{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:GQKWLTFN3CXSBFRILXSPFRQHIB","short_pith_number":"pith:GQKWLTFN","canonical_record":{"source":{"id":"2201.04620","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-12T18:57:04Z","cross_cats_sorted":[],"title_canon_sha256":"4b910dca7f63f536de38d8aabe90d8039f724645672842c8a705876786de792f","abstract_canon_sha256":"51b8805b89994399c4c9a7f3a871ae2823d84a646a0c5078b1151ebed7676233"},"schema_version":"1.0"},"canonical_sha256":"341565ccadd8af2096285de4f2c6074062f1768920762f95088a3ce8a2176ce4","source":{"kind":"arxiv","id":"2201.04620","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.04620","created_at":"2026-07-05T06:44:45Z"},{"alias_kind":"arxiv_version","alias_value":"2201.04620v2","created_at":"2026-07-05T06:44:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.04620","created_at":"2026-07-05T06:44:45Z"},{"alias_kind":"pith_short_12","alias_value":"GQKWLTFN3CXS","created_at":"2026-07-05T06:44:45Z"},{"alias_kind":"pith_short_16","alias_value":"GQKWLTFN3CXSBFRI","created_at":"2026-07-05T06:44:45Z"},{"alias_kind":"pith_short_8","alias_value":"GQKWLTFN","created_at":"2026-07-05T06:44:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:GQKWLTFN3CXSBFRILXSPFRQHIB","target":"record","payload":{"canonical_record":{"source":{"id":"2201.04620","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-12T18:57:04Z","cross_cats_sorted":[],"title_canon_sha256":"4b910dca7f63f536de38d8aabe90d8039f724645672842c8a705876786de792f","abstract_canon_sha256":"51b8805b89994399c4c9a7f3a871ae2823d84a646a0c5078b1151ebed7676233"},"schema_version":"1.0"},"canonical_sha256":"341565ccadd8af2096285de4f2c6074062f1768920762f95088a3ce8a2176ce4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:44:45.977496Z","signature_b64":"UHsm0rAf70MaidLXAe6f+GiP9oCQAvveReZy7u6n/E4u3LVT96QqvQqehUdJ04a4A+dU8mz+57kykVdoV1yIBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"341565ccadd8af2096285de4f2c6074062f1768920762f95088a3ce8a2176ce4","last_reissued_at":"2026-07-05T06:44:45.977005Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:44:45.977005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.04620","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":"2026-07-05T06:44:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rVWRZZm4brFnvkLPUJkUL9ZioNXdkhNBSFt1SadpXIgU4FhGgB8O23rnDzOROW7nuS8sQjdNYKuQYAenz2tGDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:10:36.062924Z"},"content_sha256":"2adfa2efc884e0b88686821aa021fc69a54e19624b9e9099e2080b6fb55a1bb8","schema_version":"1.0","event_id":"sha256:2adfa2efc884e0b88686821aa021fc69a54e19624b9e9099e2080b6fb55a1bb8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:GQKWLTFN3CXSBFRILXSPFRQHIB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Mining","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Rama Chellappa, Sai Saketh Rambhatla, Saksham Suri","submitted_at":"2022-01-12T18:57:04Z","abstract_excerpt":"Training with sparse annotations is known to reduce the performance of object detectors. Previous methods have focused on proxies for missing ground truth annotations in the form of pseudo-labels for unlabeled boxes. We observe that existing methods suffer at higher levels of sparsity in the data due to noisy pseudo-labels. To prevent this, we propose an end-to-end system that learns to separate the proposals into labeled and unlabeled regions using Pseudo-positive mining. While the labeled regions are processed as usual, self-supervised learning is used to process the unlabeled regions thereb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.04620","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/2201.04620/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":"2026-07-05T06:44:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CZinAW6AbsBj8SrlcGOrxrHbHh7KeZ0Yoo0AZR+cA0hyPoGCK+3RnAwuetuRGP1MWtAfrRPF12XMLPjDqv9gDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:10:36.063919Z"},"content_sha256":"c7abea5a09e362f47f5bf22e0287c39863c728de150c0c364820d17882821b2d","schema_version":"1.0","event_id":"sha256:c7abea5a09e362f47f5bf22e0287c39863c728de150c0c364820d17882821b2d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GQKWLTFN3CXSBFRILXSPFRQHIB/bundle.json","state_url":"https://pith.science/pith/GQKWLTFN3CXSBFRILXSPFRQHIB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GQKWLTFN3CXSBFRILXSPFRQHIB/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":"2026-08-07T17:10:36Z","links":{"resolver":"https://pith.science/pith/GQKWLTFN3CXSBFRILXSPFRQHIB","bundle":"https://pith.science/pith/GQKWLTFN3CXSBFRILXSPFRQHIB/bundle.json","state":"https://pith.science/pith/GQKWLTFN3CXSBFRILXSPFRQHIB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GQKWLTFN3CXSBFRILXSPFRQHIB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GQKWLTFN3CXSBFRILXSPFRQHIB","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":"51b8805b89994399c4c9a7f3a871ae2823d84a646a0c5078b1151ebed7676233","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-12T18:57:04Z","title_canon_sha256":"4b910dca7f63f536de38d8aabe90d8039f724645672842c8a705876786de792f"},"schema_version":"1.0","source":{"id":"2201.04620","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.04620","created_at":"2026-07-05T06:44:45Z"},{"alias_kind":"arxiv_version","alias_value":"2201.04620v2","created_at":"2026-07-05T06:44:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.04620","created_at":"2026-07-05T06:44:45Z"},{"alias_kind":"pith_short_12","alias_value":"GQKWLTFN3CXS","created_at":"2026-07-05T06:44:45Z"},{"alias_kind":"pith_short_16","alias_value":"GQKWLTFN3CXSBFRI","created_at":"2026-07-05T06:44:45Z"},{"alias_kind":"pith_short_8","alias_value":"GQKWLTFN","created_at":"2026-07-05T06:44:45Z"}],"graph_snapshots":[{"event_id":"sha256:c7abea5a09e362f47f5bf22e0287c39863c728de150c0c364820d17882821b2d","target":"graph","created_at":"2026-07-05T06:44:45Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2201.04620/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training with sparse annotations is known to reduce the performance of object detectors. Previous methods have focused on proxies for missing ground truth annotations in the form of pseudo-labels for unlabeled boxes. We observe that existing methods suffer at higher levels of sparsity in the data due to noisy pseudo-labels. To prevent this, we propose an end-to-end system that learns to separate the proposals into labeled and unlabeled regions using Pseudo-positive mining. While the labeled regions are processed as usual, self-supervised learning is used to process the unlabeled regions thereb","authors_text":"Abhinav Shrivastava, Rama Chellappa, Sai Saketh Rambhatla, Saksham Suri","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-12T18:57:04Z","title":"SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Mining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.04620","kind":"arxiv","version":2},"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":"sha256:2adfa2efc884e0b88686821aa021fc69a54e19624b9e9099e2080b6fb55a1bb8","target":"record","created_at":"2026-07-05T06:44:45Z","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":"51b8805b89994399c4c9a7f3a871ae2823d84a646a0c5078b1151ebed7676233","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-12T18:57:04Z","title_canon_sha256":"4b910dca7f63f536de38d8aabe90d8039f724645672842c8a705876786de792f"},"schema_version":"1.0","source":{"id":"2201.04620","kind":"arxiv","version":2}},"canonical_sha256":"341565ccadd8af2096285de4f2c6074062f1768920762f95088a3ce8a2176ce4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"341565ccadd8af2096285de4f2c6074062f1768920762f95088a3ce8a2176ce4","first_computed_at":"2026-07-05T06:44:45.977005Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:44:45.977005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UHsm0rAf70MaidLXAe6f+GiP9oCQAvveReZy7u6n/E4u3LVT96QqvQqehUdJ04a4A+dU8mz+57kykVdoV1yIBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:44:45.977496Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.04620","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2adfa2efc884e0b88686821aa021fc69a54e19624b9e9099e2080b6fb55a1bb8","sha256:c7abea5a09e362f47f5bf22e0287c39863c728de150c0c364820d17882821b2d"],"state_sha256":"0ce23090911261c6b030885b270dea99c95e83cd18f99c95d8b49a61a2ec57b3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5NOX6N4pgbCfBGHR5rez691rU8arMUtyc2Dt8dD5RArSFVs9Rv8SaJzCDLGG8v7Be2Szspp29dMYfDyOCZs5Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T17:10:36.071344Z","bundle_sha256":"ab49128d2b2ce2ed3f0fc34d2b4673e055ba343d9b2f47ff48e052774668a586"}}