{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:RPN6VRFBYFC663BSBJV7VT7DIB","short_pith_number":"pith:RPN6VRFB","schema_version":"1.0","canonical_sha256":"8bdbeac4a1c145ef6c320a6bfacfe3404f1f736700b9df0c0555535e91bc89e2","source":{"kind":"arxiv","id":"2007.13278","version":2},"attestation_state":"computed","paper":{"title":"Representation Learning with Video Deep InfoMax","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Philip Bachman, R Devon Hjelm","submitted_at":"2020-07-27T02:28:47Z","abstract_excerpt":"Self-supervised learning has made unsupervised pretraining relevant again for difficult computer vision tasks. The most effective self-supervised methods involve prediction tasks based on features extracted from diverse views of the data. DeepInfoMax (DIM) is a self-supervised method which leverages the internal structure of deep networks to construct such views, forming prediction tasks between local features which depend on small patches in an image and global features which depend on the whole image. In this paper, we extend DIM to the video domain by leveraging similar structure in spatio-"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2007.13278","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-27T02:28:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"41d66776d7af6c5ac800e7225aa84ffe5040306f6a87971f0a1cf6faaec2da60","abstract_canon_sha256":"29e1ed8a7ae30637cf88b6865f0c641c4e762e765935a64f52e563442e1588a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:22:52.090170Z","signature_b64":"soIb4W6s9vNYJpLuqYsCtl4pvQ8RZwYdUgJBxUuj1LKY6TIyqVWUjhot+WA0hp5RpmVnyD6PbBR0nmU5xpshDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bdbeac4a1c145ef6c320a6bfacfe3404f1f736700b9df0c0555535e91bc89e2","last_reissued_at":"2026-07-05T01:22:52.089815Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:22:52.089815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Representation Learning with Video Deep InfoMax","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Philip Bachman, R Devon Hjelm","submitted_at":"2020-07-27T02:28:47Z","abstract_excerpt":"Self-supervised learning has made unsupervised pretraining relevant again for difficult computer vision tasks. The most effective self-supervised methods involve prediction tasks based on features extracted from diverse views of the data. DeepInfoMax (DIM) is a self-supervised method which leverages the internal structure of deep networks to construct such views, forming prediction tasks between local features which depend on small patches in an image and global features which depend on the whole image. In this paper, we extend DIM to the video domain by leveraging similar structure in spatio-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.13278","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.13278/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2007.13278","created_at":"2026-07-05T01:22:52.089877+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.13278v2","created_at":"2026-07-05T01:22:52.089877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.13278","created_at":"2026-07-05T01:22:52.089877+00:00"},{"alias_kind":"pith_short_12","alias_value":"RPN6VRFBYFC6","created_at":"2026-07-05T01:22:52.089877+00:00"},{"alias_kind":"pith_short_16","alias_value":"RPN6VRFBYFC663BS","created_at":"2026-07-05T01:22:52.089877+00:00"},{"alias_kind":"pith_short_8","alias_value":"RPN6VRFB","created_at":"2026-07-05T01:22:52.089877+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RPN6VRFBYFC663BSBJV7VT7DIB","json":"https://pith.science/pith/RPN6VRFBYFC663BSBJV7VT7DIB.json","graph_json":"https://pith.science/api/pith-number/RPN6VRFBYFC663BSBJV7VT7DIB/graph.json","events_json":"https://pith.science/api/pith-number/RPN6VRFBYFC663BSBJV7VT7DIB/events.json","paper":"https://pith.science/paper/RPN6VRFB"},"agent_actions":{"view_html":"https://pith.science/pith/RPN6VRFBYFC663BSBJV7VT7DIB","download_json":"https://pith.science/pith/RPN6VRFBYFC663BSBJV7VT7DIB.json","view_paper":"https://pith.science/paper/RPN6VRFB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.13278&json=true","fetch_graph":"https://pith.science/api/pith-number/RPN6VRFBYFC663BSBJV7VT7DIB/graph.json","fetch_events":"https://pith.science/api/pith-number/RPN6VRFBYFC663BSBJV7VT7DIB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RPN6VRFBYFC663BSBJV7VT7DIB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RPN6VRFBYFC663BSBJV7VT7DIB/action/storage_attestation","attest_author":"https://pith.science/pith/RPN6VRFBYFC663BSBJV7VT7DIB/action/author_attestation","sign_citation":"https://pith.science/pith/RPN6VRFBYFC663BSBJV7VT7DIB/action/citation_signature","submit_replication":"https://pith.science/pith/RPN6VRFBYFC663BSBJV7VT7DIB/action/replication_record"}},"created_at":"2026-07-05T01:22:52.089877+00:00","updated_at":"2026-07-05T01:22:52.089877+00:00"}