{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:WXPIB7JYKLJ2AJQO7UJJ6PFMXO","short_pith_number":"pith:WXPIB7JY","canonical_record":{"source":{"id":"2110.10596","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-20T14:45:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"65299f85cba1e947fbc8a5c39a413b2967619757332ce92bde561a5fa2e6f8eb","abstract_canon_sha256":"cf378edc00d3ea5c29438665b2b3e1a0bbd9c03c63ed6e99381368fcf34f9735"},"schema_version":"1.0"},"canonical_sha256":"b5de80fd3852d3a0260efd129f3cacbb9af02f6969b8c30295a8c1cb1a3a65e4","source":{"kind":"arxiv","id":"2110.10596","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.10596","created_at":"2026-07-05T03:36:57Z"},{"alias_kind":"arxiv_version","alias_value":"2110.10596v2","created_at":"2026-07-05T03:36:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.10596","created_at":"2026-07-05T03:36:57Z"},{"alias_kind":"pith_short_12","alias_value":"WXPIB7JYKLJ2","created_at":"2026-07-05T03:36:57Z"},{"alias_kind":"pith_short_16","alias_value":"WXPIB7JYKLJ2AJQO","created_at":"2026-07-05T03:36:57Z"},{"alias_kind":"pith_short_8","alias_value":"WXPIB7JY","created_at":"2026-07-05T03:36:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:WXPIB7JYKLJ2AJQO7UJJ6PFMXO","target":"record","payload":{"canonical_record":{"source":{"id":"2110.10596","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-20T14:45:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"65299f85cba1e947fbc8a5c39a413b2967619757332ce92bde561a5fa2e6f8eb","abstract_canon_sha256":"cf378edc00d3ea5c29438665b2b3e1a0bbd9c03c63ed6e99381368fcf34f9735"},"schema_version":"1.0"},"canonical_sha256":"b5de80fd3852d3a0260efd129f3cacbb9af02f6969b8c30295a8c1cb1a3a65e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:36:57.848412Z","signature_b64":"PrK/Adz2nxZksVppDyAQg9TS5uEnjitvATJq9IOP1QOAbpBUgxUFnFKL3QNzZEb8S4kiG3Y0nCrss5SQBNHACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5de80fd3852d3a0260efd129f3cacbb9af02f6969b8c30295a8c1cb1a3a65e4","last_reissued_at":"2026-07-05T03:36:57.847926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:36:57.847926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.10596","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:36:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+wdZU/k0XSJn5105phK0SHdb+ZjF9hU8dNdYRTkatqSe5GgSvKf+sPue49OdoFYcvSAkWSWb7NG48jeuUlxeBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T20:05:44.016842Z"},"content_sha256":"a7a339ca0a8154746e612ffa283b20d6c5c6c97e4d13fed444f6e14bf7a33412","schema_version":"1.0","event_id":"sha256:a7a339ca0a8154746e612ffa283b20d6c5c6c97e4d13fed444f6e14bf7a33412"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:WXPIB7JYKLJ2AJQO7UJJ6PFMXO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Look at What I'm Doing: Self-Supervised Spatial Grounding of Narrations in Instructional Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bryan A. Plummer, Bryan Russell, Hailin Jin, Kate Saenko, Reuben Tan","submitted_at":"2021-10-20T14:45:13Z","abstract_excerpt":"We introduce the task of spatially localizing narrated interactions in videos. Key to our approach is the ability to learn to spatially localize interactions with self-supervision on a large corpus of videos with accompanying transcribed narrations. To achieve this goal, we propose a multilayer cross-modal attention network that enables effective optimization of a contrastive loss during training. We introduce a divided strategy that alternates between computing inter- and intra-modal attention across the visual and natural language modalities, which allows effective training via directly cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.10596","kind":"arxiv","version":2},"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/2110.10596/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":"2026-07-05T03:36:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cBEayJGEf/dP3qLqBxa+/NU/yqnIFB9qYbdspM1RtrleVBFZIbHUmUCy/Hiq32oFjnN+fyydUItiJZUAyH21CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T20:05:44.017433Z"},"content_sha256":"788602a47e2c59aa2f2d107515fdb83ad2f7f1bace6f859348bcd788cf1c07a9","schema_version":"1.0","event_id":"sha256:788602a47e2c59aa2f2d107515fdb83ad2f7f1bace6f859348bcd788cf1c07a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WXPIB7JYKLJ2AJQO7UJJ6PFMXO/bundle.json","state_url":"https://pith.science/pith/WXPIB7JYKLJ2AJQO7UJJ6PFMXO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WXPIB7JYKLJ2AJQO7UJJ6PFMXO/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":"2026-08-19T20:05:44Z","links":{"resolver":"https://pith.science/pith/WXPIB7JYKLJ2AJQO7UJJ6PFMXO","bundle":"https://pith.science/pith/WXPIB7JYKLJ2AJQO7UJJ6PFMXO/bundle.json","state":"https://pith.science/pith/WXPIB7JYKLJ2AJQO7UJJ6PFMXO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WXPIB7JYKLJ2AJQO7UJJ6PFMXO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WXPIB7JYKLJ2AJQO7UJJ6PFMXO","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":"cf378edc00d3ea5c29438665b2b3e1a0bbd9c03c63ed6e99381368fcf34f9735","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-20T14:45:13Z","title_canon_sha256":"65299f85cba1e947fbc8a5c39a413b2967619757332ce92bde561a5fa2e6f8eb"},"schema_version":"1.0","source":{"id":"2110.10596","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.10596","created_at":"2026-07-05T03:36:57Z"},{"alias_kind":"arxiv_version","alias_value":"2110.10596v2","created_at":"2026-07-05T03:36:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.10596","created_at":"2026-07-05T03:36:57Z"},{"alias_kind":"pith_short_12","alias_value":"WXPIB7JYKLJ2","created_at":"2026-07-05T03:36:57Z"},{"alias_kind":"pith_short_16","alias_value":"WXPIB7JYKLJ2AJQO","created_at":"2026-07-05T03:36:57Z"},{"alias_kind":"pith_short_8","alias_value":"WXPIB7JY","created_at":"2026-07-05T03:36:57Z"}],"graph_snapshots":[{"event_id":"sha256:788602a47e2c59aa2f2d107515fdb83ad2f7f1bace6f859348bcd788cf1c07a9","target":"graph","created_at":"2026-07-05T03:36:57Z","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/2110.10596/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce the task of spatially localizing narrated interactions in videos. Key to our approach is the ability to learn to spatially localize interactions with self-supervision on a large corpus of videos with accompanying transcribed narrations. To achieve this goal, we propose a multilayer cross-modal attention network that enables effective optimization of a contrastive loss during training. We introduce a divided strategy that alternates between computing inter- and intra-modal attention across the visual and natural language modalities, which allows effective training via directly cont","authors_text":"Bryan A. Plummer, Bryan Russell, Hailin Jin, Kate Saenko, Reuben Tan","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-20T14:45:13Z","title":"Look at What I'm Doing: Self-Supervised Spatial Grounding of Narrations in Instructional Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.10596","kind":"arxiv","version":2},"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:a7a339ca0a8154746e612ffa283b20d6c5c6c97e4d13fed444f6e14bf7a33412","target":"record","created_at":"2026-07-05T03:36:57Z","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":"cf378edc00d3ea5c29438665b2b3e1a0bbd9c03c63ed6e99381368fcf34f9735","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-20T14:45:13Z","title_canon_sha256":"65299f85cba1e947fbc8a5c39a413b2967619757332ce92bde561a5fa2e6f8eb"},"schema_version":"1.0","source":{"id":"2110.10596","kind":"arxiv","version":2}},"canonical_sha256":"b5de80fd3852d3a0260efd129f3cacbb9af02f6969b8c30295a8c1cb1a3a65e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b5de80fd3852d3a0260efd129f3cacbb9af02f6969b8c30295a8c1cb1a3a65e4","first_computed_at":"2026-07-05T03:36:57.847926Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:36:57.847926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PrK/Adz2nxZksVppDyAQg9TS5uEnjitvATJq9IOP1QOAbpBUgxUFnFKL3QNzZEb8S4kiG3Y0nCrss5SQBNHACA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:36:57.848412Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.10596","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7a339ca0a8154746e612ffa283b20d6c5c6c97e4d13fed444f6e14bf7a33412","sha256:788602a47e2c59aa2f2d107515fdb83ad2f7f1bace6f859348bcd788cf1c07a9"],"state_sha256":"f30ed399393890092b7f2d96c557ef4ecefd76ef366a3b12538452cd839e8838"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZVi3yyXziwKTQ1pXt3zYKG9NncNtvv+vE8AgusPYQhvmTXY70s9ofrSd1BaxbObqodey4UPQYC588t9R5+CWDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T20:05:44.024534Z","bundle_sha256":"331817d4801126989f93a8ed707931346f63c9978b19dc57068aedd4a01aabae"}}