{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:REHDR3G7JDWJHBZCVRFTROPLDJ","short_pith_number":"pith:REHDR3G7","canonical_record":{"source":{"id":"2111.13241","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-25T20:30:30Z","cross_cats_sorted":[],"title_canon_sha256":"f25b187ea9d7560abe146d66e1581b10fa6d8fada5e2adf9981de9ff7d1c4541","abstract_canon_sha256":"290664ecb71ce0a2042c9bda77b88906784d18c4c2f5ce63ade7b6b2936ca756"},"schema_version":"1.0"},"canonical_sha256":"890e38ecdf48ec938722ac4b38b9eb1a597b3c53ca11bc6d45dc663e8b2c725f","source":{"kind":"arxiv","id":"2111.13241","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.13241","created_at":"2026-07-05T04:17:03Z"},{"alias_kind":"arxiv_version","alias_value":"2111.13241v3","created_at":"2026-07-05T04:17:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.13241","created_at":"2026-07-05T04:17:03Z"},{"alias_kind":"pith_short_12","alias_value":"REHDR3G7JDWJ","created_at":"2026-07-05T04:17:03Z"},{"alias_kind":"pith_short_16","alias_value":"REHDR3G7JDWJHBZC","created_at":"2026-07-05T04:17:03Z"},{"alias_kind":"pith_short_8","alias_value":"REHDR3G7","created_at":"2026-07-05T04:17:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:REHDR3G7JDWJHBZCVRFTROPLDJ","target":"record","payload":{"canonical_record":{"source":{"id":"2111.13241","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-25T20:30:30Z","cross_cats_sorted":[],"title_canon_sha256":"f25b187ea9d7560abe146d66e1581b10fa6d8fada5e2adf9981de9ff7d1c4541","abstract_canon_sha256":"290664ecb71ce0a2042c9bda77b88906784d18c4c2f5ce63ade7b6b2936ca756"},"schema_version":"1.0"},"canonical_sha256":"890e38ecdf48ec938722ac4b38b9eb1a597b3c53ca11bc6d45dc663e8b2c725f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:17:03.607888Z","signature_b64":"622iDyTck7CGSSkOV9na+pnxirha1QeX2DYJX4NWlD/1Y1Q5xsUhH0alUm5birr2uwmOBjHCx4Ntv9P2Y1/GCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"890e38ecdf48ec938722ac4b38b9eb1a597b3c53ca11bc6d45dc663e8b2c725f","last_reissued_at":"2026-07-05T04:17:03.607407Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:17:03.607407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.13241","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":"2026-07-05T04:17:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F3P+kJmMgSbEAMfd3gr2WcMWntYV4LGC3X3To89PXc5RVQEiGxijMXuAsn+hnHP8k/SMTO3zDYyw6BEGZE7FBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T09:19:15.655699Z"},"content_sha256":"eb563df87dd06baa882e194dad19f4859bc84112864b8354e246eff5bac0aa8f","schema_version":"1.0","event_id":"sha256:eb563df87dd06baa882e194dad19f4859bc84112864b8354e246eff5bac0aa8f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:REHDR3G7JDWJHBZCVRFTROPLDJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning from Temporal Gradient for Semi-supervised Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Ju He, Junfei Xiao, Lin Zhang, Longlong Jing, Qi She, Yingwei Li, Zongwei Zhou","submitted_at":"2021-11-25T20:30:30Z","abstract_excerpt":"Semi-supervised video action recognition tends to enable deep neural networks to achieve remarkable performance even with very limited labeled data. However, existing methods are mainly transferred from current image-based methods (e.g., FixMatch). Without specifically utilizing the temporal dynamics and inherent multimodal attributes, their results could be suboptimal. To better leverage the encoded temporal information in videos, we introduce temporal gradient as an additional modality for more attentive feature extraction in this paper. To be specific, our method explicitly distills the fin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.13241","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/2111.13241/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":"2026-07-05T04:17:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+/HtnsQLOmcRhGZcwdOz6HksDQa1RFPmn+8ygHB3CTLOzWQDgyoamzz5JPxPSMhMZMFyrG2sVrJKxELlV1YpDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T09:19:15.656079Z"},"content_sha256":"507d054a7e2bf561d48870b63c7cb707b49169e9838327db7ce72ebe80e1a508","schema_version":"1.0","event_id":"sha256:507d054a7e2bf561d48870b63c7cb707b49169e9838327db7ce72ebe80e1a508"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/REHDR3G7JDWJHBZCVRFTROPLDJ/bundle.json","state_url":"https://pith.science/pith/REHDR3G7JDWJHBZCVRFTROPLDJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/REHDR3G7JDWJHBZCVRFTROPLDJ/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":"2026-07-09T09:19:15Z","links":{"resolver":"https://pith.science/pith/REHDR3G7JDWJHBZCVRFTROPLDJ","bundle":"https://pith.science/pith/REHDR3G7JDWJHBZCVRFTROPLDJ/bundle.json","state":"https://pith.science/pith/REHDR3G7JDWJHBZCVRFTROPLDJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/REHDR3G7JDWJHBZCVRFTROPLDJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:REHDR3G7JDWJHBZCVRFTROPLDJ","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":"290664ecb71ce0a2042c9bda77b88906784d18c4c2f5ce63ade7b6b2936ca756","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-25T20:30:30Z","title_canon_sha256":"f25b187ea9d7560abe146d66e1581b10fa6d8fada5e2adf9981de9ff7d1c4541"},"schema_version":"1.0","source":{"id":"2111.13241","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.13241","created_at":"2026-07-05T04:17:03Z"},{"alias_kind":"arxiv_version","alias_value":"2111.13241v3","created_at":"2026-07-05T04:17:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.13241","created_at":"2026-07-05T04:17:03Z"},{"alias_kind":"pith_short_12","alias_value":"REHDR3G7JDWJ","created_at":"2026-07-05T04:17:03Z"},{"alias_kind":"pith_short_16","alias_value":"REHDR3G7JDWJHBZC","created_at":"2026-07-05T04:17:03Z"},{"alias_kind":"pith_short_8","alias_value":"REHDR3G7","created_at":"2026-07-05T04:17:03Z"}],"graph_snapshots":[{"event_id":"sha256:507d054a7e2bf561d48870b63c7cb707b49169e9838327db7ce72ebe80e1a508","target":"graph","created_at":"2026-07-05T04:17:03Z","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/2111.13241/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Semi-supervised video action recognition tends to enable deep neural networks to achieve remarkable performance even with very limited labeled data. However, existing methods are mainly transferred from current image-based methods (e.g., FixMatch). Without specifically utilizing the temporal dynamics and inherent multimodal attributes, their results could be suboptimal. To better leverage the encoded temporal information in videos, we introduce temporal gradient as an additional modality for more attentive feature extraction in this paper. To be specific, our method explicitly distills the fin","authors_text":"Alan Yuille, Ju He, Junfei Xiao, Lin Zhang, Longlong Jing, Qi She, Yingwei Li, Zongwei Zhou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-25T20:30:30Z","title":"Learning from Temporal Gradient for Semi-supervised Action Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.13241","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:eb563df87dd06baa882e194dad19f4859bc84112864b8354e246eff5bac0aa8f","target":"record","created_at":"2026-07-05T04:17:03Z","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":"290664ecb71ce0a2042c9bda77b88906784d18c4c2f5ce63ade7b6b2936ca756","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-25T20:30:30Z","title_canon_sha256":"f25b187ea9d7560abe146d66e1581b10fa6d8fada5e2adf9981de9ff7d1c4541"},"schema_version":"1.0","source":{"id":"2111.13241","kind":"arxiv","version":3}},"canonical_sha256":"890e38ecdf48ec938722ac4b38b9eb1a597b3c53ca11bc6d45dc663e8b2c725f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"890e38ecdf48ec938722ac4b38b9eb1a597b3c53ca11bc6d45dc663e8b2c725f","first_computed_at":"2026-07-05T04:17:03.607407Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:17:03.607407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"622iDyTck7CGSSkOV9na+pnxirha1QeX2DYJX4NWlD/1Y1Q5xsUhH0alUm5birr2uwmOBjHCx4Ntv9P2Y1/GCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:17:03.607888Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.13241","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb563df87dd06baa882e194dad19f4859bc84112864b8354e246eff5bac0aa8f","sha256:507d054a7e2bf561d48870b63c7cb707b49169e9838327db7ce72ebe80e1a508"],"state_sha256":"9cd267c6044e080f0c1638890775df7f050d7b72f4b5fec84a4a0c689f2543f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t1W81TBQAXwe40kyc39R6k9S3167d+5MpAZDuKvn17a0PQA8FUejqfsHOOQDV+1VRi7l66laaD/ddu4bo4yvBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T09:19:15.658374Z","bundle_sha256":"502b327c4b45ddd5b71f13544070eef4a0f42216d54570db603f9e4920677c2d"}}