{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:XKJO234NU2O4GFR6MOIT4CZWW6","short_pith_number":"pith:XKJO234N","canonical_record":{"source":{"id":"1504.08023","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-04-29T21:01:51Z","cross_cats_sorted":[],"title_canon_sha256":"856385e1a32ce13279278aa2b42eb23bf9e04b6738cd049d2fec43932227de7e","abstract_canon_sha256":"bed5331a5520624b89c709aa4d8f3780d343dd5a78d7575ed418a9003e822331"},"schema_version":"1.0"},"canonical_sha256":"ba92ed6f8da69dc3163e63913e0b36b78de77b961355531905354eb79aa5eebf","source":{"kind":"arxiv","id":"1504.08023","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1504.08023","created_at":"2026-05-18T00:56:12Z"},{"alias_kind":"arxiv_version","alias_value":"1504.08023v2","created_at":"2026-05-18T00:56:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1504.08023","created_at":"2026-05-18T00:56:12Z"},{"alias_kind":"pith_short_12","alias_value":"XKJO234NU2O4","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_16","alias_value":"XKJO234NU2O4GFR6","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_8","alias_value":"XKJO234N","created_at":"2026-05-18T12:29:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:XKJO234NU2O4GFR6MOIT4CZWW6","target":"record","payload":{"canonical_record":{"source":{"id":"1504.08023","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-04-29T21:01:51Z","cross_cats_sorted":[],"title_canon_sha256":"856385e1a32ce13279278aa2b42eb23bf9e04b6738cd049d2fec43932227de7e","abstract_canon_sha256":"bed5331a5520624b89c709aa4d8f3780d343dd5a78d7575ed418a9003e822331"},"schema_version":"1.0"},"canonical_sha256":"ba92ed6f8da69dc3163e63913e0b36b78de77b961355531905354eb79aa5eebf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:56:12.545463Z","signature_b64":"edYZzwhF2CVrD0Clsn6d+f64gAHGqxkNAql8yOTNdj2O1wudMLt2DrwWkVl8PYOhdB4p09y7JxcQ7CyGcICpAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba92ed6f8da69dc3163e63913e0b36b78de77b961355531905354eb79aa5eebf","last_reissued_at":"2026-05-18T00:56:12.544839Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:56:12.544839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1504.08023","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":"2026-05-18T00:56:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"09w2NtPgM62hukLz3N87e3V6uoTwd25WeKmxUyFRrewbMtYil7lKnsoa2neyelKvk/+D+VySA7nqY4ZoVCqqAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T04:21:12.904588Z"},"content_sha256":"3375cd6319e1a3e66c8e5715865546416541e21d5381f2eb36379777b3f5044e","schema_version":"1.0","event_id":"sha256:3375cd6319e1a3e66c8e5715865546416541e21d5381f2eb36379777b3f5044e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:XKJO234NU2O4GFR6MOIT4CZWW6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Anticipating Visual Representations from Unlabeled Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antonio Torralba, Carl Vondrick, Hamed Pirsiavash","submitted_at":"2015-04-29T21:01:51Z","abstract_excerpt":"Anticipating actions and objects before they start or appear is a difficult problem in computer vision with several real-world applications. This task is challenging partly because it requires leveraging extensive knowledge of the world that is difficult to write down. We believe that a promising resource for efficiently learning this knowledge is through readily available unlabeled video. We present a framework that capitalizes on temporal structure in unlabeled video to learn to anticipate human actions and objects. The key idea behind our approach is that we can train deep networks to predi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1504.08023","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":"2026-05-18T00:56:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gx6/7P4sPB3mNCTtRWP5FKgMfS47gPx13b2tRK6Ubb60/ANCD0hJ5qp0WmWwlo56/1CX88JkHrND4y7EGMxSDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T04:21:12.905189Z"},"content_sha256":"1696f17a4851bed42fdd7bdf637f35804a48ca625b31e10d26f0fab6446836d7","schema_version":"1.0","event_id":"sha256:1696f17a4851bed42fdd7bdf637f35804a48ca625b31e10d26f0fab6446836d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XKJO234NU2O4GFR6MOIT4CZWW6/bundle.json","state_url":"https://pith.science/pith/XKJO234NU2O4GFR6MOIT4CZWW6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XKJO234NU2O4GFR6MOIT4CZWW6/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":"2026-06-06T04:21:12Z","links":{"resolver":"https://pith.science/pith/XKJO234NU2O4GFR6MOIT4CZWW6","bundle":"https://pith.science/pith/XKJO234NU2O4GFR6MOIT4CZWW6/bundle.json","state":"https://pith.science/pith/XKJO234NU2O4GFR6MOIT4CZWW6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XKJO234NU2O4GFR6MOIT4CZWW6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:XKJO234NU2O4GFR6MOIT4CZWW6","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":"bed5331a5520624b89c709aa4d8f3780d343dd5a78d7575ed418a9003e822331","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-04-29T21:01:51Z","title_canon_sha256":"856385e1a32ce13279278aa2b42eb23bf9e04b6738cd049d2fec43932227de7e"},"schema_version":"1.0","source":{"id":"1504.08023","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1504.08023","created_at":"2026-05-18T00:56:12Z"},{"alias_kind":"arxiv_version","alias_value":"1504.08023v2","created_at":"2026-05-18T00:56:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1504.08023","created_at":"2026-05-18T00:56:12Z"},{"alias_kind":"pith_short_12","alias_value":"XKJO234NU2O4","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_16","alias_value":"XKJO234NU2O4GFR6","created_at":"2026-05-18T12:29:50Z"},{"alias_kind":"pith_short_8","alias_value":"XKJO234N","created_at":"2026-05-18T12:29:50Z"}],"graph_snapshots":[{"event_id":"sha256:1696f17a4851bed42fdd7bdf637f35804a48ca625b31e10d26f0fab6446836d7","target":"graph","created_at":"2026-05-18T00:56:12Z","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":"Anticipating actions and objects before they start or appear is a difficult problem in computer vision with several real-world applications. This task is challenging partly because it requires leveraging extensive knowledge of the world that is difficult to write down. We believe that a promising resource for efficiently learning this knowledge is through readily available unlabeled video. We present a framework that capitalizes on temporal structure in unlabeled video to learn to anticipate human actions and objects. The key idea behind our approach is that we can train deep networks to predi","authors_text":"Antonio Torralba, Carl Vondrick, Hamed Pirsiavash","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-04-29T21:01:51Z","title":"Anticipating Visual Representations from Unlabeled Video"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1504.08023","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":"sha256:3375cd6319e1a3e66c8e5715865546416541e21d5381f2eb36379777b3f5044e","target":"record","created_at":"2026-05-18T00:56:12Z","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":"bed5331a5520624b89c709aa4d8f3780d343dd5a78d7575ed418a9003e822331","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-04-29T21:01:51Z","title_canon_sha256":"856385e1a32ce13279278aa2b42eb23bf9e04b6738cd049d2fec43932227de7e"},"schema_version":"1.0","source":{"id":"1504.08023","kind":"arxiv","version":2}},"canonical_sha256":"ba92ed6f8da69dc3163e63913e0b36b78de77b961355531905354eb79aa5eebf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba92ed6f8da69dc3163e63913e0b36b78de77b961355531905354eb79aa5eebf","first_computed_at":"2026-05-18T00:56:12.544839Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:56:12.544839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"edYZzwhF2CVrD0Clsn6d+f64gAHGqxkNAql8yOTNdj2O1wudMLt2DrwWkVl8PYOhdB4p09y7JxcQ7CyGcICpAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:56:12.545463Z","signed_message":"canonical_sha256_bytes"},"source_id":"1504.08023","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3375cd6319e1a3e66c8e5715865546416541e21d5381f2eb36379777b3f5044e","sha256:1696f17a4851bed42fdd7bdf637f35804a48ca625b31e10d26f0fab6446836d7"],"state_sha256":"816ffe0ba54ffdb23820ebb243defaf2186c56a61f0b12a193b6667f0a0f11e7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FY3ZdlQVbqGJaCUnivBl8uO21mudrSwOAkeqGQXNMpZeXBCiofcIpEXnGMQtWXgZ7Qr8szjtBEyPxgYGbFeUBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T04:21:12.909173Z","bundle_sha256":"678c0c3701d6ad69a6143160c0971b5f78d11054252843b0204246416d37520c"}}