{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:4KPY2EA76IIHM3AGEUCM4P3DHT","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":"ba396ac638b686e508bf2daca1214295ec3ee0cb091bbdd58736372f9eeff825","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-29T20:36:13Z","title_canon_sha256":"2da403097054c63dba283c96219a17b189e24f60f2033b08fab6cf9ea02e6d42"},"schema_version":"1.0","source":{"id":"2205.00073","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.00073","created_at":"2026-07-05T04:19:09Z"},{"alias_kind":"arxiv_version","alias_value":"2205.00073v1","created_at":"2026-07-05T04:19:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.00073","created_at":"2026-07-05T04:19:09Z"},{"alias_kind":"pith_short_12","alias_value":"4KPY2EA76IIH","created_at":"2026-07-05T04:19:09Z"},{"alias_kind":"pith_short_16","alias_value":"4KPY2EA76IIHM3AG","created_at":"2026-07-05T04:19:09Z"},{"alias_kind":"pith_short_8","alias_value":"4KPY2EA7","created_at":"2026-07-05T04:19:09Z"}],"graph_snapshots":[{"event_id":"sha256:91d8d1931f60eb8f1612a5e014dc060d5941f390f1ff0082c876e582d0eedd2d","target":"graph","created_at":"2026-07-05T04:19:09Z","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/2205.00073/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The abundance and ease of utilizing sound, along with the fact that auditory clues reveal a plethora of information about what happens in a scene, make the audio-visual space an intuitive choice for representation learning. In this paper, we explore the efficacy of audio-visual self-supervised learning from uncurated long-form content i.e movies. Studying its differences with conventional short-form content, we identify a non-i.i.d distribution of data, driven by the nature of movies. Specifically, we find long-form content to naturally contain a diverse set of semantic concepts (semantic dive","authors_text":"Ashok Chandrashekar, Lingyi Liu, Mahdi M. Kalayeh, Nagendra Kamath, Shervin Ardeshir","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-29T20:36:13Z","title":"On Negative Sampling for Audio-Visual Contrastive Learning from Movies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.00073","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":"sha256:1180f1fab336c9cf787ae90f068d36382cf818f91dc7189c639bcfd5793a3410","target":"record","created_at":"2026-07-05T04:19:09Z","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":"ba396ac638b686e508bf2daca1214295ec3ee0cb091bbdd58736372f9eeff825","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-29T20:36:13Z","title_canon_sha256":"2da403097054c63dba283c96219a17b189e24f60f2033b08fab6cf9ea02e6d42"},"schema_version":"1.0","source":{"id":"2205.00073","kind":"arxiv","version":1}},"canonical_sha256":"e29f8d101ff210766c062504ce3f633cf16d637d6e302426d288813a129d1ec1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e29f8d101ff210766c062504ce3f633cf16d637d6e302426d288813a129d1ec1","first_computed_at":"2026-07-05T04:19:09.422532Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:19:09.422532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bV2XMCmihA+AjdHfL77+D3HbXiOoq6P8hsCviWzzQi40pSJNiJXOm5FTeOryDVBa5/DDExI9m8B3Hko5b3BYDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:19:09.422996Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.00073","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1180f1fab336c9cf787ae90f068d36382cf818f91dc7189c639bcfd5793a3410","sha256:91d8d1931f60eb8f1612a5e014dc060d5941f390f1ff0082c876e582d0eedd2d"],"state_sha256":"4f2432fd20604a22364819380dd939b665556dd69f945b187c5c92ab90d373d0"}