{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SBSUKLGLS3LCHNJNOOAL3OGR4J","short_pith_number":"pith:SBSUKLGL","canonical_record":{"source":{"id":"2310.03940","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-05T23:09:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a9b3f48d6ba1d01561577e779ccca3c6e8840e4187506c864f4567d9985b7263","abstract_canon_sha256":"ab1ca587d7667c1eb3163c8f30b68a9c64dcb3dcb3889bc7c2462f1181755261"},"schema_version":"1.0"},"canonical_sha256":"9065452ccb96d623b52d7380bdb8d1e273f36c4601a8aae24ba742f70c933aa6","source":{"kind":"arxiv","id":"2310.03940","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.03940","created_at":"2026-07-05T10:10:21Z"},{"alias_kind":"arxiv_version","alias_value":"2310.03940v6","created_at":"2026-07-05T10:10:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03940","created_at":"2026-07-05T10:10:21Z"},{"alias_kind":"pith_short_12","alias_value":"SBSUKLGLS3LC","created_at":"2026-07-05T10:10:21Z"},{"alias_kind":"pith_short_16","alias_value":"SBSUKLGLS3LCHNJN","created_at":"2026-07-05T10:10:21Z"},{"alias_kind":"pith_short_8","alias_value":"SBSUKLGL","created_at":"2026-07-05T10:10:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SBSUKLGLS3LCHNJNOOAL3OGR4J","target":"record","payload":{"canonical_record":{"source":{"id":"2310.03940","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-05T23:09:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a9b3f48d6ba1d01561577e779ccca3c6e8840e4187506c864f4567d9985b7263","abstract_canon_sha256":"ab1ca587d7667c1eb3163c8f30b68a9c64dcb3dcb3889bc7c2462f1181755261"},"schema_version":"1.0"},"canonical_sha256":"9065452ccb96d623b52d7380bdb8d1e273f36c4601a8aae24ba742f70c933aa6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:21.919082Z","signature_b64":"gMFzT+jf/HClR8szSEa6T7wXC7RhSkLeO+RXKdRyGtwb8koWW785wu44yDk/ci/n2XhHOIzYKAPSbz+EyR4WAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9065452ccb96d623b52d7380bdb8d1e273f36c4601a8aae24ba742f70c933aa6","last_reissued_at":"2026-07-05T10:10:21.918643Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:21.918643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.03940","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:10:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"chhv/gzrXcwGVnn2bk1Ya/w6lA32ZTQ5EzdToCDD5/ze2hhi775rB15Z7z3qFcrnL2VAFlc7RuIMcJdTPpr4BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T23:29:51.705149Z"},"content_sha256":"7ec3b1d14427d9ac535ad40df9e3c69decd4b6a036f4fb5e0256ff7674fac966","schema_version":"1.0","event_id":"sha256:7ec3b1d14427d9ac535ad40df9e3c69decd4b6a036f4fb5e0256ff7674fac966"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SBSUKLGLS3LCHNJNOOAL3OGR4J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Random Augmentations: Pretraining with Hard Views","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fabio Ferreira, Frank Hutter, Ivo Rapant, J\\\"org K. H. Franke","submitted_at":"2023-10-05T23:09:19Z","abstract_excerpt":"Self-Supervised Learning (SSL) methods typically rely on random image augmentations, or views, to make models invariant to different transformations. We hypothesize that the efficacy of pretraining pipelines based on conventional random view sampling can be enhanced by explicitly selecting views that benefit the learning progress. A simple yet effective approach is to select hard views that yield a higher loss. In this paper, we propose Hard View Pretraining (HVP), a learning-free strategy that extends random view generation by exposing models to more challenging samples during SSL pretraining"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03940","kind":"arxiv","version":6},"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/2310.03940/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":"2026-07-05T10:10:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZfcpyGOQ9PwseTr501K7wVnesZ/KrT2v8myrmQyTapRbYbzdm0HSfX804shAECAbOJqeBGI8bvGh+9ALXiqcCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T23:29:51.705477Z"},"content_sha256":"d1d95f07b93b9949c72a72cf300368f3fe7069a0129598f8dc2462cc48f13919","schema_version":"1.0","event_id":"sha256:d1d95f07b93b9949c72a72cf300368f3fe7069a0129598f8dc2462cc48f13919"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SBSUKLGLS3LCHNJNOOAL3OGR4J/bundle.json","state_url":"https://pith.science/pith/SBSUKLGLS3LCHNJNOOAL3OGR4J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SBSUKLGLS3LCHNJNOOAL3OGR4J/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":"2026-08-19T23:29:51Z","links":{"resolver":"https://pith.science/pith/SBSUKLGLS3LCHNJNOOAL3OGR4J","bundle":"https://pith.science/pith/SBSUKLGLS3LCHNJNOOAL3OGR4J/bundle.json","state":"https://pith.science/pith/SBSUKLGLS3LCHNJNOOAL3OGR4J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SBSUKLGLS3LCHNJNOOAL3OGR4J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SBSUKLGLS3LCHNJNOOAL3OGR4J","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":"ab1ca587d7667c1eb3163c8f30b68a9c64dcb3dcb3889bc7c2462f1181755261","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-05T23:09:19Z","title_canon_sha256":"a9b3f48d6ba1d01561577e779ccca3c6e8840e4187506c864f4567d9985b7263"},"schema_version":"1.0","source":{"id":"2310.03940","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.03940","created_at":"2026-07-05T10:10:21Z"},{"alias_kind":"arxiv_version","alias_value":"2310.03940v6","created_at":"2026-07-05T10:10:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03940","created_at":"2026-07-05T10:10:21Z"},{"alias_kind":"pith_short_12","alias_value":"SBSUKLGLS3LC","created_at":"2026-07-05T10:10:21Z"},{"alias_kind":"pith_short_16","alias_value":"SBSUKLGLS3LCHNJN","created_at":"2026-07-05T10:10:21Z"},{"alias_kind":"pith_short_8","alias_value":"SBSUKLGL","created_at":"2026-07-05T10:10:21Z"}],"graph_snapshots":[{"event_id":"sha256:d1d95f07b93b9949c72a72cf300368f3fe7069a0129598f8dc2462cc48f13919","target":"graph","created_at":"2026-07-05T10:10:21Z","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/2310.03940/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-Supervised Learning (SSL) methods typically rely on random image augmentations, or views, to make models invariant to different transformations. We hypothesize that the efficacy of pretraining pipelines based on conventional random view sampling can be enhanced by explicitly selecting views that benefit the learning progress. A simple yet effective approach is to select hard views that yield a higher loss. In this paper, we propose Hard View Pretraining (HVP), a learning-free strategy that extends random view generation by exposing models to more challenging samples during SSL pretraining","authors_text":"Fabio Ferreira, Frank Hutter, Ivo Rapant, J\\\"org K. H. Franke","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-05T23:09:19Z","title":"Beyond Random Augmentations: Pretraining with Hard Views"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03940","kind":"arxiv","version":6},"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":"sha256:7ec3b1d14427d9ac535ad40df9e3c69decd4b6a036f4fb5e0256ff7674fac966","target":"record","created_at":"2026-07-05T10:10:21Z","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":"ab1ca587d7667c1eb3163c8f30b68a9c64dcb3dcb3889bc7c2462f1181755261","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-05T23:09:19Z","title_canon_sha256":"a9b3f48d6ba1d01561577e779ccca3c6e8840e4187506c864f4567d9985b7263"},"schema_version":"1.0","source":{"id":"2310.03940","kind":"arxiv","version":6}},"canonical_sha256":"9065452ccb96d623b52d7380bdb8d1e273f36c4601a8aae24ba742f70c933aa6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9065452ccb96d623b52d7380bdb8d1e273f36c4601a8aae24ba742f70c933aa6","first_computed_at":"2026-07-05T10:10:21.918643Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:21.918643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gMFzT+jf/HClR8szSEa6T7wXC7RhSkLeO+RXKdRyGtwb8koWW785wu44yDk/ci/n2XhHOIzYKAPSbz+EyR4WAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:21.919082Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.03940","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ec3b1d14427d9ac535ad40df9e3c69decd4b6a036f4fb5e0256ff7674fac966","sha256:d1d95f07b93b9949c72a72cf300368f3fe7069a0129598f8dc2462cc48f13919"],"state_sha256":"5896e57a996b4123e56f6ee28facfc790f2c8a019424b4364103a176fd8ad0c6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fQWRB/plIYxRgYSuPQW6z9cmNTzLkrWLl8mePsQapGdWkjMCdc2LMxPmB+3Y32wzctQ/MZer4zQ0RGZLzszXAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T23:29:51.708711Z","bundle_sha256":"6ae9ed87ee7b7421f166d11ffd46ed5bec4bc5e9126895d2c664d80bd8d5ac06"}}