{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HRWK4MKSUQKAI2P2KLUJ3BX2OO","short_pith_number":"pith:HRWK4MKS","schema_version":"1.0","canonical_sha256":"3c6cae3152a4140469fa52e89d86fa73833bb832c47e79713ddb9d929125ebcd","source":{"kind":"arxiv","id":"2501.12254","version":3},"attestation_state":"computed","paper":{"title":"Memory Storyboard: Leveraging Temporal Segmentation for Streaming Self-Supervised Learning from Egocentric Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Mengye Ren, Yanlai Yang","submitted_at":"2025-01-21T16:19:38Z","abstract_excerpt":"Self-supervised learning holds the promise of learning good representations from real-world continuous uncurated data streams. However, most existing works in visual self-supervised learning focus on static images or artificial data streams. Towards exploring a more realistic learning substrate, we investigate streaming self-supervised learning from long-form real-world egocentric video streams. Inspired by the event segmentation mechanism in human perception and memory, we propose \"Memory Storyboard\" that groups recent past frames into temporal segments for more effective summarization of the"},"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":"2501.12254","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-21T16:19:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"aee7f10110d1e8705f17ec8867a3a387849fbb4e3cf34c23ed312028ddf1ba47","abstract_canon_sha256":"93b5cd3f91ed72139d2c3838a831c35d7409787b8e9f5199d45d42b7e81033dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:17.065854Z","signature_b64":"z4gmYd+IOgRtt3k3vQmPcn6w66gap5N01SYnRkvK5Z7Xt3Nc0WbDwf0zgAlKLoJ4QSf7PzkwFY2re/y1JAeHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c6cae3152a4140469fa52e89d86fa73833bb832c47e79713ddb9d929125ebcd","last_reissued_at":"2026-07-05T11:52:17.065336Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:17.065336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory Storyboard: Leveraging Temporal Segmentation for Streaming Self-Supervised Learning from Egocentric Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Mengye Ren, Yanlai Yang","submitted_at":"2025-01-21T16:19:38Z","abstract_excerpt":"Self-supervised learning holds the promise of learning good representations from real-world continuous uncurated data streams. However, most existing works in visual self-supervised learning focus on static images or artificial data streams. Towards exploring a more realistic learning substrate, we investigate streaming self-supervised learning from long-form real-world egocentric video streams. Inspired by the event segmentation mechanism in human perception and memory, we propose \"Memory Storyboard\" that groups recent past frames into temporal segments for more effective summarization of the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12254","kind":"arxiv","version":3},"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/2501.12254/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":"2501.12254","created_at":"2026-07-05T11:52:17.065401+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.12254v3","created_at":"2026-07-05T11:52:17.065401+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12254","created_at":"2026-07-05T11:52:17.065401+00:00"},{"alias_kind":"pith_short_12","alias_value":"HRWK4MKSUQKA","created_at":"2026-07-05T11:52:17.065401+00:00"},{"alias_kind":"pith_short_16","alias_value":"HRWK4MKSUQKAI2P2","created_at":"2026-07-05T11:52:17.065401+00:00"},{"alias_kind":"pith_short_8","alias_value":"HRWK4MKS","created_at":"2026-07-05T11:52:17.065401+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05115","citing_title":"Continual Visual and Verbal Learning Through a Child's Egocentric Input","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08342","citing_title":"EgoEverything: A Benchmark for Human Behavior Inspired Long Context Egocentric Video Understanding in AR Environment","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HRWK4MKSUQKAI2P2KLUJ3BX2OO","json":"https://pith.science/pith/HRWK4MKSUQKAI2P2KLUJ3BX2OO.json","graph_json":"https://pith.science/api/pith-number/HRWK4MKSUQKAI2P2KLUJ3BX2OO/graph.json","events_json":"https://pith.science/api/pith-number/HRWK4MKSUQKAI2P2KLUJ3BX2OO/events.json","paper":"https://pith.science/paper/HRWK4MKS"},"agent_actions":{"view_html":"https://pith.science/pith/HRWK4MKSUQKAI2P2KLUJ3BX2OO","download_json":"https://pith.science/pith/HRWK4MKSUQKAI2P2KLUJ3BX2OO.json","view_paper":"https://pith.science/paper/HRWK4MKS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.12254&json=true","fetch_graph":"https://pith.science/api/pith-number/HRWK4MKSUQKAI2P2KLUJ3BX2OO/graph.json","fetch_events":"https://pith.science/api/pith-number/HRWK4MKSUQKAI2P2KLUJ3BX2OO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HRWK4MKSUQKAI2P2KLUJ3BX2OO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HRWK4MKSUQKAI2P2KLUJ3BX2OO/action/storage_attestation","attest_author":"https://pith.science/pith/HRWK4MKSUQKAI2P2KLUJ3BX2OO/action/author_attestation","sign_citation":"https://pith.science/pith/HRWK4MKSUQKAI2P2KLUJ3BX2OO/action/citation_signature","submit_replication":"https://pith.science/pith/HRWK4MKSUQKAI2P2KLUJ3BX2OO/action/replication_record"}},"created_at":"2026-07-05T11:52:17.065401+00:00","updated_at":"2026-07-05T11:52:17.065401+00:00"}