodataset.org/"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.06975","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2003.06975/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2003.06975","created_at":"2026-07-05T00:48:25.751143+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.06975v2","created_at":"2026-07-05T00:48:25.751143+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.06975","created_at":"2026-07-05T00:48:25.751143+00:00"},{"alias_kind":"pith_short_12","alias_value":"EXUFQ5KCYOPX","created_at":"2026-07-05T00:48:25.751143+00:00"},{"alias_kind":"pith_short_16","alias_value":"EXUFQ5KCYOPXDLDM","created_at":"2026-07-05T00:48:25.751143+00:00"},{"alias_kind":"pith_short_8","alias_value":"EXUFQ5KC","created_at":"2026-07-05T00:48:25.751143+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02230","citing_title":"Efficient Waste Sorting for Circular Economy: A Confidence-guided comparison between One-Vs-All and One-Vs-Rest Classification Strategies with Human-in-the-Loop for Automated Waste Sorting","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13587","citing_title":"Towards Effective Waste Segmentation for Automated Waste Recycling in Cluttered Background","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26682","citing_title":"SteelDS: A High-Resolution Video Dataset of E40 Steel Scrap for Object Detection and Instance Segmentation","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EXUFQ5KCYOPXDLDM6QNL4ZUPRN","json":"https://pith.science/pith/EXUFQ5KCYOPXDLDM6QNL4ZUPRN.json","graph_json":"https://pith.science/api/pith-number/EXUFQ5KCYOPXDLDM6QNL4ZUPRN/graph.json","events_json":"https://pith.science/api/pith-number/EXUFQ5KCYOPXDLDM6QNL4ZUPRN/events.json","paper":"https://pith.science/paper/EXUFQ5KC"},"agent_actions":{"view_html":"https://pith.science/pith/EXUFQ5KCYOPXDLDM6QNL4ZUPRN","download_json":"https://pith.science/pith/EXUFQ5KCYOPXDLDM6QNL4ZUPRN.json","view_paper":"https://pith.science/paper/EXUFQ5KC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.06975&json=true","fetch_graph":"https://pith.science/api/pith-number/EXUFQ5KCYOPXDLDM6QNL4ZUPRN/graph.json","fetch_events":"https://pith.science/api/pith-number/EXUFQ5KCYOPXDLDM6QNL4ZUPRN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EXUFQ5KCYOPXDLDM6QNL4ZUPRN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EXUFQ5KCYOPXDLDM6QNL4ZUPRN/action/storage_attestation","attest_author":"https://pith.science/pith/EXUFQ5KCYOPXDLDM6QNL4ZUPRN/action/author_attestation","sign_citation":"https://pith.science/pith/EXUFQ5KCYOPXDLDM6QNL4ZUPRN/action/citation_signature","submit_replication":"https://pith.science/pith/EXUFQ5KCYOPXDLDM6QNL4ZUPRN/action/replication_record"}},"created_at":"2026-07-05T00:48:25.751143+00:00","updated_at":"2026-07-05T00:48:25.751143+00:00"}