{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:NRDVDU7OPJJBPAKNTIO7EIOLEY","short_pith_number":"pith:NRDVDU7O","canonical_record":{"source":{"id":"2106.08513","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-16T02:00:11Z","cross_cats_sorted":[],"title_canon_sha256":"19c6945ded7734440158b2e13bbca8d33f4962fb801aa0d4aa6c350c9fd456b9","abstract_canon_sha256":"4c312165c348b904cc3659f6af986d0e0c13a14b1bb385b1e24b4d53282262a9"},"schema_version":"1.0"},"canonical_sha256":"6c4751d3ee7a5217814d9a1df221cb26004501b6c7dbee516255792a03ea3870","source":{"kind":"arxiv","id":"2106.08513","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.08513","created_at":"2026-07-05T02:49:58Z"},{"alias_kind":"arxiv_version","alias_value":"2106.08513v1","created_at":"2026-07-05T02:49:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.08513","created_at":"2026-07-05T02:49:58Z"},{"alias_kind":"pith_short_12","alias_value":"NRDVDU7OPJJB","created_at":"2026-07-05T02:49:58Z"},{"alias_kind":"pith_short_16","alias_value":"NRDVDU7OPJJBPAKN","created_at":"2026-07-05T02:49:58Z"},{"alias_kind":"pith_short_8","alias_value":"NRDVDU7O","created_at":"2026-07-05T02:49:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:NRDVDU7OPJJBPAKNTIO7EIOLEY","target":"record","payload":{"canonical_record":{"source":{"id":"2106.08513","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-16T02:00:11Z","cross_cats_sorted":[],"title_canon_sha256":"19c6945ded7734440158b2e13bbca8d33f4962fb801aa0d4aa6c350c9fd456b9","abstract_canon_sha256":"4c312165c348b904cc3659f6af986d0e0c13a14b1bb385b1e24b4d53282262a9"},"schema_version":"1.0"},"canonical_sha256":"6c4751d3ee7a5217814d9a1df221cb26004501b6c7dbee516255792a03ea3870","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:58.764729Z","signature_b64":"ii0E6H3tG+EfLgUEuQ+WyNYMMV/P8UHAs673wEd3RvK9y4w/BTOEE2aNKPZK4YmOmiMs64kQtAd/QAFVMO3oAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c4751d3ee7a5217814d9a1df221cb26004501b6c7dbee516255792a03ea3870","last_reissued_at":"2026-07-05T02:49:58.764249Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:58.764249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.08513","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":"2026-07-05T02:49:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"76ljmT7n9ZoYA1kTmY11FInqmg40mPDR1/UlyJtMH4J4x5FbT3n09ks8OyT+SKOS+2d3XPOarm5Db4vIahmoBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T14:42:35.829052Z"},"content_sha256":"06ebe901f80203d81deb82d63afbc8e191e1ee4c763e06648f989374d45863f7","schema_version":"1.0","event_id":"sha256:06ebe901f80203d81deb82d63afbc8e191e1ee4c763e06648f989374d45863f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:NRDVDU7OPJJBPAKNTIO7EIOLEY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Watching Too Much Television is Good: Self-Supervised Audio-Visual Representation Learning from Movies and TV Shows","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ashok Chandrashekar, Lingyi Liu, Mahdi M. Kalayeh, Nagendra Kamath","submitted_at":"2021-06-16T02:00:11Z","abstract_excerpt":"The abundance and ease of utilizing sound, along with the fact that auditory clues reveal so much about what happens in the scene, make the audio-visual space a perfectly intuitive choice for self-supervised representation learning. However, the current literature suggests that training on \\textit{uncurated} data yields considerably poorer representations compared to the \\textit{curated} alternatives collected in supervised manner, and the gap only narrows when the volume of data significantly increases. Furthermore, the quality of learned representations is known to be heavily influenced by t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.08513","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/2106.08513/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":"2026-07-05T02:49:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M16FgcgMgf1KZXlueXjLHFQB1yOyE0lWR/gjPrNe5XQwToN2Ku0UiweYuTWMv+r83C/4g8zFjJ7BEmVoZ149Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T14:42:35.829568Z"},"content_sha256":"6e997cd6097c1fb6040f1ae46954116ebe38a1980b308e487344caa8da818ce0","schema_version":"1.0","event_id":"sha256:6e997cd6097c1fb6040f1ae46954116ebe38a1980b308e487344caa8da818ce0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NRDVDU7OPJJBPAKNTIO7EIOLEY/bundle.json","state_url":"https://pith.science/pith/NRDVDU7OPJJBPAKNTIO7EIOLEY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NRDVDU7OPJJBPAKNTIO7EIOLEY/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":"2026-08-23T14:42:35Z","links":{"resolver":"https://pith.science/pith/NRDVDU7OPJJBPAKNTIO7EIOLEY","bundle":"https://pith.science/pith/NRDVDU7OPJJBPAKNTIO7EIOLEY/bundle.json","state":"https://pith.science/pith/NRDVDU7OPJJBPAKNTIO7EIOLEY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NRDVDU7OPJJBPAKNTIO7EIOLEY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NRDVDU7OPJJBPAKNTIO7EIOLEY","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":"4c312165c348b904cc3659f6af986d0e0c13a14b1bb385b1e24b4d53282262a9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-16T02:00:11Z","title_canon_sha256":"19c6945ded7734440158b2e13bbca8d33f4962fb801aa0d4aa6c350c9fd456b9"},"schema_version":"1.0","source":{"id":"2106.08513","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.08513","created_at":"2026-07-05T02:49:58Z"},{"alias_kind":"arxiv_version","alias_value":"2106.08513v1","created_at":"2026-07-05T02:49:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.08513","created_at":"2026-07-05T02:49:58Z"},{"alias_kind":"pith_short_12","alias_value":"NRDVDU7OPJJB","created_at":"2026-07-05T02:49:58Z"},{"alias_kind":"pith_short_16","alias_value":"NRDVDU7OPJJBPAKN","created_at":"2026-07-05T02:49:58Z"},{"alias_kind":"pith_short_8","alias_value":"NRDVDU7O","created_at":"2026-07-05T02:49:58Z"}],"graph_snapshots":[{"event_id":"sha256:6e997cd6097c1fb6040f1ae46954116ebe38a1980b308e487344caa8da818ce0","target":"graph","created_at":"2026-07-05T02:49:58Z","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/2106.08513/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 so much about what happens in the scene, make the audio-visual space a perfectly intuitive choice for self-supervised representation learning. However, the current literature suggests that training on \\textit{uncurated} data yields considerably poorer representations compared to the \\textit{curated} alternatives collected in supervised manner, and the gap only narrows when the volume of data significantly increases. Furthermore, the quality of learned representations is known to be heavily influenced by t","authors_text":"Ashok Chandrashekar, Lingyi Liu, Mahdi M. Kalayeh, Nagendra Kamath","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-16T02:00:11Z","title":"Watching Too Much Television is Good: Self-Supervised Audio-Visual Representation Learning from Movies and TV Shows"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.08513","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":"sha256:06ebe901f80203d81deb82d63afbc8e191e1ee4c763e06648f989374d45863f7","target":"record","created_at":"2026-07-05T02:49:58Z","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":"4c312165c348b904cc3659f6af986d0e0c13a14b1bb385b1e24b4d53282262a9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-16T02:00:11Z","title_canon_sha256":"19c6945ded7734440158b2e13bbca8d33f4962fb801aa0d4aa6c350c9fd456b9"},"schema_version":"1.0","source":{"id":"2106.08513","kind":"arxiv","version":1}},"canonical_sha256":"6c4751d3ee7a5217814d9a1df221cb26004501b6c7dbee516255792a03ea3870","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c4751d3ee7a5217814d9a1df221cb26004501b6c7dbee516255792a03ea3870","first_computed_at":"2026-07-05T02:49:58.764249Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:49:58.764249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ii0E6H3tG+EfLgUEuQ+WyNYMMV/P8UHAs673wEd3RvK9y4w/BTOEE2aNKPZK4YmOmiMs64kQtAd/QAFVMO3oAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:49:58.764729Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.08513","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:06ebe901f80203d81deb82d63afbc8e191e1ee4c763e06648f989374d45863f7","sha256:6e997cd6097c1fb6040f1ae46954116ebe38a1980b308e487344caa8da818ce0"],"state_sha256":"b5cf860fbaf1186efaee0b0fdf2905d3ef6c97366d16cb06fa37c9975a806300"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dJU2TS35mgSe3BtHHcbqJZO5XHR1sHG4g0b16SlOH6/nbNh1Pjd+jhEsDxi5yEgUMvfVUDDOWlNidn+xd3llCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T14:42:35.835001Z","bundle_sha256":"6dbcb8f3b1e116541671c4f88b98d98dac920ff471dfdc620ccf26aa58d84b0b"}}