{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OCBE7EYVA74UV5R2LMW3JCFW2R","short_pith_number":"pith:OCBE7EYV","canonical_record":{"source":{"id":"2509.02029","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-02T07:17:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4677eb7d296e6c07c38d08cd2bc5fc1a3649cc880473d7561abd3721fd076704","abstract_canon_sha256":"9889b407ce050be676d52f3d462c448e5db5dcffc957c5a262cd315471fe7967"},"schema_version":"1.0"},"canonical_sha256":"70824f931507f94af63a5b2db488b6d46432768ebbeafdc5d7a148119f94cc13","source":{"kind":"arxiv","id":"2509.02029","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02029","created_at":"2026-07-05T12:03:13Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02029v1","created_at":"2026-07-05T12:03:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02029","created_at":"2026-07-05T12:03:13Z"},{"alias_kind":"pith_short_12","alias_value":"OCBE7EYVA74U","created_at":"2026-07-05T12:03:13Z"},{"alias_kind":"pith_short_16","alias_value":"OCBE7EYVA74UV5R2","created_at":"2026-07-05T12:03:13Z"},{"alias_kind":"pith_short_8","alias_value":"OCBE7EYV","created_at":"2026-07-05T12:03:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OCBE7EYVA74UV5R2LMW3JCFW2R","target":"record","payload":{"canonical_record":{"source":{"id":"2509.02029","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-02T07:17:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4677eb7d296e6c07c38d08cd2bc5fc1a3649cc880473d7561abd3721fd076704","abstract_canon_sha256":"9889b407ce050be676d52f3d462c448e5db5dcffc957c5a262cd315471fe7967"},"schema_version":"1.0"},"canonical_sha256":"70824f931507f94af63a5b2db488b6d46432768ebbeafdc5d7a148119f94cc13","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:13.250466Z","signature_b64":"Rzn6OcDquat5dmycp0/dLHMKARX5li2VcT/tGM8YFUS+hrOMZfA+PQ5lwuG+DpSmURxiDPF3Uu5NPZQDyZWpDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70824f931507f94af63a5b2db488b6d46432768ebbeafdc5d7a148119f94cc13","last_reissued_at":"2026-07-05T12:03:13.250027Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:13.250027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.02029","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:03:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k1JHfxdOd1o4ReHK60/jU0D/ZDliYTjFoV2wkm8Jl1jnTzmUqlWiToRP9ZnMfjOJzhTFoj0usu1e+26LbRwWCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:52:46.951274Z"},"content_sha256":"d049aad30580c68949540b05dea6958378bb125f5b004169c51729c8bdcf0926","schema_version":"1.0","event_id":"sha256:d049aad30580c68949540b05dea6958378bb125f5b004169c51729c8bdcf0926"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OCBE7EYVA74UV5R2LMW3JCFW2R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Andreas Floros, Kleanthis Marios Papadopoulos, Nikolaos Giakoumoglou, Tania Stathaki","submitted_at":"2025-09-02T07:17:46Z","abstract_excerpt":"This paper does not introduce a new method per se. Instead, we build on existing self-supervised learning approaches for vision, drawing inspiration from the adage \"fake it till you make it\". While contrastive self-supervised learning has achieved remarkable success, it typically relies on vast amounts of real-world data and carefully curated hard negatives. To explore alternatives to these requirements, we investigate two forms of \"faking it\" in vision transformers. First, we study the potential of generative models for unsupervised representation learning, leveraging synthetic data to augmen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02029","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/2509.02029/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:03:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AmgUYBcX15jeisc0pRJkMHt8PMCwIiY+eDdw0BcKCeA05wwsg6sb+O45HZIG5k4PE0D6vBAqIH0IpHl+wpzTCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:52:46.951831Z"},"content_sha256":"5de7f9173cb1d2e900ea20793f187efcfb5068bbb3eb928a40b3e86423835426","schema_version":"1.0","event_id":"sha256:5de7f9173cb1d2e900ea20793f187efcfb5068bbb3eb928a40b3e86423835426"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OCBE7EYVA74UV5R2LMW3JCFW2R/bundle.json","state_url":"https://pith.science/pith/OCBE7EYVA74UV5R2LMW3JCFW2R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OCBE7EYVA74UV5R2LMW3JCFW2R/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":"2026-08-08T08:52:46Z","links":{"resolver":"https://pith.science/pith/OCBE7EYVA74UV5R2LMW3JCFW2R","bundle":"https://pith.science/pith/OCBE7EYVA74UV5R2LMW3JCFW2R/bundle.json","state":"https://pith.science/pith/OCBE7EYVA74UV5R2LMW3JCFW2R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OCBE7EYVA74UV5R2LMW3JCFW2R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OCBE7EYVA74UV5R2LMW3JCFW2R","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":"9889b407ce050be676d52f3d462c448e5db5dcffc957c5a262cd315471fe7967","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-02T07:17:46Z","title_canon_sha256":"4677eb7d296e6c07c38d08cd2bc5fc1a3649cc880473d7561abd3721fd076704"},"schema_version":"1.0","source":{"id":"2509.02029","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02029","created_at":"2026-07-05T12:03:13Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02029v1","created_at":"2026-07-05T12:03:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02029","created_at":"2026-07-05T12:03:13Z"},{"alias_kind":"pith_short_12","alias_value":"OCBE7EYVA74U","created_at":"2026-07-05T12:03:13Z"},{"alias_kind":"pith_short_16","alias_value":"OCBE7EYVA74UV5R2","created_at":"2026-07-05T12:03:13Z"},{"alias_kind":"pith_short_8","alias_value":"OCBE7EYV","created_at":"2026-07-05T12:03:13Z"}],"graph_snapshots":[{"event_id":"sha256:5de7f9173cb1d2e900ea20793f187efcfb5068bbb3eb928a40b3e86423835426","target":"graph","created_at":"2026-07-05T12:03:13Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2509.02029/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper does not introduce a new method per se. Instead, we build on existing self-supervised learning approaches for vision, drawing inspiration from the adage \"fake it till you make it\". While contrastive self-supervised learning has achieved remarkable success, it typically relies on vast amounts of real-world data and carefully curated hard negatives. To explore alternatives to these requirements, we investigate two forms of \"faking it\" in vision transformers. First, we study the potential of generative models for unsupervised representation learning, leveraging synthetic data to augmen","authors_text":"Andreas Floros, Kleanthis Marios Papadopoulos, Nikolaos Giakoumoglou, Tania Stathaki","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02029","kind":"arxiv","version":1},"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:d049aad30580c68949540b05dea6958378bb125f5b004169c51729c8bdcf0926","target":"record","created_at":"2026-07-05T12:03:13Z","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":"9889b407ce050be676d52f3d462c448e5db5dcffc957c5a262cd315471fe7967","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-02T07:17:46Z","title_canon_sha256":"4677eb7d296e6c07c38d08cd2bc5fc1a3649cc880473d7561abd3721fd076704"},"schema_version":"1.0","source":{"id":"2509.02029","kind":"arxiv","version":1}},"canonical_sha256":"70824f931507f94af63a5b2db488b6d46432768ebbeafdc5d7a148119f94cc13","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70824f931507f94af63a5b2db488b6d46432768ebbeafdc5d7a148119f94cc13","first_computed_at":"2026-07-05T12:03:13.250027Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:13.250027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rzn6OcDquat5dmycp0/dLHMKARX5li2VcT/tGM8YFUS+hrOMZfA+PQ5lwuG+DpSmURxiDPF3Uu5NPZQDyZWpDg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:13.250466Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.02029","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d049aad30580c68949540b05dea6958378bb125f5b004169c51729c8bdcf0926","sha256:5de7f9173cb1d2e900ea20793f187efcfb5068bbb3eb928a40b3e86423835426"],"state_sha256":"4cc42807d34e9bd3034525291861251cfa6e277281d306822eee2c48bb5d0281"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"28eeRIrOC35s2WCHZ4NAqDg5HL1jjG3gt9zagWrFsyiuw32tzuF7DUBVIHeSQxmo1rUN8S7XazkTGKghBebODA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T08:52:46.957782Z","bundle_sha256":"9e6fa46e5f4116b2039ab6047f6fd4d64277e980fa6d2fe077694f2813a9cb78"}}