{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:6DFOURRW3UKK64UB35YLAYFECX","short_pith_number":"pith:6DFOURRW","canonical_record":{"source":{"id":"1612.08871","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-28T12:50:39Z","cross_cats_sorted":[],"title_canon_sha256":"ef1e86fbc5da5dd19c184ccce9224f53c2197d9e7c9fb533189eb66cea943e22","abstract_canon_sha256":"f948994c52c4fc621525925eda040c139404a0a9a178af1ca49640695a2cb267"},"schema_version":"1.0"},"canonical_sha256":"f0caea4636dd14af7281df70b060a415d327fa6d08543b84df79101be455bbcf","source":{"kind":"arxiv","id":"1612.08871","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.08871","created_at":"2026-05-18T00:33:59Z"},{"alias_kind":"arxiv_version","alias_value":"1612.08871v2","created_at":"2026-05-18T00:33:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.08871","created_at":"2026-05-18T00:33:59Z"},{"alias_kind":"pith_short_12","alias_value":"6DFOURRW3UKK","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_16","alias_value":"6DFOURRW3UKK64UB","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_8","alias_value":"6DFOURRW","created_at":"2026-05-18T12:30:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:6DFOURRW3UKK64UB35YLAYFECX","target":"record","payload":{"canonical_record":{"source":{"id":"1612.08871","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-28T12:50:39Z","cross_cats_sorted":[],"title_canon_sha256":"ef1e86fbc5da5dd19c184ccce9224f53c2197d9e7c9fb533189eb66cea943e22","abstract_canon_sha256":"f948994c52c4fc621525925eda040c139404a0a9a178af1ca49640695a2cb267"},"schema_version":"1.0"},"canonical_sha256":"f0caea4636dd14af7281df70b060a415d327fa6d08543b84df79101be455bbcf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:59.585785Z","signature_b64":"DTV+p/bvHPYcPY/S+Lu+QTTmj18J/8UFEwfyhioexi8pDEaEgsB+15pGUkNiVFt1u1PM2AzHevxTdeya/J/aAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0caea4636dd14af7281df70b060a415d327fa6d08543b84df79101be455bbcf","last_reissued_at":"2026-05-18T00:33:59.585052Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:59.585052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1612.08871","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":"2026-05-18T00:33:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZII0dwGcrrdE+LmQXEK+JWqzlr/Wsl1bBG/wuprvIdWqjAM7/qDWUOPkCTCwNT6y/KOxHkNR5hn/ScahlImGDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:19:00.478060Z"},"content_sha256":"82be099df5048b33c893a3246406548a9d5e000343bb3904a5c79e2a843a3f75","schema_version":"1.0","event_id":"sha256:82be099df5048b33c893a3246406548a9d5e000343bb3904a5c79e2a843a3f75"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:6DFOURRW3UKK64UB35YLAYFECX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semantic Video Segmentation by Gated Recurrent Flow Propagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cristian Sminchisescu, David Nilsson","submitted_at":"2016-12-28T12:50:39Z","abstract_excerpt":"Semantic video segmentation is challenging due to the sheer amount of data that needs to be processed and labeled in order to construct accurate models. In this paper we present a deep, end-to-end trainable methodology to video segmentation that is capable of leveraging information present in unlabeled data in order to improve semantic estimates. Our model combines a convolutional architecture and a spatio-temporal transformer recurrent layer that are able to temporally propagate labeling information by means of optical flow, adaptively gated based on its locally estimated uncertainty. The flo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.08871","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":""},"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":"2026-05-18T00:33:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qxz//4yBL5nFr9Q+BCSSpRME+nCSmsLvrgYSsCbdRYd9ChTomisqPWD4AKstY6T0bQxZw9psQG6ucZ1yrWNkDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:19:00.478417Z"},"content_sha256":"0398a55bcf225eea1323fbbeb0750b1544796b83e6a857418b33c470f5436b00","schema_version":"1.0","event_id":"sha256:0398a55bcf225eea1323fbbeb0750b1544796b83e6a857418b33c470f5436b00"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6DFOURRW3UKK64UB35YLAYFECX/bundle.json","state_url":"https://pith.science/pith/6DFOURRW3UKK64UB35YLAYFECX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6DFOURRW3UKK64UB35YLAYFECX/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":"2026-07-09T02:19:00Z","links":{"resolver":"https://pith.science/pith/6DFOURRW3UKK64UB35YLAYFECX","bundle":"https://pith.science/pith/6DFOURRW3UKK64UB35YLAYFECX/bundle.json","state":"https://pith.science/pith/6DFOURRW3UKK64UB35YLAYFECX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6DFOURRW3UKK64UB35YLAYFECX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:6DFOURRW3UKK64UB35YLAYFECX","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":"f948994c52c4fc621525925eda040c139404a0a9a178af1ca49640695a2cb267","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-28T12:50:39Z","title_canon_sha256":"ef1e86fbc5da5dd19c184ccce9224f53c2197d9e7c9fb533189eb66cea943e22"},"schema_version":"1.0","source":{"id":"1612.08871","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.08871","created_at":"2026-05-18T00:33:59Z"},{"alias_kind":"arxiv_version","alias_value":"1612.08871v2","created_at":"2026-05-18T00:33:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.08871","created_at":"2026-05-18T00:33:59Z"},{"alias_kind":"pith_short_12","alias_value":"6DFOURRW3UKK","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_16","alias_value":"6DFOURRW3UKK64UB","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_8","alias_value":"6DFOURRW","created_at":"2026-05-18T12:30:01Z"}],"graph_snapshots":[{"event_id":"sha256:0398a55bcf225eea1323fbbeb0750b1544796b83e6a857418b33c470f5436b00","target":"graph","created_at":"2026-05-18T00:33:59Z","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"},"paper":{"abstract_excerpt":"Semantic video segmentation is challenging due to the sheer amount of data that needs to be processed and labeled in order to construct accurate models. In this paper we present a deep, end-to-end trainable methodology to video segmentation that is capable of leveraging information present in unlabeled data in order to improve semantic estimates. Our model combines a convolutional architecture and a spatio-temporal transformer recurrent layer that are able to temporally propagate labeling information by means of optical flow, adaptively gated based on its locally estimated uncertainty. The flo","authors_text":"Cristian Sminchisescu, David Nilsson","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-28T12:50:39Z","title":"Semantic Video Segmentation by Gated Recurrent Flow Propagation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.08871","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":"sha256:82be099df5048b33c893a3246406548a9d5e000343bb3904a5c79e2a843a3f75","target":"record","created_at":"2026-05-18T00:33:59Z","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":"f948994c52c4fc621525925eda040c139404a0a9a178af1ca49640695a2cb267","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-28T12:50:39Z","title_canon_sha256":"ef1e86fbc5da5dd19c184ccce9224f53c2197d9e7c9fb533189eb66cea943e22"},"schema_version":"1.0","source":{"id":"1612.08871","kind":"arxiv","version":2}},"canonical_sha256":"f0caea4636dd14af7281df70b060a415d327fa6d08543b84df79101be455bbcf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0caea4636dd14af7281df70b060a415d327fa6d08543b84df79101be455bbcf","first_computed_at":"2026-05-18T00:33:59.585052Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:33:59.585052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DTV+p/bvHPYcPY/S+Lu+QTTmj18J/8UFEwfyhioexi8pDEaEgsB+15pGUkNiVFt1u1PM2AzHevxTdeya/J/aAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:33:59.585785Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.08871","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82be099df5048b33c893a3246406548a9d5e000343bb3904a5c79e2a843a3f75","sha256:0398a55bcf225eea1323fbbeb0750b1544796b83e6a857418b33c470f5436b00"],"state_sha256":"1b5be42460435306ae2748e8c27d37a39c335e3cb14ddf499df3707553547633"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2yTyDkTTIyTVUHMZALN23RovX07IF7qN6byyoCtb0wE+5BsNnEtlZEsyQol8oNltcDaVZmvgNfxa1jvz8MEcCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T02:19:00.480484Z","bundle_sha256":"3ab6ec796abba05c8e81f6e06092e6800b141fe400356261c5dd574214a24fda"}}