{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:K7WFWCAUUPYVNFRRVP6G35QGTE","short_pith_number":"pith:K7WFWCAU","schema_version":"1.0","canonical_sha256":"57ec5b0814a3f1569631abfc6df606993c948cf47c45501ce139634499de5533","source":{"kind":"arxiv","id":"2407.06704","version":2},"attestation_state":"computed","paper":{"title":"Self-supervised visual learning from interactions with objects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Arthur Aubret, C\\'eline Teuli\\`ere, Jochen Triesch","submitted_at":"2024-07-09T09:31:15Z","abstract_excerpt":"Self-supervised learning (SSL) has revolutionized visual representation learning, but has not achieved the robustness of human vision. A reason for this could be that SSL does not leverage all the data available to humans during learning. When learning about an object, humans often purposefully turn or move around objects and research suggests that these interactions can substantially enhance their learning. Here we explore whether such object-related actions can boost SSL. For this, we extract the actions performed to change from one ego-centric view of an object to another in four video data"},"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":"2407.06704","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-09T09:31:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d83f4ba67a37aac29190e2e8bb70076aeddfb76366a59aded4dea24cc191297f","abstract_canon_sha256":"295b1462ffdba271517a473218297abf2d2cd34fe9fd3686fceac08ddaf806e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:23.908171Z","signature_b64":"M3LCr1bT4tvf7ZVWvCrcAjFMR7aeXW4RELWEBZNHQKIjYGGvHqFtrY5YER6RPhvca3fLbXmkGIOCgL+mccjwCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57ec5b0814a3f1569631abfc6df606993c948cf47c45501ce139634499de5533","last_reissued_at":"2026-07-05T08:53:23.907759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:23.907759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-supervised visual learning from interactions with objects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Arthur Aubret, C\\'eline Teuli\\`ere, Jochen Triesch","submitted_at":"2024-07-09T09:31:15Z","abstract_excerpt":"Self-supervised learning (SSL) has revolutionized visual representation learning, but has not achieved the robustness of human vision. A reason for this could be that SSL does not leverage all the data available to humans during learning. When learning about an object, humans often purposefully turn or move around objects and research suggests that these interactions can substantially enhance their learning. Here we explore whether such object-related actions can boost SSL. For this, we extract the actions performed to change from one ego-centric view of an object to another in four video data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.06704","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/2407.06704/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":"2407.06704","created_at":"2026-07-05T08:53:23.907816+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.06704v2","created_at":"2026-07-05T08:53:23.907816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.06704","created_at":"2026-07-05T08:53:23.907816+00:00"},{"alias_kind":"pith_short_12","alias_value":"K7WFWCAUUPYV","created_at":"2026-07-05T08:53:23.907816+00:00"},{"alias_kind":"pith_short_16","alias_value":"K7WFWCAUUPYVNFRR","created_at":"2026-07-05T08:53:23.907816+00:00"},{"alias_kind":"pith_short_8","alias_value":"K7WFWCAU","created_at":"2026-07-05T08:53:23.907816+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.02966","citing_title":"Human Gaze Boosts Object-Centered Representation Learning","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K7WFWCAUUPYVNFRRVP6G35QGTE","json":"https://pith.science/pith/K7WFWCAUUPYVNFRRVP6G35QGTE.json","graph_json":"https://pith.science/api/pith-number/K7WFWCAUUPYVNFRRVP6G35QGTE/graph.json","events_json":"https://pith.science/api/pith-number/K7WFWCAUUPYVNFRRVP6G35QGTE/events.json","paper":"https://pith.science/paper/K7WFWCAU"},"agent_actions":{"view_html":"https://pith.science/pith/K7WFWCAUUPYVNFRRVP6G35QGTE","download_json":"https://pith.science/pith/K7WFWCAUUPYVNFRRVP6G35QGTE.json","view_paper":"https://pith.science/paper/K7WFWCAU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.06704&json=true","fetch_graph":"https://pith.science/api/pith-number/K7WFWCAUUPYVNFRRVP6G35QGTE/graph.json","fetch_events":"https://pith.science/api/pith-number/K7WFWCAUUPYVNFRRVP6G35QGTE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K7WFWCAUUPYVNFRRVP6G35QGTE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K7WFWCAUUPYVNFRRVP6G35QGTE/action/storage_attestation","attest_author":"https://pith.science/pith/K7WFWCAUUPYVNFRRVP6G35QGTE/action/author_attestation","sign_citation":"https://pith.science/pith/K7WFWCAUUPYVNFRRVP6G35QGTE/action/citation_signature","submit_replication":"https://pith.science/pith/K7WFWCAUUPYVNFRRVP6G35QGTE/action/replication_record"}},"created_at":"2026-07-05T08:53:23.907816+00:00","updated_at":"2026-07-05T08:53:23.907816+00:00"}