{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:JXTNQOQLFVD7F4KGVNC6ITLSFU","short_pith_number":"pith:JXTNQOQL","canonical_record":{"source":{"id":"1912.02096","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-04T16:38:24Z","cross_cats_sorted":[],"title_canon_sha256":"75585ad6f380d33fdd138cbc8b5c9f61985286e00378402bbabea83bd9020bea","abstract_canon_sha256":"b9c828a1ed73bb978ec23307e44927eb5188baeb7e3add6481dbad451a17b3f5"},"schema_version":"1.0"},"canonical_sha256":"4de6d83a0b2d47f2f146ab45e44d722d197bff34c334afbda2e08d7612d408ff","source":{"kind":"arxiv","id":"1912.02096","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.02096","created_at":"2026-07-05T00:51:05Z"},{"alias_kind":"arxiv_version","alias_value":"1912.02096v3","created_at":"2026-07-05T00:51:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.02096","created_at":"2026-07-05T00:51:05Z"},{"alias_kind":"pith_short_12","alias_value":"JXTNQOQLFVD7","created_at":"2026-07-05T00:51:05Z"},{"alias_kind":"pith_short_16","alias_value":"JXTNQOQLFVD7F4KG","created_at":"2026-07-05T00:51:05Z"},{"alias_kind":"pith_short_8","alias_value":"JXTNQOQL","created_at":"2026-07-05T00:51:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:JXTNQOQLFVD7F4KGVNC6ITLSFU","target":"record","payload":{"canonical_record":{"source":{"id":"1912.02096","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-04T16:38:24Z","cross_cats_sorted":[],"title_canon_sha256":"75585ad6f380d33fdd138cbc8b5c9f61985286e00378402bbabea83bd9020bea","abstract_canon_sha256":"b9c828a1ed73bb978ec23307e44927eb5188baeb7e3add6481dbad451a17b3f5"},"schema_version":"1.0"},"canonical_sha256":"4de6d83a0b2d47f2f146ab45e44d722d197bff34c334afbda2e08d7612d408ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:51:05.095927Z","signature_b64":"teHeMUJutWc+law28rqEGq7EvyzJ431a3R6efqUsOL0tCuxmR3WawI+V0dCpvrCTRo/CivzE7jwkekJOszXDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4de6d83a0b2d47f2f146ab45e44d722d197bff34c334afbda2e08d7612d408ff","last_reissued_at":"2026-07-05T00:51:05.095490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:51:05.095490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.02096","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:51:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H4YBHhbo17nEVdSbrhTCV0q7pIFFT5Bsdlsux08WXQyBqFPwOnPpISap7tZcDWX19YD6Wa1ZBuHffMjMvhqxAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T14:41:50.604689Z"},"content_sha256":"a7b5ad8a3e74745cc4c112e4364c587caa10c3b149357a0d9849661cf3efe220","schema_version":"1.0","event_id":"sha256:a7b5ad8a3e74745cc4c112e4364c587caa10c3b149357a0d9849661cf3efe220"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:JXTNQOQLFVD7F4KGVNC6ITLSFU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Multi-Object Tracking and Segmentation from Automatic Annotations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Idoia Ruiz, Joan Serrat, Lorenzo Porzi, Markus Hofinger, Peter Kontschieder, Samuel Rota Bul\\`o","submitted_at":"2019-12-04T16:38:24Z","abstract_excerpt":"In this work we contribute a novel pipeline to automatically generate training data, and to improve over state-of-the-art multi-object tracking and segmentation (MOTS) methods. Our proposed track mining algorithm turns raw street-level videos into high-fidelity MOTS training data, is scalable and overcomes the need of expensive and time-consuming manual annotation approaches. We leverage state-of-the-art instance segmentation results in combination with optical flow predictions, also trained on automatically harvested training data. Our second major contribution is MOTSNet - a deep learning, t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.02096","kind":"arxiv","version":3},"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/1912.02096/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":"2026-07-05T00:51:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xwUfm6GbS8sOf8GAb3QPFAMdYqoRgwrVgHcESGBSah0a2ITgMo9+AV+Z7n67TUwf9b0KxvGWrEAY/ib8Zn1pCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T14:41:50.605060Z"},"content_sha256":"cac8b82bb8c56aee5baea5a0b29be12451f53346fe1155531ff31bbc18bda5a2","schema_version":"1.0","event_id":"sha256:cac8b82bb8c56aee5baea5a0b29be12451f53346fe1155531ff31bbc18bda5a2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JXTNQOQLFVD7F4KGVNC6ITLSFU/bundle.json","state_url":"https://pith.science/pith/JXTNQOQLFVD7F4KGVNC6ITLSFU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JXTNQOQLFVD7F4KGVNC6ITLSFU/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":"2026-07-05T14:41:50Z","links":{"resolver":"https://pith.science/pith/JXTNQOQLFVD7F4KGVNC6ITLSFU","bundle":"https://pith.science/pith/JXTNQOQLFVD7F4KGVNC6ITLSFU/bundle.json","state":"https://pith.science/pith/JXTNQOQLFVD7F4KGVNC6ITLSFU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JXTNQOQLFVD7F4KGVNC6ITLSFU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:JXTNQOQLFVD7F4KGVNC6ITLSFU","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":"b9c828a1ed73bb978ec23307e44927eb5188baeb7e3add6481dbad451a17b3f5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-04T16:38:24Z","title_canon_sha256":"75585ad6f380d33fdd138cbc8b5c9f61985286e00378402bbabea83bd9020bea"},"schema_version":"1.0","source":{"id":"1912.02096","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.02096","created_at":"2026-07-05T00:51:05Z"},{"alias_kind":"arxiv_version","alias_value":"1912.02096v3","created_at":"2026-07-05T00:51:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.02096","created_at":"2026-07-05T00:51:05Z"},{"alias_kind":"pith_short_12","alias_value":"JXTNQOQLFVD7","created_at":"2026-07-05T00:51:05Z"},{"alias_kind":"pith_short_16","alias_value":"JXTNQOQLFVD7F4KG","created_at":"2026-07-05T00:51:05Z"},{"alias_kind":"pith_short_8","alias_value":"JXTNQOQL","created_at":"2026-07-05T00:51:05Z"}],"graph_snapshots":[{"event_id":"sha256:cac8b82bb8c56aee5baea5a0b29be12451f53346fe1155531ff31bbc18bda5a2","target":"graph","created_at":"2026-07-05T00:51:05Z","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/1912.02096/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work we contribute a novel pipeline to automatically generate training data, and to improve over state-of-the-art multi-object tracking and segmentation (MOTS) methods. Our proposed track mining algorithm turns raw street-level videos into high-fidelity MOTS training data, is scalable and overcomes the need of expensive and time-consuming manual annotation approaches. We leverage state-of-the-art instance segmentation results in combination with optical flow predictions, also trained on automatically harvested training data. Our second major contribution is MOTSNet - a deep learning, t","authors_text":"Idoia Ruiz, Joan Serrat, Lorenzo Porzi, Markus Hofinger, Peter Kontschieder, Samuel Rota Bul\\`o","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-04T16:38:24Z","title":"Learning Multi-Object Tracking and Segmentation from Automatic Annotations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.02096","kind":"arxiv","version":3},"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:a7b5ad8a3e74745cc4c112e4364c587caa10c3b149357a0d9849661cf3efe220","target":"record","created_at":"2026-07-05T00:51:05Z","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":"b9c828a1ed73bb978ec23307e44927eb5188baeb7e3add6481dbad451a17b3f5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-04T16:38:24Z","title_canon_sha256":"75585ad6f380d33fdd138cbc8b5c9f61985286e00378402bbabea83bd9020bea"},"schema_version":"1.0","source":{"id":"1912.02096","kind":"arxiv","version":3}},"canonical_sha256":"4de6d83a0b2d47f2f146ab45e44d722d197bff34c334afbda2e08d7612d408ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4de6d83a0b2d47f2f146ab45e44d722d197bff34c334afbda2e08d7612d408ff","first_computed_at":"2026-07-05T00:51:05.095490Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:51:05.095490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"teHeMUJutWc+law28rqEGq7EvyzJ431a3R6efqUsOL0tCuxmR3WawI+V0dCpvrCTRo/CivzE7jwkekJOszXDCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:51:05.095927Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.02096","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7b5ad8a3e74745cc4c112e4364c587caa10c3b149357a0d9849661cf3efe220","sha256:cac8b82bb8c56aee5baea5a0b29be12451f53346fe1155531ff31bbc18bda5a2"],"state_sha256":"8322258d61d7f4d0a160f139aaa27ba256a46a79b12f57556657428eed6074ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J07T76aH04XS9w2MkY1StXPluYX/InCXrRu60unkOb9BFj4Nx70uzUteCpJodEV+leJlxZ7oEQMy2DYeNEoGCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T14:41:50.607204Z","bundle_sha256":"d56014acd11cdeca38c74c51880f28f3c7950788034e426b9e6077186446ac16"}}