{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:JUYZ4CXS4F7T3FHCWAMJ4FHRV5","short_pith_number":"pith:JUYZ4CXS","canonical_record":{"source":{"id":"1807.02800","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-08T11:12:51Z","cross_cats_sorted":[],"title_canon_sha256":"74c238925a0c0e6cbde76da739f29bd2a78f47ae77f5a62e1d6298566df6ca40","abstract_canon_sha256":"e33d58d8576f01be68f89dd87945f881e4757d62dbf01194c53b2c43380595af"},"schema_version":"1.0"},"canonical_sha256":"4d319e0af2e17f3d94e2b0189e14f1af615012adc1f218c1f5d88a0dd19a24d9","source":{"kind":"arxiv","id":"1807.02800","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.02800","created_at":"2026-05-18T00:00:08Z"},{"alias_kind":"arxiv_version","alias_value":"1807.02800v2","created_at":"2026-05-18T00:00:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.02800","created_at":"2026-05-18T00:00:08Z"},{"alias_kind":"pith_short_12","alias_value":"JUYZ4CXS4F7T","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"JUYZ4CXS4F7T3FHC","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"JUYZ4CXS","created_at":"2026-05-18T12:32:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:JUYZ4CXS4F7T3FHCWAMJ4FHRV5","target":"record","payload":{"canonical_record":{"source":{"id":"1807.02800","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-08T11:12:51Z","cross_cats_sorted":[],"title_canon_sha256":"74c238925a0c0e6cbde76da739f29bd2a78f47ae77f5a62e1d6298566df6ca40","abstract_canon_sha256":"e33d58d8576f01be68f89dd87945f881e4757d62dbf01194c53b2c43380595af"},"schema_version":"1.0"},"canonical_sha256":"4d319e0af2e17f3d94e2b0189e14f1af615012adc1f218c1f5d88a0dd19a24d9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:08.356165Z","signature_b64":"shh1MJB1sz2aN9GcsuENnAHPV+VRQVsZTauqy+0KTke5lQczeTYjxwAzed+x7bZe80wk4J+KcFapgMiHpyo2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d319e0af2e17f3d94e2b0189e14f1af615012adc1f218c1f5d88a0dd19a24d9","last_reissued_at":"2026-05-18T00:00:08.355713Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:08.355713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.02800","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":"2026-05-18T00:00:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"evn2BmrvMW4k56rqjNpDQg5u1lCUJPCWfnMiXjWg55NJamfzSfvJ7+2PtXkedBXryP5J/Jenb5Fe7OoFw8BfBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T11:45:27.042393Z"},"content_sha256":"cde9fe80037da118b0bfc4f71028dfb888f96dcd9906a19e920977acd46282c8","schema_version":"1.0","event_id":"sha256:cde9fe80037da118b0bfc4f71028dfb888f96dcd9906a19e920977acd46282c8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:JUYZ4CXS4F7T3FHCWAMJ4FHRV5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Spatio-Temporal Instance Learning: Action Tubes from Class Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cees G. M. Snoek, Pascal Mettes","submitted_at":"2018-07-08T11:12:51Z","abstract_excerpt":"The goal of this work is spatio-temporal action localization in videos, using only the supervision from video-level class labels. The state-of-the-art casts this weakly-supervised action localization regime as a Multiple Instance Learning problem, where instances are a priori computed spatio-temporal proposals. Rather than disconnecting the spatio-temporal learning from the training, we propose Spatio-Temporal Instance Learning, which enables action localization directly from box proposals in video frames. We outline the assumptions of our model and propose a max-margin objective and optimizat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.02800","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":"2026-05-18T00:00:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y8nLMw42I34ZHwQALLUjtI2S9LwTDmLonK3PuY8fm/Jdk9YDk2APC9GhNn4TAuw6Bn9XNHxvb1uX5VH9G6jRBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T11:45:27.042742Z"},"content_sha256":"11ba161150b6e48641b8ffaa4f391c80b8240aff66b4e0f84b6db4df9d91d11a","schema_version":"1.0","event_id":"sha256:11ba161150b6e48641b8ffaa4f391c80b8240aff66b4e0f84b6db4df9d91d11a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JUYZ4CXS4F7T3FHCWAMJ4FHRV5/bundle.json","state_url":"https://pith.science/pith/JUYZ4CXS4F7T3FHCWAMJ4FHRV5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JUYZ4CXS4F7T3FHCWAMJ4FHRV5/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":"2026-06-02T11:45:27Z","links":{"resolver":"https://pith.science/pith/JUYZ4CXS4F7T3FHCWAMJ4FHRV5","bundle":"https://pith.science/pith/JUYZ4CXS4F7T3FHCWAMJ4FHRV5/bundle.json","state":"https://pith.science/pith/JUYZ4CXS4F7T3FHCWAMJ4FHRV5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JUYZ4CXS4F7T3FHCWAMJ4FHRV5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:JUYZ4CXS4F7T3FHCWAMJ4FHRV5","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":"e33d58d8576f01be68f89dd87945f881e4757d62dbf01194c53b2c43380595af","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-08T11:12:51Z","title_canon_sha256":"74c238925a0c0e6cbde76da739f29bd2a78f47ae77f5a62e1d6298566df6ca40"},"schema_version":"1.0","source":{"id":"1807.02800","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.02800","created_at":"2026-05-18T00:00:08Z"},{"alias_kind":"arxiv_version","alias_value":"1807.02800v2","created_at":"2026-05-18T00:00:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.02800","created_at":"2026-05-18T00:00:08Z"},{"alias_kind":"pith_short_12","alias_value":"JUYZ4CXS4F7T","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"JUYZ4CXS4F7T3FHC","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"JUYZ4CXS","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:11ba161150b6e48641b8ffaa4f391c80b8240aff66b4e0f84b6db4df9d91d11a","target":"graph","created_at":"2026-05-18T00:00:08Z","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":"The goal of this work is spatio-temporal action localization in videos, using only the supervision from video-level class labels. The state-of-the-art casts this weakly-supervised action localization regime as a Multiple Instance Learning problem, where instances are a priori computed spatio-temporal proposals. Rather than disconnecting the spatio-temporal learning from the training, we propose Spatio-Temporal Instance Learning, which enables action localization directly from box proposals in video frames. We outline the assumptions of our model and propose a max-margin objective and optimizat","authors_text":"Cees G. M. Snoek, Pascal Mettes","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-08T11:12:51Z","title":"Spatio-Temporal Instance Learning: Action Tubes from Class Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.02800","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:cde9fe80037da118b0bfc4f71028dfb888f96dcd9906a19e920977acd46282c8","target":"record","created_at":"2026-05-18T00:00:08Z","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":"e33d58d8576f01be68f89dd87945f881e4757d62dbf01194c53b2c43380595af","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-08T11:12:51Z","title_canon_sha256":"74c238925a0c0e6cbde76da739f29bd2a78f47ae77f5a62e1d6298566df6ca40"},"schema_version":"1.0","source":{"id":"1807.02800","kind":"arxiv","version":2}},"canonical_sha256":"4d319e0af2e17f3d94e2b0189e14f1af615012adc1f218c1f5d88a0dd19a24d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d319e0af2e17f3d94e2b0189e14f1af615012adc1f218c1f5d88a0dd19a24d9","first_computed_at":"2026-05-18T00:00:08.355713Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:08.355713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"shh1MJB1sz2aN9GcsuENnAHPV+VRQVsZTauqy+0KTke5lQczeTYjxwAzed+x7bZe80wk4J+KcFapgMiHpyo2AQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:08.356165Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.02800","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cde9fe80037da118b0bfc4f71028dfb888f96dcd9906a19e920977acd46282c8","sha256:11ba161150b6e48641b8ffaa4f391c80b8240aff66b4e0f84b6db4df9d91d11a"],"state_sha256":"aa17b945787be4a3785aa83ecaf90deebb39ca498b1808726c91e7b5f2762ee0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"degstEIllGpd2gw/FRx/CetzA0k2YNh9Eo5fVD2kVx2IEFIjiLWBGk9rDu1eT+Tm1Hh+tyhXRE59Hzeo0R0cCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T11:45:27.044718Z","bundle_sha256":"86640c1c8ea81a8e3f1153c67c288f70f5243078e1befb19d4761989bf641002"}}