{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6UVCZJZGUYT4D3Y7BFTZJ7MBHX","short_pith_number":"pith:6UVCZJZG","canonical_record":{"source":{"id":"2409.16145","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-22T18:40:55Z","cross_cats_sorted":[],"title_canon_sha256":"d73373e2635a4eb637dccca446a8da5159746c22e1cf3b15b6a0c223c46a911b","abstract_canon_sha256":"c879569ce2663711649067c45feba94ea0e22df2e29bb15f7b1ca216ad5621e6"},"schema_version":"1.0"},"canonical_sha256":"f52a2ca726a627c1ef1f096794fd813df1c27608f02f20add748b081584e329f","source":{"kind":"arxiv","id":"2409.16145","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.16145","created_at":"2026-07-05T09:11:05Z"},{"alias_kind":"arxiv_version","alias_value":"2409.16145v1","created_at":"2026-07-05T09:11:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.16145","created_at":"2026-07-05T09:11:05Z"},{"alias_kind":"pith_short_12","alias_value":"6UVCZJZGUYT4","created_at":"2026-07-05T09:11:05Z"},{"alias_kind":"pith_short_16","alias_value":"6UVCZJZGUYT4D3Y7","created_at":"2026-07-05T09:11:05Z"},{"alias_kind":"pith_short_8","alias_value":"6UVCZJZG","created_at":"2026-07-05T09:11:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6UVCZJZGUYT4D3Y7BFTZJ7MBHX","target":"record","payload":{"canonical_record":{"source":{"id":"2409.16145","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-22T18:40:55Z","cross_cats_sorted":[],"title_canon_sha256":"d73373e2635a4eb637dccca446a8da5159746c22e1cf3b15b6a0c223c46a911b","abstract_canon_sha256":"c879569ce2663711649067c45feba94ea0e22df2e29bb15f7b1ca216ad5621e6"},"schema_version":"1.0"},"canonical_sha256":"f52a2ca726a627c1ef1f096794fd813df1c27608f02f20add748b081584e329f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:05.737379Z","signature_b64":"YCyQ2Qyj/IYI/o4coIWN1kCJdF+aNu3qI+858OuGl4Z9jlh5jYccAiypNYT9cnxmP+xAEyE8fP3auvygj9nKBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f52a2ca726a627c1ef1f096794fd813df1c27608f02f20add748b081584e329f","last_reissued_at":"2026-07-05T09:11:05.736835Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:05.736835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.16145","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":"2026-07-05T09:11:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H03xleha+w80yR3KQW7dT/z4Oz39fBStV4acNdSNIGHLN81p/mXZP8b7sZNmkWcejYGWXWOMOPOxAe+zr1+7DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:28:42.602119Z"},"content_sha256":"9ef4bc57240a67fa7ea0da15d219f0aca664b518d52e15245029a55dcfc0b489","schema_version":"1.0","event_id":"sha256:9ef4bc57240a67fa7ea0da15d219f0aca664b518d52e15245029a55dcfc0b489"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6UVCZJZGUYT4D3Y7BFTZJ7MBHX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Localize Actions in Instructional Videos with LLM-Based Multi-Pathway Text-Video Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deep Patel, Dimitris N. Metaxas, Kai Li, Martin Renqiang Min, Wentao Bao, Yu Kong, Yuxiao Chen","submitted_at":"2024-09-22T18:40:55Z","abstract_excerpt":"Learning to localize temporal boundaries of procedure steps in instructional videos is challenging due to the limited availability of annotated large-scale training videos. Recent works focus on learning the cross-modal alignment between video segments and ASR-transcripted narration texts through contrastive learning. However, these methods fail to account for the alignment noise, i.e., irrelevant narrations to the instructional task in videos and unreliable timestamps in narrations. To address these challenges, this work proposes a novel training framework. Motivated by the strong capabilitie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.16145","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/2409.16145/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":"2026-07-05T09:11:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CrUN82XEZd+GgrjW2bWnVr1F3F/aLZRrFJI82MhEMagGnEYZesz963dJmak/+FPdCikcfhQ4spnQSY1urnBNAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:28:42.602514Z"},"content_sha256":"72b13f6891a4e55c26af5b48661df2c20771646618162d8107d3b0105c0451fd","schema_version":"1.0","event_id":"sha256:72b13f6891a4e55c26af5b48661df2c20771646618162d8107d3b0105c0451fd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6UVCZJZGUYT4D3Y7BFTZJ7MBHX/bundle.json","state_url":"https://pith.science/pith/6UVCZJZGUYT4D3Y7BFTZJ7MBHX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6UVCZJZGUYT4D3Y7BFTZJ7MBHX/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":"2026-07-07T08:28:42Z","links":{"resolver":"https://pith.science/pith/6UVCZJZGUYT4D3Y7BFTZJ7MBHX","bundle":"https://pith.science/pith/6UVCZJZGUYT4D3Y7BFTZJ7MBHX/bundle.json","state":"https://pith.science/pith/6UVCZJZGUYT4D3Y7BFTZJ7MBHX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6UVCZJZGUYT4D3Y7BFTZJ7MBHX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6UVCZJZGUYT4D3Y7BFTZJ7MBHX","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":"c879569ce2663711649067c45feba94ea0e22df2e29bb15f7b1ca216ad5621e6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-22T18:40:55Z","title_canon_sha256":"d73373e2635a4eb637dccca446a8da5159746c22e1cf3b15b6a0c223c46a911b"},"schema_version":"1.0","source":{"id":"2409.16145","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.16145","created_at":"2026-07-05T09:11:05Z"},{"alias_kind":"arxiv_version","alias_value":"2409.16145v1","created_at":"2026-07-05T09:11:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.16145","created_at":"2026-07-05T09:11:05Z"},{"alias_kind":"pith_short_12","alias_value":"6UVCZJZGUYT4","created_at":"2026-07-05T09:11:05Z"},{"alias_kind":"pith_short_16","alias_value":"6UVCZJZGUYT4D3Y7","created_at":"2026-07-05T09:11:05Z"},{"alias_kind":"pith_short_8","alias_value":"6UVCZJZG","created_at":"2026-07-05T09:11:05Z"}],"graph_snapshots":[{"event_id":"sha256:72b13f6891a4e55c26af5b48661df2c20771646618162d8107d3b0105c0451fd","target":"graph","created_at":"2026-07-05T09:11:05Z","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/2409.16145/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning to localize temporal boundaries of procedure steps in instructional videos is challenging due to the limited availability of annotated large-scale training videos. Recent works focus on learning the cross-modal alignment between video segments and ASR-transcripted narration texts through contrastive learning. However, these methods fail to account for the alignment noise, i.e., irrelevant narrations to the instructional task in videos and unreliable timestamps in narrations. To address these challenges, this work proposes a novel training framework. Motivated by the strong capabilitie","authors_text":"Deep Patel, Dimitris N. Metaxas, Kai Li, Martin Renqiang Min, Wentao Bao, Yu Kong, Yuxiao Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-22T18:40:55Z","title":"Learning to Localize Actions in Instructional Videos with LLM-Based Multi-Pathway Text-Video Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.16145","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":"sha256:9ef4bc57240a67fa7ea0da15d219f0aca664b518d52e15245029a55dcfc0b489","target":"record","created_at":"2026-07-05T09:11:05Z","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":"c879569ce2663711649067c45feba94ea0e22df2e29bb15f7b1ca216ad5621e6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-22T18:40:55Z","title_canon_sha256":"d73373e2635a4eb637dccca446a8da5159746c22e1cf3b15b6a0c223c46a911b"},"schema_version":"1.0","source":{"id":"2409.16145","kind":"arxiv","version":1}},"canonical_sha256":"f52a2ca726a627c1ef1f096794fd813df1c27608f02f20add748b081584e329f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f52a2ca726a627c1ef1f096794fd813df1c27608f02f20add748b081584e329f","first_computed_at":"2026-07-05T09:11:05.736835Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:11:05.736835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YCyQ2Qyj/IYI/o4coIWN1kCJdF+aNu3qI+858OuGl4Z9jlh5jYccAiypNYT9cnxmP+xAEyE8fP3auvygj9nKBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:11:05.737379Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.16145","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ef4bc57240a67fa7ea0da15d219f0aca664b518d52e15245029a55dcfc0b489","sha256:72b13f6891a4e55c26af5b48661df2c20771646618162d8107d3b0105c0451fd"],"state_sha256":"93db3d03754a635c386eb2b01cbe0bd1405708c6e224d8c4028bb81aacd49762"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bywdfbuOPnpkOYlPQAwNhijRFFvcpPDCCz4IOWl/3tRLtWdS1BHOJqlyyq/SnijACSsH0wQAnDZxo3RppyqvBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:28:42.604426Z","bundle_sha256":"38d045bf3dc2d003b9fd6f70dded6f3ce03a7cc1e506f5dcb9e141e8e2f77c13"}}