{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CGLAZUEP7T6UDKEY5N7LKSU2TW","short_pith_number":"pith:CGLAZUEP","schema_version":"1.0","canonical_sha256":"11960cd08ffcfd41a898eb7eb54a9a9d91c70e14fb573df2d03df81fcdc31bc4","source":{"kind":"arxiv","id":"2207.03552","version":1},"attestation_state":"computed","paper":{"title":"An Embedding-Dynamic Approach to Self-supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Domas Buracas, Jinkyu Kim, John Canny, Seunghyun Park, Suhong Moon","submitted_at":"2022-07-07T19:56:20Z","abstract_excerpt":"A number of recent self-supervised learning methods have shown impressive performance on image classification and other tasks. A somewhat bewildering variety of techniques have been used, not always with a clear understanding of the reasons for their benefits, especially when used in combination. Here we treat the embeddings of images as point particles and consider model optimization as a dynamic process on this system of particles. Our dynamic model combines an attractive force for similar images, a locally dispersive force to avoid local collapse, and a global dispersive force to achieve a "},"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":"2207.03552","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-07T19:56:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fc75c08f710a7d4dc7b12e8b0427c645a4c3bd1cb6a5ace955638ef5272119b4","abstract_canon_sha256":"6fc34f972b065c96fa223d219121c9c54416efc25d0eb20fbb737c85f03cb953"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:38:25.714925Z","signature_b64":"IJhDw0Z1jsFfbmBqWutbndNMimsNYNWv42+ut+/5LSICpjHMRzOwnfHcIEN+43vLDz/2/DPdV3X/mdSkjuKqBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11960cd08ffcfd41a898eb7eb54a9a9d91c70e14fb573df2d03df81fcdc31bc4","last_reissued_at":"2026-07-05T04:38:25.714520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:38:25.714520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Embedding-Dynamic Approach to Self-supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Domas Buracas, Jinkyu Kim, John Canny, Seunghyun Park, Suhong Moon","submitted_at":"2022-07-07T19:56:20Z","abstract_excerpt":"A number of recent self-supervised learning methods have shown impressive performance on image classification and other tasks. A somewhat bewildering variety of techniques have been used, not always with a clear understanding of the reasons for their benefits, especially when used in combination. Here we treat the embeddings of images as point particles and consider model optimization as a dynamic process on this system of particles. Our dynamic model combines an attractive force for similar images, a locally dispersive force to avoid local collapse, and a global dispersive force to achieve a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.03552","kind":"arxiv","version":1},"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/2207.03552/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":"2207.03552","created_at":"2026-07-05T04:38:25.714583+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.03552v1","created_at":"2026-07-05T04:38:25.714583+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.03552","created_at":"2026-07-05T04:38:25.714583+00:00"},{"alias_kind":"pith_short_12","alias_value":"CGLAZUEP7T6U","created_at":"2026-07-05T04:38:25.714583+00:00"},{"alias_kind":"pith_short_16","alias_value":"CGLAZUEP7T6UDKEY","created_at":"2026-07-05T04:38:25.714583+00:00"},{"alias_kind":"pith_short_8","alias_value":"CGLAZUEP","created_at":"2026-07-05T04:38:25.714583+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/CGLAZUEP7T6UDKEY5N7LKSU2TW","json":"https://pith.science/pith/CGLAZUEP7T6UDKEY5N7LKSU2TW.json","graph_json":"https://pith.science/api/pith-number/CGLAZUEP7T6UDKEY5N7LKSU2TW/graph.json","events_json":"https://pith.science/api/pith-number/CGLAZUEP7T6UDKEY5N7LKSU2TW/events.json","paper":"https://pith.science/paper/CGLAZUEP"},"agent_actions":{"view_html":"https://pith.science/pith/CGLAZUEP7T6UDKEY5N7LKSU2TW","download_json":"https://pith.science/pith/CGLAZUEP7T6UDKEY5N7LKSU2TW.json","view_paper":"https://pith.science/paper/CGLAZUEP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.03552&json=true","fetch_graph":"https://pith.science/api/pith-number/CGLAZUEP7T6UDKEY5N7LKSU2TW/graph.json","fetch_events":"https://pith.science/api/pith-number/CGLAZUEP7T6UDKEY5N7LKSU2TW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CGLAZUEP7T6UDKEY5N7LKSU2TW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CGLAZUEP7T6UDKEY5N7LKSU2TW/action/storage_attestation","attest_author":"https://pith.science/pith/CGLAZUEP7T6UDKEY5N7LKSU2TW/action/author_attestation","sign_citation":"https://pith.science/pith/CGLAZUEP7T6UDKEY5N7LKSU2TW/action/citation_signature","submit_replication":"https://pith.science/pith/CGLAZUEP7T6UDKEY5N7LKSU2TW/action/replication_record"}},"created_at":"2026-07-05T04:38:25.714583+00:00","updated_at":"2026-07-05T04:38:25.714583+00:00"}